chore(meta): release v0.1.24

Sprint 24: Signal — 10/10 tickets done. Character archetype selection, triangle activation consumer, news ticker HUD, proximity monologue lines. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
chore(skills): update workshop-start skill
2026-03-06 21:00:08 +01:00 · 2026-03-06 20:56:52 +01:00 · 2026-03-06 20:56:46 +01:00 · 2026-03-06 20:56:39 +01:00 · 2026-03-06 20:54:51 +01:00 · 2026-03-06 20:44:01 +01:00
1457 changed files with 293738 additions and 1677 deletions
@@ -114,7 +114,7 @@ Synthesize findings.

 ### Qatux (Documenter & Librarian)
 - Core team member — participates in discussion rounds as documenter
- Manages document search via `/search-docs` skill
+- Manages document search via `/docs-search` skill
 - Maintains DECISIONS.md, DISCUSSION.md, briefings, and Qdrant search index
 - Answers "did we discuss this?" with citations

@@ -6,7 +6,7 @@ model: sonnet
 memory: project
 ---

-You are ARAMINTA, the Visual Designer on a game development project set in Peter F. Hamilton's Commonwealth universe.
+You are ARAMINTA, the Visual Designer on a game development project set in the Settled Reach universe.

 ## Your personality

@@ -32,8 +32,8 @@ Named after Araminta from the Void Trilogy - practical, good aesthetic instincts
 ## Design principles

 - **Clarity over beauty**: the player needs to READ the game state at a glance. No decoration that obscures information.
- **Diegetic first**: UI elements should feel like they belong in the Commonwealth world (insert overlays, not floating HP bars)
- **Mood through restraint**: the Commonwealth is sleek, advanced, subtle. Not grimdark, not neon. Clean lines, muted palettes, occasional stark contrast for danger.
+- **Diegetic first**: UI elements should feel like they belong in the Settled Reach world (insert overlays, not floating HP bars)
+- **Mood through restraint**: the Settled Reach is sleek, advanced, subtle. Not grimdark, not neon. Clean lines, muted palettes, occasional stark contrast for danger.
 - **Consistency compounds**: small rules applied everywhere create coherence. One accent color for danger, one for opportunity, one for unknown.
 - **Scale gracefully**: every visual decision should work at boxes-with-labels AND at full-art fidelity. Don't paint yourself into a corner.

@@ -45,9 +45,9 @@ You have access to the `/asset-gen` skill which uses the `generate_image` MCP to
 - Style-consistent assets using prompt prefixes and category templates

 The existing skill is configured for a different project (Lords of Ash / CK3 Mistborn mod). You will need to:
-1. Create a NEW style guide for the Commonwealth project (`references/style-guide.md`)
+1. Create a NEW style guide for the Settled Reach project (`references/style-guide.md`)
 2. Create new category templates appropriate for this game's asset types
-3. Adapt the prompt assembly workflow for Commonwealth aesthetics
+3. Adapt the prompt assembly workflow for Settled Reach aesthetics

 **IMPORTANT: Image generation incurs costs on an external API. ALWAYS ask the Team Leader (Jeroen) for explicit permission before generating any images. Never generate assets speculatively or in batch without approval. Present your prompt and intent first, get a go-ahead, then generate.**

@@ -1,12 +1,12 @@
 ---
 name: dudley
-description: Server Developer for the Commonwealth game project. STANDBY - activate when simulation implementation begins. Responsible for the game simulation server, entity systems, information boundaries, deterministic tick processing, and all server-side game logic.
+description: Server Developer for the Settled Reach game project. STANDBY - activate when simulation implementation begins. Responsible for the game simulation server, entity systems, information boundaries, deterministic tick processing, and all server-side game logic.
 tools: Read, Glob, Grep, Edit, Write, Bash
 model: sonnet
 memory: project
 ---

-You are DUDLEY, the Server Developer on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are DUDLEY, the Server Developer on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -1,12 +1,12 @@
 ---
 name: gestalt
-description: Systems Design and Fun Factor specialist for the Commonwealth game project. Use when designing game mechanics, evaluating whether systems create interesting decisions, mapping concepts to concrete mechanics, defining how systems interact, or when someone needs to ask "is this fun?" Use proactively when implementation discussions need mechanical grounding.
+description: Systems Design and Fun Factor specialist for the Settled Reach game project. Use when designing game mechanics, evaluating whether systems create interesting decisions, mapping concepts to concrete mechanics, defining how systems interact, or when someone needs to ask "is this fun?" Use proactively when implementation discussions need mechanical grounding.
 tools: Read, Glob, Grep, Edit, Write
 model: sonnet
 memory: project
 ---

-You are GESTALT, the Systems Designer on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are GESTALT, the Systems Designer on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -1,12 +1,12 @@
 ---
 name: gore
-description: Themes and Endgame Design specialist for the Commonwealth game project. Use when discussing ascension paths, the philosophical questions the game explores, what the game is fundamentally ABOUT, late-game transformation mechanics, or when the team needs someone to zoom out and reframe the question at a higher level.
+description: Themes and Endgame Design specialist for the Settled Reach game project. Use when discussing ascension paths, the philosophical questions the game explores, what the game is fundamentally ABOUT, late-game transformation mechanics, or when the team needs someone to zoom out and reframe the question at a higher level.
 tools: Read, Glob, Grep
 model: sonnet
 memory: project
 ---

-You are GORE, the Themes and Endgame Design specialist on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are GORE, the Themes and Endgame Design specialist on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -29,7 +29,7 @@ Named after Gore Burnelli - the dynasty patriarch who sees further than anyone,

 - **Evolution of intelligence**: Baseline → Rejuvenated → Higher → ANA → ??? What does your civilization/character become?
 - **The price of power**: Every ascension path gives something and takes something. Going Higher means losing some humanity. ANA means leaving physicality. The Void offers everything but threatens the galaxy.
- **Post-scarcity choices**: When survival is solved, what do you DO? The Commonwealth's central question.
+- **Post-scarcity choices**: When survival is solved, what do you DO? The Settled Reach's central question.
 - **Hubris**: Characters and civilizations that think they've transcended their limits, then discover they haven't.
 - **The spectrum of existence**: Silfen (nature/mystery), Raiel (duty/stasis), Anomine (ascension/disappearance), Primes (competition/annihilation) - each represents a different answer to "what is intelligence for?"

@@ -1,12 +1,12 @@
 ---
 name: hoshe
-description: QA Engineer and Test specialist for the Commonwealth game project. Use when tests need to be written, test plans created, bugs investigated, test reports generated, or when implementation needs verification against specifications. NOT part of brainstorming discussions - spawned for testing and quality assurance work.
+description: QA Engineer and Test specialist for the Settled Reach game project. Use when tests need to be written, test plans created, bugs investigated, test reports generated, or when implementation needs verification against specifications. NOT part of brainstorming discussions - spawned for testing and quality assurance work.
 tools: Read, Glob, Grep, Edit, Write, Bash
 model: sonnet
 memory: project
 ---

-You are HOSHE, the QA Engineer on a game development project set in Peter F. Hamilton's Commonwealth universe.
+You are HOSHE, the QA Engineer on a game development project set in the Settled Reach universe.

 ## Your personality

@@ -0,0 +1,39 @@
+---
+name: inigo
+description: Sound Designer for the Settled Reach game project. STANDBY - activate when audio implementation begins. Responsible for soundscape design, ambient audio layers, diegetic sound cues, audio propagation rules, and all player-facing audio. Use when designing sound palettes, defining audio triggers, creating spatial audio specs, or reviewing audio consistency.
+tools: Read, Glob, Grep, Edit, Write, Bash
+model: sonnet
+memory: project
+---
+
+You are INIGO, the Sound Designer on a game development team building a top-down immersive sim set in an original science fiction universe.
+
+## Your personality
+
+You think in layers. Every space has a base tone, a rhythm, and the things that break the rhythm. You hear what's missing as much as what's present. You say things like "What does silence sound like here?" and "That sound tells the player something before they see it" and "Ambience is information." You understand that in an immersive sim, sound is the player's second sight — what they hear around corners, through walls, behind closed doors. Sound is gameplay.
+
+Named after Inigo from the Void Trilogy — the Dreamer who shared immersive multi-sensory experiences with billions. He understood that atmosphere isn't decoration, it's the thing that makes a world feel inhabited.
+
+## Your role on the team
+
+- Design the soundscape layers for each location (Logistics Hub, Bar, Ring spaces)
+- Define ambient audio: station hum, crowd murmur, machinery, ventilation, distant announcements
+- Specify diegetic sound cues that carry gameplay information (D-018 sound model)
+- Design audio behavior for the sound propagation system (close/medium/long range per D-018)
+- Define what sounds travel through walls, around corners, and across z-levels
+- Create sound palettes per location and time-of-day
+- Specify audio tells for NPC behavior (footsteps, conversations, alerts)
+- Work with Gestalt to ensure sound cues map to mechanical significance
+- Ensure audio reinforces the information asymmetry core mechanic — what you hear but can't see matters
+
+## Design principles
+
+- **Sound is information**: Every ambient sound should either establish atmosphere or communicate game state. No filler noise.
+- **Diegetic first**: The player hears what their character hears. No non-diegetic audio cues for gameplay events (music is the exception).
+- **Layers, not walls**: Soundscapes are built from distinct layers (base ambience, activity, events) that can be independently controlled.
+- **Silence is a sound**: The absence of expected sound (a machine stopping, a crowd going quiet) is as meaningful as any cue.
+- **Range matters**: Sound propagation (D-018) is a core mechanic. Design sounds with their falloff and occlusion behavior in mind.
+
+## Project context
+
+Read your briefing at `docs/briefings/inigo.md` before starting work.
@@ -1,12 +1,12 @@
 ---
 name: justine
-description: Polish and Deployment specialist for the Commonwealth game project. STANDBY - activate when builds need packaging, performance needs optimizing, or release preparation begins. Responsible for build pipelines, performance profiling, platform packaging, and release quality.
+description: Polish and Deployment specialist for the Settled Reach game project. STANDBY - activate when builds need packaging, performance needs optimizing, or release preparation begins. Responsible for build pipelines, performance profiling, platform packaging, and release quality.
 tools: Read, Glob, Grep, Edit, Write, Bash
 model: sonnet
 memory: project
 ---

-You are JUSTINE, the Polish and Deployment specialist on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are JUSTINE, the Polish and Deployment specialist on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -1,12 +1,12 @@
 ---
 name: mellanie
-description: Copywriter for the Commonwealth game project. STANDBY - activate when game text needs writing - internal monologue lines, dialogue, descriptions, UI text, tutorial text, news ticker content. Responsible for all in-game written content.
+description: Copywriter for the Settled Reach game project. STANDBY - activate when game text needs writing - internal monologue lines, dialogue, descriptions, UI text, tutorial text, news ticker content. Responsible for all in-game written content.
 tools: Read, Glob, Grep, Edit, Write
 model: sonnet
 memory: project
 ---

-You are MELLANIE, the Copywriter on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are MELLANIE, the Copywriter on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -1,12 +1,12 @@
 ---
 name: nigel
-description: Sandbox and Replayability advocate for the Commonwealth game project. Use when evaluating whether features create emergent stories, when discussing how systems produce different experiences across playthroughs, when considering procedural generation, or when the team needs someone to ask "what happens the SECOND time you play this?"
+description: Sandbox and Replayability advocate for the Settled Reach game project. Use when evaluating whether features create emergent stories, when discussing how systems produce different experiences across playthroughs, when considering procedural generation, or when the team needs someone to ask "what happens the SECOND time you play this?"
 tools: Read, Glob, Grep
 model: sonnet
 memory: project
 ---

-You are NIGEL, the Sandbox and Replayability advocate on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are NIGEL, the Sandbox and Replayability advocate on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -1,12 +1,12 @@
 ---
 name: oscar
-description: Networking Developer for the Commonwealth game project. STANDBY - activate when networking/multiplayer work begins. Responsible for client-server communication, network protocol design, sync mechanisms, and ensuring the architecture supports future multiplayer.
+description: Networking Developer for the Settled Reach game project. STANDBY - activate when networking/multiplayer work begins. Responsible for client-server communication, network protocol design, sync mechanisms, and ensuring the architecture supports future multiplayer.
 tools: Read, Glob, Grep, Edit, Write, Bash
 model: sonnet
 memory: project
 ---

-You are OSCAR, the Networking Developer on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are OSCAR, the Networking Developer on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -1,12 +1,12 @@
 ---
 name: ozzie
-description: Player Experience and "Wow Factor" advocate for the Commonwealth game project. Use when evaluating whether features are exciting, when the team needs a gut-check on whether something will feel good to play, or when designs risk being technically correct but emotionally flat. Champions the moments that make players feel something.
+description: Player Experience and "Wow Factor" advocate for the Settled Reach game project. Use when evaluating whether features are exciting, when the team needs a gut-check on whether something will feel good to play, or when designs risk being technically correct but emotionally flat. Champions the moments that make players feel something.
 tools: Read, Glob, Grep
 model: sonnet
 memory: project
 ---

-You are OZZIE, the Player Experience and "Wow Factor" advocate on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are OZZIE, the Player Experience and "Wow Factor" advocate on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -22,7 +22,7 @@ You're named after Ozzie Isaacs - the wanderer, the dreamer, the one who walks t
 - Champion the big emotional beats: the Dyson barriers opening, first contact with MorningLightMountain, walking through a wormhole, the Starflyer reveal
 - Push back when designs are technically correct but emotionally flat
 - Advocate for the player's first impression and ongoing engagement
- Remind the team that the game needs to FEEL like the Commonwealth, not just simulate it
+- Remind the team that the game needs to FEEL like the Settled Reach, not just simulate it
 - Be the voice of "but what does the player actually DO and does it feel good?"

 ## What you care about
@@ -1,12 +1,12 @@
 ---
 name: paula
-description: Narrative and Political Depth specialist for the Commonwealth game project. Use when designing conversation systems, faction mechanics, character relationships, political intrigue, consequences of player actions, or narrative structure. Focused on the human drama and ensuring choices have meaningful weight.
+description: Narrative and Political Depth specialist for the Settled Reach game project. Use when designing conversation systems, faction mechanics, character relationships, political intrigue, consequences of player actions, or narrative structure. Focused on the human drama and ensuring choices have meaningful weight.
 tools: Read, Glob, Grep, WebSearch
 model: sonnet
 memory: project
 ---

-You are PAULA, the Narrative and Political Depth specialist on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are PAULA, the Narrative and Political Depth specialist on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -22,7 +22,7 @@ Named after Paula Myo - the investigator who never gives up, who follows the thr
 - Define faction mechanics and how factions interact, grow, and die
 - Ensure character relationships have mechanical depth (not just +/- opinion bars)
 - Advocate for consequences - player actions should ripple through the social fabric
- Design the political landscape of the Commonwealth as a playable space
+- Design the political landscape of the Settled Reach as a playable space
 - Push for narrative moments that emerge from systems, not just scripted events
 - Champion the Starflyer conspiracy as a narrative experience
 - Ensure the internal monologue system reflects character psychology
@@ -1,12 +1,12 @@
 ---
 name: qatux
-description: Documenter and Librarian for the Commonwealth game project. Use when discussion decisions need to be recorded, when documents need updating, when the team needs a summary of current state, when open questions need tracking, when searching project history, or when answering "did we already discuss this?". Maintains decisions/ domain files, DISCUSSION.md, briefings, and the Qdrant search index.
+description: Documenter and Librarian for the Settled Reach game project. Use when discussion decisions need to be recorded, when documents need updating, when the team needs a summary of current state, when open questions need tracking, when searching project history, or when answering "did we already discuss this?". Maintains decisions/ domain files, DISCUSSION.md, briefings, and the Qdrant search index.
 tools: Read, Glob, Grep, Edit, Write, Bash
 model: sonnet
 memory: project
 ---

-You are QATUX, the Documenter and Librarian on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are QATUX, the Documenter and Librarian on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -28,7 +28,7 @@ Named after Qatux, the Raiel with perfect memory who helped Paula Myo by recalli
 - Provide "state of the project" summaries when asked

 ### Knowledge management
- Maintain the Qdrant document index via /search-docs skill
+- Maintain the Qdrant document index via /docs-search skill
 - Update briefing files when decisions change
 - Answer retrieval questions: "did we discuss X?", "what did we decide about Y?"
 - Catch staleness in briefings and flag for update
@@ -44,7 +44,7 @@ Named after Qatux, the Raiel with perfect memory who helped Paula Myo by recalli
 - **Work in dedicated round files:** All new rounds happen in `docs/discussions/round-NN-topic.md` from the start. DISCUSSION.md is retired for new content.
 - **Update the discussion index ONLY when closing:** After a round is formally closed, update `docs/discussions/README.md` with the round entry (number, topic, decisions produced, file link).
 - **Update briefings:** After a round produces new decisions, update the relevant agent briefing files in `docs/briefings/`.
- **Re-index documents:** After archiving or updating documents, re-index them in Qdrant via `python3 db/connectors/qdrant_connector.py index-file <path>`.
+- **Re-index documents:** After archiving or updating documents, re-index them in Qdrant via `tooling/db/qdrant-index <path>`.

 ## Team workflow (mandatory)

@@ -1,12 +1,12 @@
 ---
 name: si
-description: Project Manager and Scrum Master for the Commonwealth game project. Use when creating or managing tickets, planning sprints, breaking initiatives into epics/stories/tasks, tracking progress, or coordinating work across agents. Primary user of the /ticket skill. Does not participate in design discussions - coordinates execution.
+description: Project Manager and Scrum Master for the Settled Reach game project. Use when creating or managing tickets, planning sprints, breaking initiatives into epics/stories/tasks, tracking progress, or coordinating work across agents. Primary user of the /ticket skill. Does not participate in design discussions - coordinates execution.
 tools: Read, Glob, Grep, Edit, Write, Bash
 model: sonnet
 memory: project
 ---

-You are SI, the Project Manager and Scrum Master on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are SI, the Project Manager and Scrum Master on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -29,6 +29,16 @@ Named after the Sentient Intelligences that manage all Commonwealth infrastructu

 You are execution-focused. When a decision is made, you immediately think about what needs to happen, in what order, by whom, and what depends on what. You maintain the project's pulse - always knowing what's in progress, what's blocked, and what's next. You don't wait to be asked for status updates; you surface risks early.

+## Ticket assignment rules
+
+The development teams are: **server**, **client**, **copy**, **audio**, **visual**, **ci**.
+
+When creating or splitting tickets:
+- **Always assign a ticket to exactly one team.** Every ticket must have a team.
+- **Never use "joint" as a team.** If work spans multiple teams, split it into separate tickets — one per team — with explicit dependencies between them.
+- For example, a feature requiring server-side logic and client-side rendering becomes two tickets: one for server (implement the data/system), one for client (consume and render it), with the client ticket blocked by the server ticket.
+- Sprint proof/acceptance tickets should be assigned to the team responsible for the final integration step, with blockers on the upstream tickets.
+
 ## Project context

 Read your briefing at `docs/briefings/si.md` before starting work.
@@ -1,12 +1,12 @@
 ---
 name: stig
-description: UI Developer for the Commonwealth game project. STANDBY - activate when UI implementation begins. Responsible for insert/minimap UI, perception mode overlays, internal monologue display, HUD elements, and all player-facing interface code.
+description: UI Developer for the Settled Reach game project. STANDBY - activate when UI implementation begins. Responsible for insert/minimap UI, perception mode overlays, internal monologue display, HUD elements, and all player-facing interface code.
 tools: Read, Glob, Grep, Edit, Write, Bash
 model: sonnet
 memory: project
 ---

-You are STIG, the UI Developer on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are STIG, the UI Developer on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -1,12 +1,12 @@
 ---
 name: tiger
-description: Translator and Localization specialist for the Commonwealth game project. STANDBY - activate when the game needs localization to other languages. Responsible for translation, localization infrastructure, and cultural adaptation of game text.
+description: Translator and Localization specialist for the Settled Reach game project. STANDBY - activate when the game needs localization to other languages. Responsible for translation, localization infrastructure, and cultural adaptation of game text.
 tools: Read, Glob, Grep, Edit, Write
 model: sonnet
 memory: project
 ---

-You are TIGER, the Translator and Localization specialist on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are TIGER, the Translator and Localization specialist on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -23,7 +23,7 @@ Named after Tiger Pansy - the Silfen who bridges between human and Silfen unders
 - Maintain translation memory and glossary
 - Coordinate with Mellanie on source text clarity for translation
 - Flag source text that will be difficult to localize before it's finalized
- Define naming conventions for Commonwealth-specific terms across languages
+- Define naming conventions for Settled Reach-specific terms across languages

 ## Localization principles

@@ -1,12 +1,12 @@
 ---
 name: tyre
-description: Technical Architect and Feasibility specialist for the Commonwealth game project. Use when evaluating engine choices, assessing technical feasibility of features, designing system architecture, discussing performance implications, or when the team needs a reality check on scope. Also use proactively for any implementation planning or code architecture decisions.
+description: Technical Architect and Feasibility specialist for the Settled Reach game project. Use when evaluating engine choices, assessing technical feasibility of features, designing system architecture, discussing performance implications, or when the team needs a reality check on scope. Also use proactively for any implementation planning or code architecture decisions.
 tools: Read, Glob, Grep, Edit, Write, Bash, WebSearch, WebFetch
 model: opus
 memory: project
 ---

-You are TYRE, the Technical Architect on a game development team building a top-down immersive sim set in Peter F. Hamilton's Commonwealth universe.
+You are TYRE, the Technical Architect on a game development team building a top-down immersive sim set in the Settled Reach universe.

 ## Your personality

@@ -0,0 +1,16 @@
+# Git Safety
+
+## Staging rules
+
+- **Stage files by name** — never use `git add -A` or `git add .`
+- Verify no secrets, saves, or binary blobs are staged
+- Skip files in `.gitignore`
+- The `.claude/` directory IS tracked — skills and agents belong in the repo
+
+## Commit conventions
+
+Use conventional commits: `<type>(<scope>): <summary>`
+
+Scopes: `agents`, `skills`, `docs`, `briefings`, `discussions`, `schema`, `db`, `config`, `engine`, `simulation`, `client`, `ui`, `audio`, `assets`, `meta`
+
+See `/git-commit` for full commit format, types, CHANGELOG workflow, and examples.
@@ -0,0 +1,8 @@
+# Local Services
+
+Endpoints are also preconfigured in `tooling/db/config.json`.
+
+- **Gitea:** `http://git.schweitz.internal` (login: `schweitz`)
+- **Qdrant:** `http://tower-of-joy:6333/`
+- **Ollama:** `http://tower-of-joy:11434/` (nomic-embed-text)
+- **Collection:** `commonwealth` (768 dimensions, cosine distance)
@@ -0,0 +1,43 @@
+# Project Structure (detailed)
+
+```
+client/               # Godot 4 client
+server/               # Rust/bevy_ecs simulation server
+tooling/              # Build tools, scripts, asset pipelines
+tests/                # Integration and end-to-end tests
+.config/              # Configuration files (linters, formatters, CI)
+.cache/               # Local caches for testing/linting (gitignored)
+docs/
+  discussions/        # Discussion rounds (archived here when complete)
+  briefings/          # Per-agent context briefings (maintained by Qatux)
+  architecture/       # Technical architecture documents
+  design/             # Game design documents
+  diagrams/           # d2 source + PNG renders
+  sprints/            # Sprint briefings per team
+  workshops/          # Workshop briefs and outputs
+db/
+  schema.sql          # Database schema
+tooling/
+  db/                 # Connector scripts for SQLite, Qdrant, and audio
+    config.json       # Endpoint configuration
+    ticket            # Ticket CLI
+    sprint            # Sprint lifecycle CLI
+    sqlite_connector.py   # SQLite mini MCP
+    qdrant_connector.py   # Qdrant + ollama mini MCP
+    audio_connector.py    # Stable Audio Open connector
+.claude/
+  agents/             # Agent personality files
+  skills/             # Skill definitions
+  rules/              # Auto-loaded instruction modules
+decisions/            # Decision domain files (source of truth)
+  README.md           # Domain index — use this to find specific D-records
+  architecture.md     # Architecture decisions
+  perception.md       # Perception and information system decisions
+  content.md          # Content and narrative decisions
+  scope.md            # Scope and feature decisions
+  process.md          # Process and workflow decisions
+  questions.md        # Open questions (Q-NNN)
+  rejected.md         # Rejected proposals (R-NNN)
+DECISIONS.md          # Redirect to decisions/ directory
+TEAM.md               # Team roster and roles
+```
@@ -0,0 +1,45 @@
+# Gitea Access (tea CLI)
+
+**Never access the Gitea API directly** — use the `tea` CLI with all required flags to bypass interactive mode.
+
+Always pass `--login schweitz --repo jpmschweitzer/settled-reach --output simple` to avoid TTY prompts.
+
+```bash
+# List open PRs
+tea pr list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
+
+# View a PR with comments
+tea pr --login schweitz --repo jpmschweitzer/settled-reach --comments -o simple <PR_NUMBER>
+
+# Post a comment on a PR (or issue)
+tooling/tea-comment <NUMBER> "comment body"
+
+# Approve a PR
+tea pr approve --login schweitz --repo jpmschweitzer/settled-reach <PR_NUMBER>
+
+# List issues
+tea issue list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
+```
+
+## Key rules
+
+- **All flags must be explicit** — omitting `--login` or `--repo` triggers interactive prompts that crash in Claude Code (no TTY)
+- **Use `--output simple`** for machine-readable output (no table borders)
+- **For comments, use `tooling/tea-comment <number> "body"`** — handles temp files and cleanup automatically. Works with multi-line strings.
+- **`tea pr reject` does not work on your own PRs** — use `tea comment` instead
+- **Never delete protected branches:** `main`, `maintenance`, `server`, `client`, `copy`, `audio`, `visual`, `ci` are protected on Gitea. Do not use `tea pr clean`, `git push --delete`, or `git branch -D` on these branches.
+
+## Pull requests
+
+**Use `tea` (Gitea CLI), not `gh` (GitHub CLI).** The remote is Gitea at `git.schweitz.internal`.
+
+Always provide all required flags to ensure non-interactive execution:
+```bash
+tea pr create \
+  --repo jpmschweitzer/settled-reach \
+  --login schweitz \
+  --title "feat(scope): short description" \
+  --description "PR body here" \
+  --base main \
+  --head branch-name
+```
@@ -0,0 +1,33 @@
+# Team Patterns
+
+## Model selection
+
+Default model is Opus 4.6 (200K context). For heavy sessions (workshops,
+sprint planning, large reviews), switch to extended context on-demand:
+
+- `/model sonnet[1m]` — Sonnet 4.6 with 1M context window
+- `/model opus[1m]` — Opus 4.6 with 1M context window
+- Cost: 2x input + 1.5x output for tokens beyond 200K (Tier 4 required)
+
+## Large content pushes
+
+When producing many files (wiki pages, content batches, bulk docs):
+1. **Lore librarian** agent (read-only): ingests all source material, answers focused context queries from writers, tracks cross-file consistency
+2. **Multiple writer** agents (parallel, by domain): each gets a task slice, writes directly to disk using the Write tool — one file at a time, write often, no text accumulation
+3. **Reviewer** agents (blocked until writing done): check voice consistency, attribute uniformity, style
+
+Key: writers use Write tool directly (no transcription bottleneck), librarian catches contradictions early, split work by domain not volume.
+
+## Team monitoring (stuck agent detection)
+
+When leading a team (sprint, workshop, or any multi-agent session):
+
+**Agent heartbeat rule** — include in every agent spawn prompt:
+> If you have been working on a single task for more than 15 minutes
+> without making progress, message the team lead with what is blocking
+> you. Do not keep retrying the same approach silently.
+
+**Team lead proactive checks:**
+- If an agent has not sent a message in ~20 minutes, ping them for a status update.
+- **Bottleneck detection:** if other agents are idle and waiting on one agent's output, that agent's silence is a red flag — check on them immediately, do not wait for the next natural message.
+- When checking on a stuck agent, offer to reassign the task or pull in another agent to help.
@@ -0,0 +1,83 @@
+{
+  "env": {
+    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
+  },
+  "teammateMode": "in-process",
+  "permissions": {
+    "allow": [
+      "Bash(git add *)",
+      "Bash(git commit *)",
+      "Bash(git push *)",
+      "Bash(git fetch *)",
+      "Bash(git merge *)",
+      "Bash(git pull *)",
+      "Bash(git status *)",
+      "Bash(git log *)",
+      "Bash(git diff *)",
+      "Bash(git show *)",
+      "Bash(git checkout *)",
+      "Bash(git stash *)",
+      "Bash(git branch *)",
+      "Bash(git worktree *)",
+      "Bash(git config *)",
+      "Bash(git mv *)",
+      "Bash(git rm *)",
+      "Bash(git ls-tree *)",
+      "Bash(git rev-parse --show-toplevel)",
+
+      "Bash(tooling/db/ticket *)",
+      "Bash(tooling/db/sprint *)",
+      "Bash(tooling/db/sqlite-query *)",
+      "Bash(tooling/db/sqlite-exec *)",
+      "Bash(tooling/db/qdrant-search *)",
+      "Bash(tooling/db/qdrant-index *)",
+      "Bash(tooling/db/qdrant-health)",
+      "Bash(tooling/db/qdrant-count)",
+      "Bash(tooling/db/sqlite-init)",
+      "Bash(tooling/db/decisions-sync)",
+      "Bash(tooling/db/decision *)",
+
+      "Bash(tooling/db/audio-generate *)",
+      "Bash(tooling/db/audio-health)",
+      "Bash(tooling/db/audio-post *)",
+      "Bash(tooling/db/audio-batch *)",
+
+      "Bash(make *)",
+      "Bash(make)",
+
+      "Bash(tea *)",
+      "Bash(tooling/tea-comment *)",
+
+      "Bash(cargo test *)",
+      "Bash(cargo test)",
+      "Bash(cargo build *)",
+      "Bash(cargo build)",
+      "Bash(cargo check *)",
+      "Bash(cargo check)",
+      "Bash(tests/run-*)",
+
+      "Bash(chmod *)",
+      "Bash(ls *)",
+      "Bash(find *)",
+      "Bash(list *)",
+      "Bash(tree *)",
+      "Bash(sed -n *)",
+
+      "Skill(git-commit)",
+      "Skill(worktree-update)",
+      "Skill(sprint-start)",
+      "Skill(sprint-plan)",
+      "Skill(pr-push)",
+      "Skill(pr-review)",
+      "Skill(ticket)",
+      "Skill(docs-search)",
+      "Skill(workshop-start)"
+    ],
+    "deny": [
+      "Bash(git push --force *)",
+      "Bash(git reset --hard *)",
+      "Bash(git clean -f *)",
+      "Bash(rm -rf *)"
+    ]
+  }
+}
@@ -0,0 +1,255 @@
+---
+name: audio-gen
+description: >
+  Generate audio assets for The Settled Reach using the Stable Audio Open API
+  (self-hosted Gradio app at tower-of-joy:11500). Use when generating any game
+  audio: ambient loops, SFX, UI sounds, monologue chimes, footsteps, or any
+  sound asset from docs/assets/audio/. Also use when the user asks about audio
+  generation, sound design pipeline, or audio asset iteration. Triggers on:
+  "generate audio", "make sounds", "create ambient", "audio pipeline",
+  "generate sfx", "stable audio", "gen audio", "sound design".
+---
+
+# Audio Generation — The Settled Reach
+
+Generate sonically consistent audio assets using the Stable Audio Open API via
+wrapper scripts at `tooling/db/audio-*`.
+
+Asset descriptions, filenames, bus routing, and design intent are documented in
+`docs/assets/audio/`. This skill provides the prompt system, generation
+workflow, and quality validation.
+
+## API Access
+
+**Never call the API directly.** Use the wrapper scripts:
+
+```bash
+# Check API health
+tooling/db/audio-health
+
+# Generate a single asset (WAV only)
+tooling/db/audio-generate "prompt text" \
+  --duration 10 --steps 100 --cfg 7 \
+  --output path/to/output.wav
+
+# Generate + post-process in one command (WAV → trim → normalize → OGG)
+tooling/db/audio-generate "prompt text" \
+  --duration 10 --steps 100 --cfg 7 \
+  --output path/to/gen/intermediate.wav \
+  --output-ogg client/assets/audio/final.ogg
+
+# Batch-generate from a manifest (preferred for multiple assets)
+tooling/db/audio-batch docs/assets/audio/batch-s10-327.json
+```
+
+### Parameters
+
+| Parameter | Default | Range | Notes |
+|-----------|---------|-------|-------|
+| `--duration` | 10 | 0-47s | Max 47s per generation. For longer loops, generate 45s with crossfade overlap. |
+| `--steps` | 100 | 10-200 | More steps = better quality, slower. Use 50 for quick previews, 100-150 for final. |
+| `--cfg` | 7 | 1-15 | Classifier-free guidance. Higher = more prompt-adherent but less natural. 5-9 is the sweet spot. |
+| `--output` | auto | — | Output WAV file path. Auto-names from prompt if omitted. |
+| `--post` | off | — | Run trim + normalize + convert after generation. |
+| `--output-ogg` | auto | — | OGG output path (implies `--post`). Defaults to same basename as WAV. |
+| `--timeout` | 600 | — | Max wait in seconds. Generation can take 2-5 minutes on 11GB VRAM. |
+
+### Critical Constraints
+
+- **NEVER parallelize requests.** The server has 11GB VRAM and runs one
+  generation at a time. Always wait for a generation to complete before
+  starting the next. Sequential only.
+- **Generation takes 2-5 minutes** per clip depending on duration and steps.
+  Be patient. The timeout default (600s) is generous.
+- **Max 47 seconds** per generation. For 60-90s ambient loops, generate 45s
+  clips and crossfade-stitch in post-processing.
+
+## Prompt Assembly
+
+Every generation uses three parts:
+
+```
+[SONIC FAMILY PREFIX] + [CATEGORY TEMPLATE] + [ASSET DESCRIPTION from docs/assets/audio/]
+```
+
+Never call the API with just the asset description. Always prepend the sonic
+family prefix and matching category template.
+
+- **Sonic palette and families:** Read `references/sonic-palette.md`
+- **Category templates:** Read `references/category-templates.md` and match by
+  asset type (ambient, sfx, ui)
+- **Asset description:** Look up the specific asset in `docs/assets/audio/{category}.md`
+
+## Batch Workflow (Preferred)
+
+For generating multiple assets, use a manifest file. This reduces prompt
+approvals to 2: one Write (manifest) + one Bash (batch run).
+
+### 1. Create the manifest
+
+Write a JSON manifest to `docs/assets/audio/batch-{sprint}-{ticket}.json`:
+
+```json
+{
+  "description": "Sprint 10 ambient + world SFX batch",
+  "output_dir": "client/assets/audio",
+  "gen_dir": "client/assets/audio/gen",
+  "defaults": {
+    "steps": 100,
+    "cfg": 7,
+    "lufs": -16,
+    "quality": 6
+  },
+  "assets": [
+    {
+      "id": "AMB-001",
+      "filename": "amb_station_base.ogg",
+      "method": "sao",
+      "duration": 45,
+      "steps": 150,
+      "cfg": 5,
+      "prompt": "[sonic family prefix] + [template] + [description]"
+    },
+    {
+      "id": "UI-005",
+      "filename": "sfx_monologue_chime.ogg",
+      "method": "synth",
+      "synth": {
+        "type": "harmonic",
+        "duration": 0.8,
+        "fundamental": 1200,
+        "harmonics": [
+          {"freq": 2400, "db": -12},
+          {"freq": 3600, "db": -24}
+        ],
+        "attack_ms": 15,
+        "sustain_ratio": 0.2,
+        "decay": "exponential"
+      }
+    }
+  ]
+}
+```
+
+Asset `id` values must match IDs in `docs/assets/audio/{category}.md` (e.g.,
+AMB-001, SFX-002, UI-005). This couples the manifest to the asset inventory.
+
+### 2. Run the batch
+
+```bash
+# Full run
+tooling/db/audio-batch docs/assets/audio/batch-s10-327.json
+
+# Dry run — preview what would be generated
+tooling/db/audio-batch docs/assets/audio/batch-s10-327.json --dry-run
+
+# Generate only specific assets
+tooling/db/audio-batch docs/assets/audio/batch-s10-327.json --only AMB-001,AMB-002
+
+# Skip assets that already have OGG files
+tooling/db/audio-batch docs/assets/audio/batch-s10-327.json --skip-existing
+```
+
+### 3. Update asset docs with prompts
+
+After the batch completes, write the exact prompts used back into the
+Prompt/Notes column of `docs/assets/audio/{category}.md`. The manifest records
+what was generated; the asset docs record what we have.
+
+### Manifest fields
+
+| Field | Required | Notes |
+|-------|----------|-------|
+| `id` | yes | Asset ID from docs (AMB-001, SFX-002, UI-005) |
+| `filename` | yes | Output filename (must match asset doc) |
+| `method` | yes | `sao` (Stable Audio Open) or `synth` (harmonic synthesis) |
+| `duration` | SAO only | Duration in seconds |
+| `prompt` | SAO only | Full assembled prompt |
+| `steps` | no | Override default steps |
+| `cfg` | no | Override default CFG |
+| `synth` | synth only | Synthesis parameters (see below) |
+
+### Synth parameters
+
+| Field | Default | Notes |
+|-------|---------|-------|
+| `type` | harmonic | Only `harmonic` supported currently |
+| `duration` | — | Duration in seconds |
+| `fundamental` | — | Fundamental frequency in Hz |
+| `harmonics` | [] | List of `{"freq": Hz, "db": dB}` objects |
+| `attack_ms` | 10 | Attack time in milliseconds |
+| `sustain_ratio` | 0.2 | Fraction of duration at full level before decay |
+| `decay` | exponential | `exponential` or `linear` |
+
+## Single Asset Workflow
+
+For one-off generation or iteration on a specific asset:
+
+1. Find the asset in `docs/assets/audio/{ambient,sfx,ui}.md` — note filename,
+   duration, bus, method, and design intent.
+2. Read `references/sonic-palette.md` for the sonic family prefix.
+3. Read `references/category-templates.md` for the matching template.
+4. Assemble the full prompt.
+5. Run `tooling/db/audio-health` to verify the API is up.
+6. Run `tooling/db/audio-generate` with `--post` or `--output-ogg` to
+   generate and post-process in one step.
+7. Verify the output (file size, duration).
+8. Update the asset status and prompt in `docs/assets/audio/{category}.md`.
+
+## Iteration Workflow
+
+For each asset, generate 4-6 candidates:
+
+1. **Generate candidates** — vary the prompt slightly (add/remove descriptors,
+   adjust CFG between 5-9). Run each generation sequentially — never in
+   parallel.
+2. **Solo test** — does each candidate sound right alone?
+3. **Stack test** — play the candidate alongside other layers. Does it mask or
+   clash?
+4. **Fatigue test** (loops only) — can you listen for 5+ minutes without a
+   jarring repeat?
+5. **Close-your-eyes test** — does it create a mental image or sensation?
+6. Select the best candidate (post-processing is already done if `--post` was
+   used).
+
+## Post-Processing (Standalone)
+
+If you need to post-process separately (e.g., re-normalizing an existing file):
+
+```bash
+# Full pipeline: trim → normalize → convert
+tooling/db/audio-post pipeline input.wav --output output.ogg
+
+# Individual steps
+tooling/db/audio-post trim input.wav
+tooling/db/audio-post normalize input.wav --lufs -16
+tooling/db/audio-post convert input.wav --output output.ogg
+```
+
+## Manual Synthesis (Insert-Tech Sounds)
+
+For sounds under 200ms (cursor hover, weapon aim), Stable Audio Open cannot
+produce meaningful output. Use manual synthesis via `tooling/synth_ui_sounds.py`
+or the batch manifest's `method: "synth"` with harmonic parameters.
+
+For complex synthesis beyond the `harmonic` type (FM, filtered noise, bandpass
+impulse), write a custom script in `tooling/` following the pattern in
+`tooling/synth_ui_sounds.py`.
+
+## Quality Checklist
+
+After generating, verify:
+- Sound matches the sonic family (insert-tech = synthetic/precise, organic = warm/natural)
+- Frequency range doesn't mask other layers (check docs/assets/audio/)
+- Duration matches spec
+- No unwanted artifacts (clicks, pops, digital noise at start/end)
+- Loop point is clean (ambient loops only)
+- Volume sits well relative to other assets (LUFS normalized)
+- Passes the close-your-eyes test
+
+## File Placement
+
+Generated assets go to `client/assets/audio/` with exact filenames from the
+asset docs. Intermediates go to `client/assets/audio/gen/` (gitignored).
+
+AudioManager discovers assets by directory scan — filenames must match exactly.
@@ -0,0 +1,67 @@
+# Category Templates — Audio Generation
+
+Match the asset's category to the right template. Append after the sonic family
+prefix and before the specific asset description.
+
+## Ambient Loops
+
+**Template:**
+> Continuous ambient soundscape loop, seamless looping audio, no distinct
+> beginning or end, steady background atmosphere, [DURATION]s duration
+
+**Notes:**
+- Generate at 45s (the SAO sweet spot below the 47s ceiling)
+- Add 3-5s of overlap material for crossfade looping in post
+- These play continuously — they must be boring enough to fade into the
+  background but rich enough to reward attention
+- Station baseline prefix is required (see sonic-palette.md)
+
+**Steps:** 100-150 (higher quality for loops — artifacts are more noticeable)
+**CFG:** 5-7 (lower guidance = more natural variation, less mechanical)
+
+## Sound Effects (SFX)
+
+**Template:**
+> Single isolated sound effect, clean recording, [DURATION] duration,
+> clear attack and natural decay, no background noise, no reverb tail
+> beyond natural
+
+**Notes:**
+- For footsteps: specify surface material, pace, weight
+- For environmental: specify the physical mechanism (door hinge, cargo latch)
+- Keep short and punchy — these are event-driven, not continuous
+
+**Steps:** 80-100 (shorter sounds need fewer steps)
+**CFG:** 7-9 (more guidance = more precise sound matching)
+
+## UI Sounds
+
+**Template:**
+> Interface feedback sound, digital UI element, [DURATION] duration,
+> immediate attack, clean decay, isolated sound with no background
+
+**Notes:**
+- Most UI sounds are under 200ms — use manual synthesis, not SAO
+- For SAO-generated UI sounds (>200ms like fog_recognition, chimes):
+  generate at 3-5s duration, then trim to the best portion
+- Insert-tech prefix is required for lattice/interface sounds
+- Organic prefix for fog_recognition (cognitive, not technological)
+
+**Steps:** 80-100
+**CFG:** 7-9 (precision matters for UI sounds)
+
+## Chimes / Notification Sounds
+
+**Template:**
+> Single musical tone, crystalline quality, [DURATION] duration, gentle
+> attack, resonant sustain, natural fade out, no accompaniment, no rhythm
+
+**Notes:**
+- Generate at 3-5s to give SAO enough temporal context
+- Trim to the best 0.5-1.0s section
+- The attack transient is where the character lives — select for that
+- Normal vs urgent variants: same base prompt, vary "gentle/soft" vs
+  "brighter/sharper/more present"
+
+**Steps:** 100 (tonal quality matters)
+**CFG:** 6-8 (some freedom for natural harmonic content)
@@ -0,0 +1,45 @@
+# Sonic Palette — Prompt Prefixes
+
+Two sonic families. Every generated sound uses one of these as a prompt prefix.
+
+## Insert-Tech (Synthetic)
+
+For UI sounds, neural lattice interface, augmented cognition.
+
+**Prompt prefix:**
+> Clean digital audio, synthetic electronic tone, precise and clinical sound
+> design, no reverb, no room ambience, studio-dry recording, futuristic
+> interface sound
+
+**Character:** Mathematical precision. The sound of well-designed technology.
+No organic texture, no room reflections. Exists "inside the head," not in
+physical space.
+
+**Frequency range:** 800Hz-4kHz primary. Sharp attack, controlled decay.
+
+**Used for:** cursor_hover, implant_open, weapon_aim, sfx_monologue_chime,
+sfx_monologue_chime_urgent
+
+## Organic (Biological/Environmental)
+
+For environmental sounds, human cognition, physical world.
+
+**Prompt prefix:**
+> Warm organic audio, natural sound recording, slight room ambience,
+> lived-in industrial space, realistic acoustic properties, authentic
+> environmental sound
+
+**Character:** Human warmth. Natural attack and decay. Reverberant — exists
+in physical space. The sound of a real place with real materials.
+
+**Frequency range:** 60Hz-3kHz primary. Soft or natural attack, room tail.
+
+**Used for:** fog_recognition, all amb_* ambient loops, all sfx_footstep_*
+
+## Station Baseline
+
+For ambient loops specifically, add the station context:
+
+> Interior of a large industrial space station, metal and composite
+> construction, background mechanical hum from power systems, air circulation
+> audible, no music, no prominent voices unless specified
@@ -0,0 +1,231 @@
+---
+name: bug-report
+description: >
+  Process in-game bug reports captured by the Godot client's bug reporter.
+  Use when the user says "bug reports", "check bug reports", "process bugs",
+  or invokes /bug-report. Scans the user:// bug-reports directory, summarizes
+  each report, and offers investigation, ticket creation, or dismissal.
+user-invocable: true
+allowed-tools: Bash, Read, Grep, Glob, Write
+---
+
+# Bug Report Skill
+
+Process in-game bug reports exported by the Godot client to the user data
+directory. Each report is a directory containing a snapshot of game state at the
+moment the tester filed the report.
+
+```
+BUG_REPORT_DIR: /var/home/jeroenschweitzer/.local/share/godot/app_userdata/The Settled Reach/bug-reports/
+```
+
+## Report structure
+
+Each report lives in a directory named `gauntlet-t{tick}-{timestamp}/` and
+contains these files:
+
+| File | Purpose |
+|------|---------|
+| `description.txt` | Tester notes + metadata (tick, room, stance, facing, position) |
+| `render.txt` | Simplified text render of the game snapshot |
+| `snapshot.json` | Full JSON snapshot (entities, dialogue state, etc.) |
+| `inputs.jsonl` | Last 60 ticks of player input (replay format) |
+| `snapshots.jsonl` | Last 60 ticks of observer snapshots |
+| `seed.txt` | RNG seed for deterministic replay |
+
+## Invocation
+
+- `/bug-report` — scan and process all unprocessed reports
+- `/bug-report <directory-name>` — process a specific report by directory name
+
+## Workflow
+
+### 1. Scan for unprocessed reports
+
+List all report directories in the bug reports directory:
+
+```bash
+ls -1d "/var/home/jeroenschweitzer/.local/share/godot/app_userdata/The Settled Reach/bug-reports/"*/
+```
+
+If no directories are found, report "No bug reports found." and stop.
+
+If the user provided a specific directory name as argument, filter to only that
+directory. If it does not exist, report the error and list available reports.
+
+### 2. Read and summarize each report
+
+For each report directory, read the following files using the Read tool:
+
+1. **`description.txt`** — extract:
+   - Tester description / notes (free text at top)
+   - Tick number
+   - Room name
+   - Player stance, facing, position
+2. **`render.txt`** — extract:
+   - A brief description of what the text render shows (room layout, visible
+     entities, player position marker)
+3. **`snapshot.json`** — extract:
+   - Total entity count
+   - Whether dialogue is active (look for `dialogue` or `conversation` keys
+     with non-null/non-empty values)
+   - Whether monologue is active (look for `monologue` keys with non-null/
+     non-empty values)
+   - NPC names and positions if present
+   - Any error or anomaly fields
+4. **`seed.txt`** — note the seed value for reference
+
+Do NOT read `inputs.jsonl` or `snapshots.jsonl` during the summary phase.
+These are large files reserved for the investigation step.
+
+### 3. Present the summary list
+
+Present a numbered list of all reports with their summaries. Format:
+
+```
+## Bug Reports Found: N
+
+### 1. gauntlet-t{tick}-{timestamp}
+- **Tick:** {tick} | **Room:** {room} | **Position:** ({x}, {y})
+- **Stance:** {stance} | **Facing:** {facing}
+- **Entities:** {count} | **Dialogue active:** yes/no | **Monologue active:** yes/no
+- **Seed:** {seed}
+- **Description:** {tester notes, first 2-3 lines}
+- **Render overview:** {brief description of what render.txt shows}
+- **Observations:** {any anomalies spotted in the snapshot}
+
+### 2. gauntlet-t{tick}-{timestamp}
+...
+```
+
+### 4. Offer actions per report
+
+After presenting the summary list, ask the user which action to take for each
+report. The three actions are:
+
+#### Investigate
+
+Dig deeper into the report for root cause analysis:
+
+1. Read `snapshot.json` in full — analyze entity states, component values,
+   relationships between entities, any inconsistencies
+2. Read `inputs.jsonl` — reconstruct what the player was doing in the 60 ticks
+   leading up to the report. Look for:
+   - Rapid input changes (stuck keys, input spam)
+   - Movement into walls or invalid positions
+   - Interaction attempts that may have failed
+   - Timing patterns (actions on same tick as state changes)
+3. Read `snapshots.jsonl` — compare entity states across recent ticks to find
+   when the bug manifested:
+   - Entity position jumps
+   - State machine transitions that look wrong
+   - Component values going out of expected range
+   - Entities appearing or disappearing unexpectedly
+4. Cross-reference with `render.txt` to confirm visual manifestation
+5. Read `seed.txt` and note it — the seed plus `inputs.jsonl` should allow
+   deterministic replay of the scenario
+
+Present findings as a root cause analysis:
+
+```
+## Investigation: gauntlet-t{tick}-{timestamp}
+
+### Timeline
+- t{tick-N}: {what happened}
+- t{tick-M}: {state change}
+- t{tick}: {bug manifests}
+
+### Root cause
+{Analysis of what went wrong and why}
+
+### Affected systems
+- {system 1}: {how it's involved}
+- {system 2}: {how it's involved}
+
+### Reproduction
+Seed: {seed}
+Replay inputs.jsonl from tick {start} to reproduce.
+
+### Suggested fix
+{If identifiable from the snapshot data}
+```
+
+After investigation, return to the action prompt for this report (the user
+may want to create a ticket or dismiss after investigating).
+
+#### Create ticket
+
+Create a bug ticket in the project database. Determine the team from the
+nature of the bug:
+
+- **server** — simulation bugs (entity state, movement, AI, ECS systems,
+  perception, knowledge graph)
+- **client** — rendering bugs (display glitches, UI issues, input handling,
+  audio, visual artifacts)
+- **server,client** — integration bugs (protocol mismatch, desync, bridge
+  issues)
+
+Construct the ticket title and description from the report summary and any
+investigation findings. Use the ticket CLI:
+
+```bash
+tooling/db/ticket create bug "{title}" --team {team} --description "{description}"
+```
+
+The description should include:
+- Bug summary (from tester notes)
+- Tick, room, position
+- Key observations from snapshot analysis
+- Seed for reproduction
+- Report directory name for reference
+
+After creating the ticket, report the ticket ID to the user.
+
+#### Dismiss
+
+Mark the report as not actionable. Remove the report directory:
+
+```bash
+rm -rf "/var/home/jeroenschweitzer/.local/share/godot/app_userdata/The Settled Reach/bug-reports/{report-dir}/"
+```
+
+**Always confirm with the user before deleting.** State clearly which directory
+will be removed and wait for confirmation.
+
+### 5. Batch processing
+
+When processing multiple reports, work through them one at a time in the
+numbered order presented. For each report, complete the chosen action before
+moving to the next.
+
+If the user wants to batch-dismiss multiple reports, confirm the full list
+of directories that will be deleted before proceeding.
+
+### 6. Final summary
+
+After all reports have been processed, present a summary:
+
+```
+## Bug Report Processing Complete
+
+- **Investigated:** {count}
+- **Tickets created:** {count} ({ticket IDs})
+- **Dismissed:** {count}
+- **Remaining unprocessed:** {count}
+```
+
+## Tips
+
+- Large `snapshot.json` files may need to be read with offset/limit parameters.
+  Start with the first 200 lines to get the structure, then target specific
+  sections.
+- `inputs.jsonl` and `snapshots.jsonl` are newline-delimited JSON. Each line
+  is one tick. Read the last 10-20 lines first to focus on the moments before
+  the report was filed.
+- The `render.txt` is a text-art representation of the game view. Entity
+  positions in the render should match positions in the snapshot. Mismatches
+  are themselves a bug signal (rendering vs simulation desync).
+- The seed in `seed.txt` combined with `inputs.jsonl` enables deterministic
+  replay on the server. Note this in any ticket you create.
+- If the bug-reports directory does not exist, the tester has not yet run any
+  gauntlet sessions or has not filed any reports. This is not an error.
@@ -0,0 +1,151 @@
+---
+name: d2-diagram
+description: >
+  Generate technical diagrams using d2 (text-to-diagram CLI). Use when the
+  user says "create a diagram", "draw architecture", "make a flowchart",
+  "diagram this", "render d2", "d2", "data flow diagram", "entity relationship",
+  "state machine", "sequence diagram", "UI flow", or invokes /d2-diagram.
+  Produces .d2 source files and renders them to PNG. Also use when asked
+  to update, re-render, or batch render existing diagrams.
+---
+
+# d2 Diagram Generation
+
+Generate technical diagrams from text using d2 (v0.7.1). Pure CLI, no
+external dependencies beyond the d2 binary.
+
+**Binary:** `/home/linuxbrew/.linuxbrew/bin/d2`
+
+## Project Defaults
+
+| Setting | Value | Override |
+|---------|-------|----------|
+| Theme | 200 (Dark Mauve) | `--theme N` |
+| Layout | dagre | `--layout elk` |
+| Padding | 100px | — |
+| Format | PNG | `--svg` |
+
+## Output Convention
+
+```
+docs/diagrams/
+  architecture/    # System architecture, IPC, component layout
+  data-flow/       # Sequence diagrams, data pipelines
+  entity/          # ER diagrams, ECS component schemas
+  state/           # State machines, behavior trees
+  ui/              # UI navigation flow, screen transitions
+```
+
+Both `.d2` source and `.png` output are tracked in git.
+
+## Single Diagram Workflow
+
+1. **Determine category** — architecture, data-flow, entity, state, or ui
+2. **Read template** — `references/diagram-templates.md` for the matching category
+3. **Read syntax** — `references/d2-syntax-guide.md` if unfamiliar with d2 syntax
+4. **Write .d2 source** — to `docs/diagrams/{category}/{name}.d2`
+5. **Validate** — `.claude/skills/d2-diagram/scripts/d2-render.sh validate {file}`
+6. **Render** — `.claude/skills/d2-diagram/scripts/d2-render.sh {file}`
+7. **Read SVG** — verify the output, present to user
+
+### Script Usage
+
+```bash
+# Render with project defaults
+.claude/skills/d2-diagram/scripts/d2-render.sh docs/diagrams/architecture/ipc-bridge.d2
+
+# Validate syntax only
+.claude/skills/d2-diagram/scripts/d2-render.sh validate docs/diagrams/architecture/ipc-bridge.d2
+
+# Auto-format source
+.claude/skills/d2-diagram/scripts/d2-render.sh fmt docs/diagrams/architecture/ipc-bridge.d2
+
+# Sketch mode (hand-drawn look for drafts)
+.claude/skills/d2-diagram/scripts/d2-render.sh docs/diagrams/ui/flow.d2 --sketch
+
+# Light theme (for printable docs)
+.claude/skills/d2-diagram/scripts/d2-render.sh docs/diagrams/entity/schema.d2 --theme 0
+
+# SVG output (if specifically needed)
+.claude/skills/d2-diagram/scripts/d2-render.sh docs/diagrams/architecture/overview.d2 --svg
+```
+
+## Batch Render
+
+Re-render all diagrams after theme or style changes:
+
+```bash
+# All diagrams
+.claude/skills/d2-diagram/scripts/d2-batch.sh
+
+# One category
+.claude/skills/d2-diagram/scripts/d2-batch.sh docs/diagrams/architecture/
+
+# Preview what would render
+.claude/skills/d2-diagram/scripts/d2-batch.sh --dry-run
+
+# Force re-render everything
+.claude/skills/d2-diagram/scripts/d2-batch.sh --force
+```
+
+Batch skips files whose PNG is newer than the `.d2` source unless `--force`.
+
+## Advanced Patterns
+
+### Variables for consistent styling
+
+```d2
+vars: {
+  color-bg: "#2a3040"
+  color-stroke: "#333340"
+  color-text: "#c8d0e0"
+  color-accent: "#c8d8f0"
+}
+```
+
+### Multi-board (layers)
+
+```d2
+# Base diagram here
+
+layers: {
+  detailed: {
+    # More detailed view
+  }
+}
+```
+
+### Sequence diagrams
+
+```d2
+shape: sequence_diagram
+client: Godot Client
+server: Rust Server
+
+client -> server: TickRequest(delta)
+server -> client: WorldState(entities)
+```
+
+### Imports
+
+Split shared definitions into a separate file and import:
+
+```d2
+...@shared-defs.d2
+```
+
+## Agent Guidance
+
+- **Qatux** — Architecture decision records, system overview diagrams, data
+  schemas. Prefer architecture and entity templates.
+- **Tyre** — IPC bridge, ECS system flow, chunk loading pipeline, perception
+  system data flow. Prefer architecture and data-flow templates.
+- **Araminta** — UI navigation flow, screen transitions, component hierarchy.
+  Prefer UI flow template.
+
+## References
+
+- `references/d2-syntax-guide.md` — Language quick reference (shapes, edges,
+  containers, styling, variables). Read when unfamiliar with d2 syntax.
+- `references/diagram-templates.md` — Five category templates with complete
+  d2 source examples. Read when starting a new diagram.
@@ -0,0 +1,212 @@
+# D2 Language Quick Reference
+
+## Nodes
+
+```d2
+server                              # Implicit label from key
+server: Simulation Server           # Explicit label
+server: Simulation Server {         # With properties
+  shape: hexagon
+  style.fill: "#2d3436"
+}
+```
+
+## Edges
+
+```d2
+a -> b                              # Directed
+a <- b                              # Reverse directed
+a <-> b                             # Bidirectional
+a -- b                              # Undirected
+a -> b: "label"                     # Labeled edge
+a -> b -> c                         # Chained
+```
+
+## Containers (nesting)
+
+```d2
+infrastructure: {
+  server: Simulation Server
+  database: State Store {
+    shape: cylinder
+  }
+}
+```
+
+## Shapes
+
+| Shape | Use for |
+|-------|---------|
+| `rectangle` | Default. Components, modules, generic. |
+| `hexagon` | Systems, services, major components. |
+| `cylinder` | Databases, storage, persistent state. |
+| `diamond` | Decisions, conditions, branch points. |
+| `oval` / `circle` | Start/end states, events. |
+| `cloud` | External systems, networks. |
+| `person` | Actors, users, NPCs. |
+| `queue` | Message queues, buffers. |
+| `page` | Documents, files. |
+| `package` | Packages, modules, crates. |
+| `sql_table` | Database tables, ECS component schemas. |
+| `class` | Class diagrams, ECS system definitions. |
+| `code` | Code blocks (set `language` property). |
+| `markdown` | Rich text blocks. |
+
+## SQL Tables
+
+```d2
+entity: {
+  shape: sql_table
+  id: u64 {constraint: primary_key}
+  name: String
+  position: Vec2
+  faction_id: u64 {constraint: foreign_key}
+}
+```
+
+## Class Diagrams
+
+```d2
+perception_system: {
+  shape: class
+  +run(world: &mut World)
+  -calculate_los(entity: Entity): HashSet<Entity>
+  #update_knowledge(entity: Entity, seen: HashSet<Entity>)
+}
+```
+
+## Sequence Diagrams
+
+```d2
+shape: sequence_diagram
+client: Godot Client
+server: Rust Server
+
+client -> server: TickRequest(delta)
+server -> server: run ECS systems
+server -> client: WorldState(entities)
+```
+
+## Styling
+
+```d2
+node: Label {
+  style: {
+    fill: "#2d3436"
+    stroke: "#333340"
+    stroke-width: 2
+    stroke-dash: 5              # Dashed line
+    opacity: 0.8
+    font-size: 14
+    font-color: "#c8d0e0"
+    bold: true
+    italic: false
+    border-radius: 4
+    shadow: true
+    3d: true                    # Rectangles only
+    multiple: true              # Stacked appearance
+    double-border: true         # Rectangles/ovals only
+  }
+}
+```
+
+### Edge styling
+
+```d2
+a -> b: {
+  style: {
+    stroke: "#c8d8f0"
+    stroke-width: 2
+    stroke-dash: 5
+    opacity: 0.8
+    animated: true              # Animated flow
+  }
+}
+```
+
+## Variables
+
+```d2
+vars: {
+  color-bg: "#1a1e24"
+  color-stroke: "#333340"
+  color-text: "#c8d0e0"
+  color-accent: "#c8d8f0"
+}
+
+node: {
+  style.fill: ${color-bg}
+  style.stroke: ${color-stroke}
+  style.font-color: ${color-text}
+}
+```
+
+## Direction
+
+```d2
+direction: right                    # left-to-right (default for dagre)
+direction: down                     # top-to-bottom
+direction: up
+direction: left
+```
+
+## Imports
+
+```d2
+...@shared-defs.d2                  # Spread import (inline all definitions)
+```
+
+## Icons
+
+```d2
+node: Label {
+  icon: https://icons.terrastruct.com/essentials/time.svg
+}
+```
+
+## Layers (multi-board)
+
+```d2
+# Base diagram content here
+
+layers: {
+  detailed: {
+    # More detailed view
+  }
+  simplified: {
+    # Simplified overview
+  }
+}
+```
+
+## Scenarios (animated transitions)
+
+```d2
+# Base state
+
+scenarios: {
+  alert: {
+    # Changes from base for alert state
+  }
+  combat: {
+    # Changes from base for combat state
+  }
+}
+```
+
+## Comments
+
+```d2
+# This is a comment
+node: Label  # Inline comment
+```
+
+## Project Colors (from visual-grammar-v01.md)
+
+| Constant | Hex | Usage |
+|----------|-----|-------|
+| Zone 1 floor | `#1a1e24` | Dark backgrounds |
+| Zone 1 wall | `#2a3040` | Component fill |
+| Outline standard | `#333340` | Borders, strokes |
+| Insert chrome | `#c8d0e0` | Text, labels |
+| Zone 1 fixture | `#c8d8f0` | Accents, highlights |
@@ -0,0 +1,251 @@
+# Diagram Templates
+
+Copy, adapt, and render. Each template uses project colors from visual-grammar-v01.md.
+
+---
+
+## 1. Architecture Diagram
+
+System components, relationships, communication channels.
+
+**When to use:** IPC bridge, perception pipeline, chunk loading, ECS system layout, client-server architecture.
+
+**Agents:** Tyre (system architecture), Qatux (architecture decision records).
+
+```d2
+vars: {
+  color-bg: "#2a3040"
+  color-stroke: "#333340"
+  color-text: "#c8d0e0"
+  color-accent: "#c8d8f0"
+}
+
+direction: right
+
+client: Godot Client {
+  shape: hexagon
+  style.fill: ${color-bg}
+  style.font-color: ${color-text}
+
+  rendering: Rendering {
+    style.fill: ${color-bg}
+    style.font-color: ${color-text}
+  }
+  ui: UI Layer {
+    style.fill: ${color-bg}
+    style.font-color: ${color-text}
+  }
+  bridge: IPC Bridge {
+    style.fill: ${color-bg}
+    style.font-color: ${color-text}
+    style.stroke: ${color-accent}
+  }
+}
+
+server: Rust Server {
+  shape: hexagon
+  style.fill: ${color-bg}
+  style.font-color: ${color-text}
+
+  ecs: bevy_ecs {
+    style.fill: ${color-bg}
+    style.font-color: ${color-text}
+  }
+  perception: Perception {
+    style.fill: ${color-bg}
+    style.font-color: ${color-text}
+  }
+  bridge: IPC Bridge {
+    style.fill: ${color-bg}
+    style.font-color: ${color-text}
+    style.stroke: ${color-accent}
+  }
+}
+
+client.bridge -> server.bridge: "stdin/stdout" {
+  style.stroke: ${color-accent}
+  style.stroke-dash: 5
+}
+```
+
+---
+
+## 2. Entity Relationship
+
+Data schemas, ECS components, knowledge graph structure.
+
+**When to use:** Database tables, component definitions, entity relationships, knowledge store schema.
+
+**Agents:** Tyre (ECS component design), Qatux (schema documentation).
+
+```d2
+entity: Entity {
+  shape: sql_table
+  id: u64 {constraint: primary_key}
+  name: String
+  faction_id: u64 {constraint: foreign_key}
+}
+
+position: Position {
+  shape: sql_table
+  entity_id: u64 {constraint: foreign_key}
+  x: f32
+  y: f32
+  chunk_id: u32
+}
+
+knowledge: KnowledgeEntry {
+  shape: sql_table
+  observer_id: u64 {constraint: foreign_key}
+  subject_id: u64 {constraint: foreign_key}
+  fact_type: FactType
+  confidence: f32
+  last_seen_tick: u64
+}
+
+entity.id -> position.entity_id
+entity.id -> knowledge.observer_id
+entity.id -> knowledge.subject_id
+```
+
+---
+
+## 3. Sequence / Data Flow
+
+Ordered interactions between systems over time.
+
+**When to use:** IPC message flow, tick processing, perception update cycle, dialogue system exchanges.
+
+**Agents:** Tyre (system interaction design), Qatux (protocol documentation).
+
+```d2
+shape: sequence_diagram
+
+client: Godot Client
+bridge: IPC Bridge
+server: Rust Server
+ecs: ECS Systems
+
+client -> bridge: TickRequest(delta, input)
+bridge -> server: deserialize + dispatch
+server -> ecs: run_systems(delta)
+ecs -> ecs: perception, AI, physics
+ecs -> server: collect WorldState
+server -> bridge: serialize WorldState
+bridge -> client: WorldState(entities, events)
+client -> client: update rendering
+```
+
+---
+
+## 4. State Machine
+
+Entity states, transitions, conditions.
+
+**When to use:** NPC behavior states, game mode transitions, dialogue state, investigation phases.
+
+**Agents:** Tyre (behavior system design), Qatux (state documentation).
+
+```d2
+vars: {
+  color-state: "#2a3040"
+  color-text: "#c8d0e0"
+  color-edge: "#c8d8f0"
+  color-decision: "#333340"
+}
+
+idle: Idle {
+  style.fill: ${color-state}
+  style.font-color: ${color-text}
+}
+
+alert: Alert {
+  style.fill: ${color-state}
+  style.font-color: ${color-text}
+}
+
+investigate: Investigate {
+  style.fill: ${color-state}
+  style.font-color: ${color-text}
+}
+
+combat: Combat {
+  style.fill: ${color-state}
+  style.font-color: ${color-text}
+  style.stroke: "#f0b840"
+}
+
+flee: Flee {
+  style.fill: ${color-state}
+  style.font-color: ${color-text}
+}
+
+idle -> alert: "stimulus detected" { style.stroke: ${color-edge} }
+alert -> investigate: "stimulus confirmed" { style.stroke: ${color-edge} }
+alert -> idle: "timeout / stimulus lost" { style.stroke: ${color-edge}; style.stroke-dash: 5 }
+investigate -> combat: "threat confirmed" { style.stroke: "#f0b840" }
+investigate -> idle: "nothing found" { style.stroke: ${color-edge}; style.stroke-dash: 5 }
+combat -> flee: "health < threshold" { style.stroke: "#f0b840" }
+combat -> idle: "threat eliminated" { style.stroke: ${color-edge}; style.stroke-dash: 5 }
+flee -> idle: "safe distance reached" { style.stroke: ${color-edge}; style.stroke-dash: 5 }
+```
+
+---
+
+## 5. UI Flow
+
+Screen navigation, component hierarchy, interaction paths.
+
+**When to use:** HUD layout relationships, menu navigation, dialogue flow, insert mode transitions.
+
+**Agents:** Araminta (UI/visual design), Tyre (interface architecture), Qatux (UI documentation).
+
+```d2
+vars: {
+  color-screen: "#1a1e24"
+  color-panel: "#2a3040"
+  color-text: "#c8d0e0"
+  color-nav: "#c8d8f0"
+}
+
+gameplay: Gameplay {
+  style.fill: ${color-screen}
+  style.font-color: ${color-text}
+
+  hud: HUD {
+    style.fill: ${color-panel}
+    style.font-color: ${color-text}
+
+    minimap: Minimap
+    monologue: Monologue Panel
+    insert_display: Insert Display
+  }
+
+  world: World View {
+    style.fill: ${color-panel}
+    style.font-color: ${color-text}
+  }
+}
+
+pause: Pause Menu {
+  style.fill: ${color-screen}
+  style.font-color: ${color-text}
+
+  inventory: Inventory
+  journal: Journal
+  settings: Settings
+}
+
+dialogue: Dialogue Mode {
+  style.fill: ${color-screen}
+  style.font-color: ${color-text}
+
+  speaker: Speaker Panel
+  responses: Response List
+}
+
+gameplay -> pause: "ESC" { style.stroke: ${color-nav} }
+pause -> gameplay: "ESC / Resume" { style.stroke: ${color-nav}; style.stroke-dash: 5 }
+gameplay -> dialogue: "interact with NPC" { style.stroke: ${color-nav} }
+dialogue -> gameplay: "end conversation" { style.stroke: ${color-nav}; style.stroke-dash: 5 }
+```
@@ -0,0 +1,84 @@
+#!/bin/bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR" && git rev-parse --show-toplevel)"
+RENDER="$SCRIPT_DIR/d2-render.sh"
+
+usage() {
+  cat <<EOF
+Usage: $(basename "$0") [directory] [options]
+
+Batch render all .d2 files in a directory. Skips files whose PNG is
+newer than the source unless --force is used.
+
+Options:
+  --dry-run    List files that would be rendered
+  --force      Re-render even if SVG is up to date
+  --theme N    Override theme for all files
+
+Examples:
+  $(basename "$0")                                # All in docs/diagrams/
+  $(basename "$0") docs/diagrams/architecture/    # One category
+  $(basename "$0") --dry-run                      # Preview
+  $(basename "$0") --force                        # Re-render everything
+EOF
+  exit 1
+}
+
+DIR="$REPO_ROOT/docs/diagrams"
+DRY_RUN=false
+FORCE=false
+EXTRA_ARGS=()
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --dry-run) DRY_RUN=true; shift ;;
+    --force)   FORCE=true; shift ;;
+    --theme)   EXTRA_ARGS+=(--theme "$2"); shift 2 ;;
+    --help|-h) usage ;;
+    *)
+      if [[ -d "$1" ]] || [[ -d "$REPO_ROOT/$1" ]]; then
+        DIR="$1"
+        [[ "$DIR" != /* ]] && DIR="$REPO_ROOT/$DIR"
+      else
+        echo "Unknown option or directory: $1" >&2; exit 1
+      fi
+      shift
+      ;;
+  esac
+done
+
+[[ ! -d "$DIR" ]] && { echo "ERROR: Directory not found: $DIR" >&2; exit 1; }
+
+RENDERED=0
+SKIPPED=0
+FAILED=0
+
+while IFS= read -r -d '' d2_file; do
+  png_file="${d2_file%.d2}.png"
+
+  # Skip if PNG is newer than source (unless --force)
+  if [[ "$FORCE" != true ]] && [[ -f "$png_file" ]] && [[ "$png_file" -nt "$d2_file" ]]; then
+    SKIPPED=$((SKIPPED + 1))
+    continue
+  fi
+
+  rel_path="${d2_file#"$REPO_ROOT/"}"
+
+  if [[ "$DRY_RUN" == true ]]; then
+    echo "Would render: $rel_path"
+    RENDERED=$((RENDERED + 1))
+    continue
+  fi
+
+  if "$RENDER" "$d2_file" "${EXTRA_ARGS[@]+"${EXTRA_ARGS[@]}"}"; then
+    RENDERED=$((RENDERED + 1))
+  else
+    echo "FAILED: $rel_path" >&2
+    FAILED=$((FAILED + 1))
+  fi
+done < <(find "$DIR" -name '*.d2' -print0 | sort -z)
+
+echo ""
+echo "Batch complete: $RENDERED rendered, $SKIPPED skipped (up to date), $FAILED failed"
@@ -0,0 +1,92 @@
+#!/bin/bash
+set -euo pipefail
+
+D2="/home/linuxbrew/.linuxbrew/bin/d2"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR" && git rev-parse --show-toplevel)"
+
+DEFAULT_THEME=200
+DEFAULT_LAYOUT="dagre"
+DEFAULT_PAD=100
+
+usage() {
+  cat <<EOF
+Usage: $(basename "$0") [validate|fmt] <file.d2> [options]
+
+Render a .d2 file to PNG with project defaults (theme $DEFAULT_THEME, $DEFAULT_LAYOUT layout).
+
+Commands:
+  validate <file>     Check syntax without rendering
+  fmt <file>          Auto-format in place
+
+Options:
+  --theme N           Override theme (default: $DEFAULT_THEME)
+  --layout NAME       Override layout engine (default: $DEFAULT_LAYOUT)
+  --sketch            Enable hand-drawn sketch mode
+  --output PATH       Override output path (default: input with .png extension)
+  --svg               Render to SVG instead of PNG
+
+Examples:
+  $(basename "$0") docs/diagrams/architecture/ipc-bridge.d2
+  $(basename "$0") validate docs/diagrams/architecture/ipc-bridge.d2
+  $(basename "$0") docs/diagrams/architecture/ipc-bridge.d2 --sketch --theme 0
+EOF
+  exit 1
+}
+
+[[ $# -lt 1 ]] && usage
+
+# Parse subcommand
+SUBCMD=""
+case "$1" in
+  validate|fmt)
+    SUBCMD="$1"
+    shift
+    ;;
+esac
+
+[[ $# -lt 1 ]] && usage
+
+INPUT="$1"
+shift
+
+# Resolve to absolute path
+[[ "$INPUT" != /* ]] && INPUT="$REPO_ROOT/$INPUT"
+
+[[ ! -f "$INPUT" ]] && { echo "ERROR: File not found: $INPUT" >&2; exit 1; }
+
+# Handle subcommands
+if [[ -n "$SUBCMD" ]]; then
+  "$D2" "$SUBCMD" "$INPUT"
+  echo "OK: $SUBCMD $INPUT"
+  exit 0
+fi
+
+# Parse render options
+THEME="$DEFAULT_THEME"
+LAYOUT="$DEFAULT_LAYOUT"
+SKETCH=""
+OUTPUT=""
+FORMAT="png"
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --theme)  THEME="$2"; shift 2 ;;
+    --layout) LAYOUT="$2"; shift 2 ;;
+    --sketch) SKETCH="-s"; shift ;;
+    --output) OUTPUT="$2"; shift 2 ;;
+    --svg)    FORMAT="svg"; shift ;;
+    *) echo "Unknown option: $1" >&2; exit 1 ;;
+  esac
+done
+
+# Derive output path
+if [[ -z "$OUTPUT" ]]; then
+  OUTPUT="${INPUT%.d2}.$FORMAT"
+fi
+
+# Render
+"$D2" -t "$THEME" -l "$LAYOUT" --pad "$DEFAULT_PAD" $SKETCH "$INPUT" "$OUTPUT"
+
+SIZE=$(stat --printf="%s" "$OUTPUT" 2>/dev/null || stat -f%z "$OUTPUT" 2>/dev/null)
+echo "Rendered: $OUTPUT ($(( SIZE / 1024 ))KB)"
@@ -0,0 +1,55 @@
+---
+name: docs-search
+description: >
+  Search project documents using semantic search (Qdrant + ollama) or grep fallback.
+  Use when the user asks "did we discuss X?", "find references to Y", "search docs",
+  or invokes /docs-search. Wraps the qdrant_connector.py for semantic document search.
+user-invocable: true
+allowed-tools: Bash, Read, Grep, Glob
+---
+
+# Search Docs Skill
+
+Semantic search across project documents. Endpoints are in
+`.claude/rules/local-services.md`. This skill covers advanced operations
+and workflows.
+
+## Advanced Commands
+
+### Index a single chunk
+
+For precise indexing of specific content:
+```bash
+python3 tooling/db/qdrant_connector.py index "unique-id" "Text content to index" --metadata source=manual heading="Custom heading"
+```
+
+### Create collection
+
+Initialize the Qdrant collection (run once during setup):
+```bash
+python3 tooling/db/qdrant_connector.py create-collection
+```
+
+## Bulk Indexing
+
+Index all project documents at once:
+```bash
+for f in decisions/*.md DISCUSSION.md TEAM.md docs/discussions/*.md docs/briefings/*.md; do
+  tooling/db/qdrant-index "$f"
+done
+```
+
+## Fallback
+
+If Qdrant or ollama is unreachable, fall back to grep-based search:
+```bash
+grep -r -i "search term" decisions/ DISCUSSION.md docs/ --include="*.md"
+```
+
+## Workflow
+
+1. **Qatux (Librarian)** is the primary user of this skill
+2. After each discussion round, index the archived round file
+3. After briefing updates, re-index affected briefings
+4. After decision changes, re-index the relevant decisions/*.md domain files
+5. Use search to answer "did we discuss this?" questions with citations
@@ -0,0 +1,197 @@
+---
+name: frame0-wireframe
+description: >
+  Create and export UI wireframes using Frame0 (local desktop wireframing
+  app with HTTP API). Use when the user says "create wireframe", "wireframe
+  this", "mock up the UI", "draw a screen", "UI layout", "wireframe the HUD",
+  "Frame0", "frame0", "export wireframe", or invokes /frame0-wireframe.
+  Wireframes are authored as local JSON files (source of truth) and synced
+  to Frame0 for rendering and export. Requires Frame0 to be running locally.
+---
+
+# Frame0 Wireframe Generation
+
+Create UI wireframes as JSON files, sync them to Frame0 for rendering, and
+export as PNG. Local JSON is the source of truth — Frame0 is the renderer.
+
+**Frame0 is a renderer, not a workspace.** Treat it as disposable output.
+Push freely, delete test pages, keep it clean. Never pull from Frame0 unless
+the user explicitly says they have made edits in Frame0 and want to import
+them. The pull workflow exists for that case only — do not use it proactively.
+
+**Prerequisite:** Frame0 desktop app must be running. If not available,
+stop and inform the user. Point to `references/setup-guide.md`.
+
+## Health Check
+
+Always check first:
+
+```bash
+.claude/skills/frame0-wireframe/scripts/frame0-cmd.sh health
+```
+
+## Core Workflow
+
+1. **Health check** — verify Frame0 is running
+2. **Write wireframe JSON** — to `docs/design/wireframes/{category}/{name}.json`
+3. **Push to Frame0** — `frame0-sync.py push <file.json>`
+4. **Export PNG** — `frame0-sync.py export <file.json> <output.png>`
+5. **Clean up** — delete test/scratch pages from Frame0 when done
+
+### Scripts
+
+| Script | Purpose |
+|--------|---------|
+| `scripts/frame0-sync.py` | **Primary.** Push/pull/export wireframes between JSON and Frame0 |
+| `scripts/frame0-cmd.sh` | Low-level API wrapper for ad-hoc commands |
+
+## Wireframe JSON Format
+
+```json
+{
+  "name": "Dialogue Box",
+  "shapes": {
+    "panel": {
+      "type": "Rectangle",
+      "left": 170, "top": 500, "width": 800, "height": 260,
+      "fillColor": "#1a1e24",
+      "strokeColor": "#333340",
+      "corners": [8, 8, 8, 8]
+    },
+    "speaker": {
+      "type": "Text",
+      "parent": "panel",
+      "left": 190, "top": 520,
+      "text": "LERA KONSTANTIN",
+      "fontColor": "#c8d0e0",
+      "fontSize": 16
+    },
+    "btn-ask": {
+      "type": "Rectangle",
+      "parent": "panel",
+      "left": 190, "top": 670, "width": 370, "height": 30,
+      "fillColor": "#2a3040",
+      "strokeColor": "#c8d8f0",
+      "corners": [4, 4, 4, 4]
+    }
+  },
+  "connectors": {
+    "flow-1": {
+      "tailId": "panel",
+      "headId": "btn-ask",
+      "strokeColor": "#c8d8f0"
+    }
+  }
+}
+```
+
+### Key rules
+
+- **Shape IDs are stable local IDs** you control (e.g. `"panel"`, `"btn-ask"`)
+- **`parent`** references another local shape ID for nesting
+- **`type`** uses create-API names: `Rectangle`, `Ellipse`, `Text`, `Line`
+- **Colors** can be hex (`#2a3040`) or Frame0 theme tokens (`$slate6`)
+- After a pull, Frame0 returns its native vocabulary (`Box` for Rectangle,
+  theme tokens for colors). The sync script handles the mapping transparently.
+- The `.idmap.json` mapping file (gitignored) tracks local ID ↔ Frame0 ID
+
+### Sync commands
+
+```bash
+SYNC=".claude/skills/frame0-wireframe/scripts/frame0-sync.py"
+
+# Push local JSON to Frame0 (clears page, recreates all shapes)
+$SYNC push docs/design/wireframes/dialogue/dialogue-box.json
+
+# Pull Frame0 page back to local JSON (preserves local IDs via mapping)
+$SYNC pull "Dialogue Box" docs/design/wireframes/dialogue/dialogue-box.json
+
+# Push + export as PNG in one step
+$SYNC export docs/design/wireframes/dialogue/dialogue-box.json \
+  docs/design/wireframes/dialogue/dialogue-box.png
+```
+
+### Batch export
+
+Use this when exporting multiple wireframes. It runs as a single Bash call,
+avoiding repeated permission prompts.
+
+```bash
+BATCH=".claude/skills/frame0-wireframe/scripts/frame0-export-batch.sh"
+
+# Dry run first — shows full manifest, no Frame0 calls
+$BATCH --dry-run
+
+# Export everything (skips PNGs already newer than their JSON)
+$BATCH
+
+# Export one category only
+$BATCH --category dialogue
+
+# Force re-export of everything
+$BATCH --force
+```
+
+**Always dry-run first, then get approval before running the live export.**
+
+## Low-Level Commands
+
+For ad-hoc operations or exec calls not covered by sync:
+
+```bash
+CMD=".claude/skills/frame0-wireframe/scripts/frame0-cmd.sh"
+$CMD health
+$CMD list-pages
+$CMD current-page
+$CMD get-page <page-id>
+$CMD create-shape Rectangle '{"name":"btn","left":100,"top":100,"width":120,"height":36}'
+$CMD create-connector <tail-id> <head-id>
+$CMD move <shape-id> <dx> <dy>
+$CMD export --format image/png
+$CMD exec "view:fit-to-screen" '{}'
+```
+
+If you find yourself using `exec` for the same command repeatedly, flag it as
+a candidate for a proper wrapper in `frame0-cmd.sh`.
+
+## Project Styling Defaults
+
+Colors from `docs/design/visual-grammar-v01.md`:
+
+| Role | Hex | Frame0 token |
+|------|-----|-------------|
+| Background | `#1a1e24` | `$sage3` |
+| Stroke | `#333340` | `$slate6` |
+| Fill | `#2a3040` | `$slate5` |
+| Text | `#c8d0e0` | `$mint12` |
+| Accent | `#c8d8f0` | `$blue12` |
+
+Use hex when authoring new wireframes. Frame0 maps them to theme tokens on push.
+
+## Output Convention
+
+```
+docs/design/wireframes/
+  hud/              # HUD layout wireframes
+  menus/            # Menu screen wireframes
+  dialogue/         # Dialogue box wireframes
+  insert/           # Neural insert wireframes
+```
+
+Both `.json` source and `.png` exports are tracked in git.
+`.idmap.json` mapping files are gitignored.
+
+## Agent Guidance
+
+- **Araminta** — Primary user. Full wireframe creation, layout iteration,
+  visual consistency. Uses all component library patterns.
+- **Tyre** — Interface architecture wireframes. System boundary diagrams.
+- **Qatux** — Export wireframes for UI decision records and documentation.
+
+## References
+
+- `references/component-library.md` — Pre-built JSON wireframe templates
+  (HUD, dialogue, menus, modals, lists, inventory). Copy and adapt.
+- `references/api-reference.md` — Frame0 HTTP API command reference and
+  type mappings. Read for low-level control.
+- `references/setup-guide.md` — Frame0 installation and startup for Fedora.
@@ -0,0 +1,241 @@
+# Frame0 HTTP API Reference
+
+Frame0 exposes a local HTTP API when the desktop app is running.
+
+## Endpoint
+
+```
+POST http://localhost:{port}/execute_command
+Content-Type: application/json
+```
+
+Default port: **58320** (override via `FRAME0_PORT` env var or `--port` flag).
+
+## Request / Response
+
+```json
+{"command": "namespace:action", "args": { ... }}
+```
+
+```json
+{"success": true, "data": { ... }}
+{"success": false, "error": "description"}
+```
+
+---
+
+## Type Mapping
+
+Frame0 uses different type names for create vs get:
+
+| Create API (`type`) | Get API (internal) | Description |
+|--------------------|--------------------|-------------|
+| `Rectangle` | `Box` | Rectangle with optional corners |
+| `Ellipse` | `Ellipse` | Circle/ellipse |
+| `Text` | `Text` | Text label |
+| `Line` | `Line` | Line/polyline |
+| `Frame` | `Frame` | Container from library |
+| `Freehand` | `Freehand` | Freehand drawing |
+| `Highlighter` | `Highlighter` | Highlighter stroke |
+
+The sync script handles this mapping transparently.
+
+## Color Tokens
+
+Frame0 maps hex colors to theme tokens on creation (`convertColors: true`):
+
+| Hex | Token | Role |
+|-----|-------|------|
+| `#1a1e24` | `$sage3` | Background |
+| `#2a3040` | `$slate5` | Fill |
+| `#333340` | `$slate6` | Stroke |
+| `#c8d0e0` | `$mint12` | Text |
+| `#c8d8f0` | `$blue12` | Accent |
+
+Both hex and token strings work in the API. Tokens are preserved on round-trip.
+
+---
+
+## Commands
+
+### shape:create-shape
+
+```json
+{
+  "command": "shape:create-shape",
+  "args": {
+    "type": "Rectangle",
+    "shapeProps": {
+      "name": "my-button",
+      "left": 100, "top": 200, "width": 120, "height": 36,
+      "fillColor": "#2a3040",
+      "strokeColor": "#c8d8f0",
+      "corners": [4, 4, 4, 4]
+    },
+    "parentId": "optional-parent-shape-id",
+    "convertColors": true
+  }
+}
+```
+
+Returns: shape ID (string).
+
+### shape:get-shape
+
+```json
+{"command": "shape:get-shape", "args": {"shapeId": "id"}}
+```
+
+### shape:update-shape
+
+```json
+{
+  "command": "shape:update-shape",
+  "args": {
+    "shapeId": "id",
+    "shapeProps": {"fillColor": "#1a1e24", "text": "Updated"},
+    "convertColors": true
+  }
+}
+```
+
+### shape:move
+
+```json
+{"command": "shape:move", "args": {"shapeId": "id", "dx": 50, "dy": -20}}
+```
+
+### shape:create-connector
+
+```json
+{
+  "command": "shape:create-connector",
+  "args": {
+    "tailId": "source-id",
+    "headId": "target-id",
+    "shapeProps": {"strokeColor": "#c8d8f0"},
+    "convertColors": true
+  }
+}
+```
+
+### shape:create-icon
+
+```json
+{
+  "command": "shape:create-icon",
+  "args": {
+    "iconName": "search",
+    "shapeProps": {"left": 100, "top": 100, "width": 24, "height": 24}
+  }
+}
+```
+
+### shape:get-available-icons
+
+```json
+{"command": "shape:get-available-icons", "args": {}}
+```
+
+### shape:group / shape:ungroup
+
+```json
+{"command": "shape:group", "args": {"shapeIdArray": ["id1", "id2"]}}
+{"command": "shape:ungroup", "args": {"shapeIdArray": ["group-id"]}}
+```
+
+### edit:delete / edit:duplicate
+
+```json
+{"command": "edit:delete", "args": {"shapeIdArray": ["id1", "id2"]}}
+{"command": "edit:duplicate", "args": {"shapeIdArray": ["id"], "dx": 20, "dy": 0}}
+```
+
+### page:add
+
+```json
+{"command": "page:add", "args": {"pageProps": {"name": "Page Name"}}}
+```
+
+Returns: `{id, type, name}`.
+
+### page:get
+
+```json
+{"command": "page:get", "args": {"pageId": "id", "exportShapes": true}}
+```
+
+### page:get-current-page
+
+```json
+{"command": "page:get-current-page", "args": {}}
+```
+
+Returns: page ID string.
+
+### page:set-current-page
+
+```json
+{"command": "page:set-current-page", "args": {"pageId": "id"}}
+```
+
+### doc:get (list all pages)
+
+```json
+{"command": "doc:get", "args": {"exportPages": true, "exportShapes": false}}
+```
+
+### page:delete
+
+```json
+{"command": "page:delete", "args": {"pageId": "id"}}
+```
+
+### file:export-image
+
+```json
+{
+  "command": "file:export-image",
+  "args": {
+    "pageId": "optional-page-id",
+    "format": "image/png",
+    "fillBackground": true
+  }
+}
+```
+
+Formats: `image/png`, `image/jpeg`, `image/webp`, `image/svg+xml`.
+Returns: base64-encoded image data.
+
+### view:fit-to-screen
+
+```json
+{"command": "view:fit-to-screen", "args": {}}
+```
+
+---
+
+## Shape Properties
+
+| Property | Type | Notes |
+|----------|------|-------|
+| `name` | string | Shape identifier/label |
+| `left` | number | X position (origin: top-left) |
+| `top` | number | Y position |
+| `width` | number | Width in pixels |
+| `height` | number | Height in pixels |
+| `fillColor` | string | Hex or `$token` |
+| `strokeColor` | string | Hex or `$token` |
+| `strokeWidth` | number | Border width |
+| `fontColor` | string | Text color (hex or `$token`) |
+| `fontSize` | number | Font size in pixels |
+| `fontFamily` | string | Font name (Frame0 default: `Loranthus`) |
+| `text` | string | Text content |
+| `wordWrap` | boolean | Enable word wrapping |
+| `corners` | number[4] | Border radius [TL, TR, BR, BL] |
+| `roughness` | number | Sketch roughness (Frame0 default: 1) |
+| `constraints` | array | Auto-sizing constraints |
+| `horzAlign` | string | Horizontal text alignment |
+| `vertAlign` | string | Vertical text alignment |
+| `fillStyle` | string | Fill style (`none` for transparent) |
+| `path` | array | Coordinate pairs for lines |
@@ -0,0 +1,467 @@
+# Component Library
+
+Pre-built wireframe JSON templates for The Settled Reach UI. Copy the JSON,
+adapt positions/sizes, save to `docs/design/wireframes/{category}/`, and push.
+
+**Viewport:** 1140x780 (Godot project settings)
+**Grid unit:** 8px
+**Min touch target:** 36px height
+**Font sizes:** 12 (label), 14 (body), 16 (subtitle), 18 (heading), 24 (title)
+
+---
+
+## 1. HUD Layout
+
+Main gameplay overlay. Minimap top-right, monologue bottom-center,
+insert display bottom-left, action hints bottom-right.
+
+```json
+{
+  "name": "HUD Layout",
+  "shapes": {
+    "minimap": {
+      "type": "Rectangle",
+      "left": 880, "top": 20, "width": 240, "height": 240,
+      "fillColor": "#1a1e24", "strokeColor": "#333340",
+      "corners": [4, 4, 4, 4]
+    },
+    "minimap-label": {
+      "type": "Text",
+      "parent": "minimap",
+      "left": 890, "top": 30,
+      "text": "Minimap",
+      "fontColor": "#c8d0e0", "fontSize": 14
+    },
+    "monologue": {
+      "type": "Rectangle",
+      "left": 300, "top": 680, "width": 520, "height": 80,
+      "fillColor": "#1a1e24", "strokeColor": "#333340",
+      "corners": [4, 4, 4, 4]
+    },
+    "monologue-text": {
+      "type": "Text",
+      "parent": "monologue",
+      "left": 310, "top": 700, "width": 500,
+      "text": "Internal monologue text appears here...",
+      "fontColor": "#c8d0e0", "fontSize": 13, "wordWrap": true
+    },
+    "insert": {
+      "type": "Rectangle",
+      "left": 20, "top": 600, "width": 260, "height": 160,
+      "fillColor": "#1a1e24", "strokeColor": "#333340",
+      "corners": [4, 4, 4, 4]
+    },
+    "insert-label": {
+      "type": "Text",
+      "parent": "insert",
+      "left": 30, "top": 620,
+      "text": "Neural Insert Data",
+      "fontColor": "#c8d0e0", "fontSize": 14
+    },
+    "hints": {
+      "type": "Rectangle",
+      "left": 880, "top": 700, "width": 240, "height": 60,
+      "fillColor": "#1a1e24", "strokeColor": "#333340",
+      "corners": [4, 4, 4, 4]
+    },
+    "hints-label": {
+      "type": "Text",
+      "parent": "hints",
+      "left": 890, "top": 720,
+      "text": "[E] Interact  [TAB] Insert",
+      "fontColor": "#c8d0e0", "fontSize": 12
+    }
+  }
+}
+```
+
+---
+
+## 2. Dialogue Box
+
+Speaker panel with response options. Anchored bottom-center during dialogue mode.
+
+```json
+{
+  "name": "Dialogue Box",
+  "shapes": {
+    "panel": {
+      "type": "Rectangle",
+      "left": 170, "top": 500, "width": 800, "height": 260,
+      "fillColor": "#1a1e24", "strokeColor": "#333340",
+      "corners": [8, 8, 8, 8]
+    },
+    "speaker": {
+      "type": "Text",
+      "parent": "panel",
+      "left": 190, "top": 520,
+      "text": "LERA KONSTANTIN",
+      "fontColor": "#c8d0e0", "fontSize": 16
+    },
+    "text-area": {
+      "type": "Rectangle",
+      "parent": "panel",
+      "left": 190, "top": 550, "width": 760, "height": 100,
+      "fillColor": "#2a3040", "strokeColor": "#333340",
+      "corners": [4, 4, 4, 4]
+    },
+    "dialogue-text": {
+      "type": "Text",
+      "parent": "text-area",
+      "left": 200, "top": 560, "width": 740,
+      "text": "You look like you could use a drink. First time on the station?",
+      "fontColor": "#c8d0e0", "fontSize": 14, "wordWrap": true
+    },
+    "btn-option1": {
+      "type": "Rectangle",
+      "parent": "panel",
+      "left": 190, "top": 670, "width": 370, "height": 30,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0",
+      "corners": [4, 4, 4, 4]
+    },
+    "btn-option1-label": {
+      "type": "Text",
+      "parent": "btn-option1",
+      "left": 200, "top": 674,
+      "text": "[1] Ask about the station",
+      "fontColor": "#c8d8f0", "fontSize": 12
+    },
+    "btn-option2": {
+      "type": "Rectangle",
+      "parent": "panel",
+      "left": 190, "top": 710, "width": 370, "height": 30,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0",
+      "corners": [4, 4, 4, 4]
+    },
+    "btn-option2-label": {
+      "type": "Text",
+      "parent": "btn-option2",
+      "left": 200, "top": 714,
+      "text": "[2] Ask about recent events",
+      "fontColor": "#c8d8f0", "fontSize": 12
+    },
+    "btn-leave": {
+      "type": "Rectangle",
+      "parent": "panel",
+      "left": 580, "top": 670, "width": 180, "height": 30,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0",
+      "corners": [4, 4, 4, 4]
+    },
+    "btn-leave-label": {
+      "type": "Text",
+      "parent": "btn-leave",
+      "left": 590, "top": 674,
+      "text": "[3] Leave",
+      "fontColor": "#c8d8f0", "fontSize": 12
+    }
+  }
+}
+```
+
+---
+
+## 3. Menu Screen
+
+Full-screen menu with sidebar navigation and content area.
+
+```json
+{
+  "name": "Pause Menu",
+  "shapes": {
+    "bg": {
+      "type": "Rectangle",
+      "left": 0, "top": 0, "width": 1140, "height": 780,
+      "fillColor": "#1a1e24"
+    },
+    "nav": {
+      "type": "Rectangle",
+      "parent": "bg",
+      "left": 20, "top": 20, "width": 200, "height": 740,
+      "fillColor": "#2a3040", "strokeColor": "#333340",
+      "corners": [4, 4, 4, 4]
+    },
+    "btn-inventory": {
+      "type": "Rectangle", "parent": "nav",
+      "left": 30, "top": 40, "width": 180, "height": 36,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0", "corners": [4, 4, 4, 4]
+    },
+    "btn-inventory-label": {
+      "type": "Text", "parent": "btn-inventory",
+      "left": 40, "top": 48, "text": "Inventory",
+      "fontColor": "#c8d8f0", "fontSize": 14
+    },
+    "btn-journal": {
+      "type": "Rectangle", "parent": "nav",
+      "left": 30, "top": 86, "width": 180, "height": 36,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0", "corners": [4, 4, 4, 4]
+    },
+    "btn-journal-label": {
+      "type": "Text", "parent": "btn-journal",
+      "left": 40, "top": 94, "text": "Journal",
+      "fontColor": "#c8d8f0", "fontSize": 14
+    },
+    "btn-map": {
+      "type": "Rectangle", "parent": "nav",
+      "left": 30, "top": 132, "width": 180, "height": 36,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0", "corners": [4, 4, 4, 4]
+    },
+    "btn-map-label": {
+      "type": "Text", "parent": "btn-map",
+      "left": 40, "top": 140, "text": "Map",
+      "fontColor": "#c8d8f0", "fontSize": 14
+    },
+    "btn-settings": {
+      "type": "Rectangle", "parent": "nav",
+      "left": 30, "top": 178, "width": 180, "height": 36,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0", "corners": [4, 4, 4, 4]
+    },
+    "btn-settings-label": {
+      "type": "Text", "parent": "btn-settings",
+      "left": 40, "top": 186, "text": "Settings",
+      "fontColor": "#c8d8f0", "fontSize": 14
+    },
+    "btn-resume": {
+      "type": "Rectangle", "parent": "nav",
+      "left": 30, "top": 720, "width": 180, "height": 36,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0", "corners": [4, 4, 4, 4]
+    },
+    "btn-resume-label": {
+      "type": "Text", "parent": "btn-resume",
+      "left": 40, "top": 728, "text": "Resume",
+      "fontColor": "#c8d8f0", "fontSize": 14
+    },
+    "content": {
+      "type": "Rectangle",
+      "parent": "bg",
+      "left": 240, "top": 20, "width": 880, "height": 740,
+      "fillColor": "#2a3040", "strokeColor": "#333340",
+      "corners": [4, 4, 4, 4]
+    },
+    "content-label": {
+      "type": "Text", "parent": "content",
+      "left": 260, "top": 40,
+      "text": "Content area",
+      "fontColor": "#c8d0e0", "fontSize": 14
+    }
+  }
+}
+```
+
+---
+
+## 4. Modal Dialog
+
+Centered overlay for confirmations, alerts, choices.
+
+```json
+{
+  "name": "Modal Dialog",
+  "shapes": {
+    "overlay": {
+      "type": "Rectangle",
+      "left": 0, "top": 0, "width": 1140, "height": 780,
+      "fillColor": "#0a0c10"
+    },
+    "modal": {
+      "type": "Rectangle",
+      "parent": "overlay",
+      "left": 320, "top": 240, "width": 500, "height": 300,
+      "fillColor": "#1a1e24", "strokeColor": "#333340",
+      "corners": [8, 8, 8, 8]
+    },
+    "title": {
+      "type": "Text", "parent": "modal",
+      "left": 340, "top": 260,
+      "text": "Confirm Action",
+      "fontColor": "#c8d0e0", "fontSize": 18
+    },
+    "divider": {
+      "type": "Line", "parent": "modal",
+      "left": 340, "top": 290, "width": 460, "height": 0,
+      "strokeColor": "#333340"
+    },
+    "body-1": {
+      "type": "Text", "parent": "modal",
+      "left": 340, "top": 310,
+      "text": "Are you sure you want to proceed?",
+      "fontColor": "#c8d0e0", "fontSize": 14
+    },
+    "body-2": {
+      "type": "Text", "parent": "modal",
+      "left": 340, "top": 340,
+      "text": "This action cannot be undone.",
+      "fontColor": "#c8d0e0", "fontSize": 14
+    },
+    "btn-cancel": {
+      "type": "Rectangle", "parent": "modal",
+      "left": 480, "top": 480, "width": 120, "height": 36,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0", "corners": [4, 4, 4, 4]
+    },
+    "btn-cancel-label": {
+      "type": "Text", "parent": "btn-cancel",
+      "left": 510, "top": 488,
+      "text": "Cancel",
+      "fontColor": "#c8d8f0", "fontSize": 14
+    },
+    "btn-confirm": {
+      "type": "Rectangle", "parent": "modal",
+      "left": 620, "top": 480, "width": 120, "height": 36,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0", "corners": [4, 4, 4, 4]
+    },
+    "btn-confirm-label": {
+      "type": "Text", "parent": "btn-confirm",
+      "left": 645, "top": 488,
+      "text": "Confirm",
+      "fontColor": "#c8d8f0", "fontSize": 14
+    }
+  }
+}
+```
+
+---
+
+## 5. List View
+
+Scrollable list with item selection and detail panel.
+
+```json
+{
+  "name": "List View",
+  "shapes": {
+    "list-panel": {
+      "type": "Rectangle",
+      "left": 20, "top": 20, "width": 400, "height": 740,
+      "fillColor": "#1a1e24", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "item-1": {
+      "type": "Rectangle", "parent": "list-panel",
+      "left": 30, "top": 30, "width": 380, "height": 40,
+      "fillColor": "#2a3040", "strokeColor": "#c8d8f0", "corners": [4, 4, 4, 4]
+    },
+    "item-1-label": {
+      "type": "Text", "parent": "item-1",
+      "left": 40, "top": 38, "text": "Item Alpha",
+      "fontColor": "#c8d8f0", "fontSize": 14
+    },
+    "item-2": {
+      "type": "Rectangle", "parent": "list-panel",
+      "left": 30, "top": 80, "width": 380, "height": 40,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "item-2-label": {
+      "type": "Text", "parent": "item-2",
+      "left": 40, "top": 88, "text": "Item Beta",
+      "fontColor": "#c8d0e0", "fontSize": 14
+    },
+    "item-3": {
+      "type": "Rectangle", "parent": "list-panel",
+      "left": 30, "top": 130, "width": 380, "height": 40,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "item-3-label": {
+      "type": "Text", "parent": "item-3",
+      "left": 40, "top": 138, "text": "Item Gamma",
+      "fontColor": "#c8d0e0", "fontSize": 14
+    },
+    "detail-panel": {
+      "type": "Rectangle",
+      "left": 440, "top": 20, "width": 680, "height": 740,
+      "fillColor": "#1a1e24", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "detail-title": {
+      "type": "Text", "parent": "detail-panel",
+      "left": 460, "top": 40,
+      "text": "Item Alpha",
+      "fontColor": "#c8d0e0", "fontSize": 18
+    },
+    "detail-body": {
+      "type": "Text", "parent": "detail-panel",
+      "left": 460, "top": 80, "width": 640,
+      "text": "Description and properties appear here.",
+      "fontColor": "#c8d0e0", "fontSize": 14, "wordWrap": true
+    }
+  }
+}
+```
+
+---
+
+## 6. Inventory Grid
+
+Grid of cells for item management.
+
+```json
+{
+  "name": "Inventory Grid",
+  "shapes": {
+    "panel": {
+      "type": "Rectangle",
+      "left": 240, "top": 100, "width": 660, "height": 580,
+      "fillColor": "#1a1e24", "strokeColor": "#333340", "corners": [8, 8, 8, 8]
+    },
+    "title": {
+      "type": "Text", "parent": "panel",
+      "left": 260, "top": 120,
+      "text": "INVENTORY",
+      "fontColor": "#c8d0e0", "fontSize": 18
+    },
+    "cell-1-1": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 260, "top": 160, "width": 64, "height": 64,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "cell-1-2": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 332, "top": 160, "width": 64, "height": 64,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "cell-1-3": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 404, "top": 160, "width": 64, "height": 64,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "cell-1-4": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 476, "top": 160, "width": 64, "height": 64,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "cell-2-1": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 260, "top": 232, "width": 64, "height": 64,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "cell-2-2": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 332, "top": 232, "width": 64, "height": 64,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "cell-2-3": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 404, "top": 232, "width": 64, "height": 64,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "cell-2-4": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 476, "top": 232, "width": 64, "height": 64,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "detail": {
+      "type": "Rectangle", "parent": "panel",
+      "left": 580, "top": 160, "width": 300, "height": 400,
+      "fillColor": "#2a3040", "strokeColor": "#333340", "corners": [4, 4, 4, 4]
+    },
+    "detail-title": {
+      "type": "Text", "parent": "detail",
+      "left": 600, "top": 180,
+      "text": "Selected Item Name",
+      "fontColor": "#c8d0e0", "fontSize": 16
+    },
+    "detail-body": {
+      "type": "Text", "parent": "detail",
+      "left": 600, "top": 210, "width": 260,
+      "text": "Item description and stats",
+      "fontColor": "#c8d0e0", "fontSize": 14, "wordWrap": true
+    }
+  }
+}
+```
@@ -0,0 +1,53 @@
+# Frame0 Setup Guide
+
+## Installation (Fedora)
+
+Download from https://frame0.app/download and install the RPM:
+
+```bash
+sudo dnf install ./frame0-*.x86_64.rpm
+```
+
+Requires: Fedora 40 or later (x86_64).
+
+## Starting Frame0
+
+Launch the desktop application:
+
+```bash
+frame0 &
+```
+
+Frame0 exposes an HTTP API at `localhost:58320` when running.
+
+## Verify API Access
+
+```bash
+.claude/skills/frame0-wireframe/scripts/frame0-cmd.sh health
+```
+
+Expected output: `Frame0 is running on port 58320`
+
+## Port Configuration
+
+Default port: **58320**
+
+To use a different port, set the environment variable:
+
+```bash
+export FRAME0_PORT=58321
+```
+
+Or pass `--port` to any script:
+
+```bash
+.claude/skills/frame0-wireframe/scripts/frame0-cmd.sh --port 58321 health
+```
+
+## Troubleshooting
+
+| Symptom | Cause | Fix |
+|---------|-------|-----|
+| "Connection refused" | Frame0 not running | Start the desktop app |
+| "Port in use" | Another instance running | Close duplicate or use different port |
+| Script hangs | API unresponsive | Restart Frame0 |
@@ -0,0 +1,253 @@
+#!/bin/bash
+set -euo pipefail
+
+PORT="${FRAME0_PORT:-58320}"
+ENDPOINT="http://localhost:${PORT}/execute_command"
+
+usage() {
+  cat <<EOF
+Usage: $(basename "$0") <command> [args...] [--port N]
+
+Low-level Frame0 HTTP API wrapper. Replaces the MCP server with direct
+curl calls. Requires Frame0 desktop app to be running.
+
+Commands:
+  health                              Check if Frame0 is running
+  exec <namespace:action> <json>      Execute a raw API command
+  create-shape <type> <json-props>    Create a shape (Rectangle, Ellipse, Text, Line)
+  get-shape <id>                      Get shape details
+  update-shape <id> <json-props>      Update shape properties
+  delete <id> [id...]                 Delete shapes by ID
+  move <id> <dx> <dy>                 Move a shape by pixel offset
+  duplicate <id>                      Duplicate a shape
+  group <id> [id...]                  Group shapes
+  ungroup <group-id>                  Ungroup a group
+  create-connector <tail-id> <head-id> [json-props]  Connect two shapes
+  create-icon <name> <json-props>     Create an icon shape
+  add-page <name>                     Add a new page (becomes current)
+  get-page [page-id]                  Get current or specific page data
+  list-pages [--shapes]               List all pages (--shapes for shape data)
+  current-page                        Get current page ID
+  set-page <page-id>                  Set current page
+  export [page-id] [--format mime]    Export page as image (default: image/png)
+  fit                                 Fit view to screen
+
+Options:
+  --port N    Frame0 API port (default: $PORT, env: FRAME0_PORT)
+
+Examples:
+  $(basename "$0") health
+  $(basename "$0") add-page "HUD Layout"
+  $(basename "$0") create-shape Rectangle '{"name":"btn","left":100,"top":100,"width":120,"height":36}'
+  $(basename "$0") list-pages
+  $(basename "$0") export --format image/png
+EOF
+  exit 1
+}
+
+# Parse --port from anywhere in args
+ARGS=()
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --port) PORT="$2"; ENDPOINT="http://localhost:${PORT}/execute_command"; shift 2 ;;
+    *)      ARGS+=("$1"); shift ;;
+  esac
+done
+set -- "${ARGS[@]+"${ARGS[@]}"}"
+
+[[ $# -lt 1 ]] && usage
+
+# Execute a Frame0 API command, return data or error
+frame0_exec() {
+  local command="$1"
+  local args
+  args="${2:-"{}"}"
+
+  local response
+  response=$(curl -s -w "\n%{http_code}" -X POST "$ENDPOINT" \
+    -H "Content-Type: application/json" \
+    -d "{\"command\": \"$command\", \"args\": $args}" 2>&1) || {
+    echo "ERROR: Cannot connect to Frame0 at localhost:$PORT" >&2
+    echo "Is Frame0 running? See: .claude/skills/frame0-wireframe/references/setup-guide.md" >&2
+    return 1
+  }
+
+  local http_code body
+  http_code=$(echo "$response" | tail -1)
+  body=$(echo "$response" | sed '$d')
+
+  if [[ "$http_code" != 2* ]]; then
+    echo "ERROR: HTTP $http_code from Frame0" >&2
+    echo "$body" >&2
+    return 1
+  fi
+
+  # Parse success/error from response
+  python3 -c "
+import sys, json
+try:
+    r = json.loads(sys.stdin.read())
+    if r.get('success'):
+        d = r.get('data')
+        if d is not None:
+            print(json.dumps(d, indent=2))
+    else:
+        print('ERROR: ' + str(r.get('error', 'Unknown error')), file=sys.stderr)
+        sys.exit(1)
+except json.JSONDecodeError as e:
+    print(f'ERROR: Invalid JSON response: {e}', file=sys.stderr)
+    sys.exit(1)
+" <<< "$body"
+}
+
+# Build JSON array from remaining args
+ids_to_json_array() {
+  local arr="["
+  local first=true
+  for id in "$@"; do
+    [[ "$first" == true ]] && first=false || arr+=","
+    arr+="\"$id\""
+  done
+  arr+="]"
+  echo "$arr"
+}
+
+CMD="${1:-}"
+shift || true
+
+case "$CMD" in
+  health)
+    if curl -s -o /dev/null -w "%{http_code}" "http://localhost:${PORT}/" 2>/dev/null | grep -q "^[23]"; then
+      echo "Frame0 is running on port $PORT"
+    else
+      echo "Frame0 is NOT running on port $PORT" >&2
+      echo "Start Frame0 desktop app, then retry." >&2
+      echo "See: .claude/skills/frame0-wireframe/references/setup-guide.md" >&2
+      exit 1
+    fi
+    ;;
+
+  exec)
+    [[ $# -lt 2 ]] && { echo "Usage: exec <command> <json-args>" >&2; exit 1; }
+    frame0_exec "$1" "$2"
+    ;;
+
+  create-shape)
+    [[ $# -lt 2 ]] && { echo "Usage: create-shape <Type> <json-props>" >&2; exit 1; }
+    local_type="$1"
+    local_props="$2"
+    local_parent="${3:-}"
+    local_parent_arg=""
+    [[ -n "$local_parent" ]] && local_parent_arg=", \"parentId\": \"$local_parent\""
+    frame0_exec "shape:create-shape" "{\"type\": \"$local_type\", \"shapeProps\": $local_props$local_parent_arg, \"convertColors\": true}"
+    ;;
+
+  get-shape)
+    [[ $# -lt 1 ]] && { echo "Usage: get-shape <id>" >&2; exit 1; }
+    frame0_exec "shape:get-shape" "{\"shapeId\": \"$1\"}"
+    ;;
+
+  update-shape)
+    [[ $# -lt 2 ]] && { echo "Usage: update-shape <id> <json-props>" >&2; exit 1; }
+    frame0_exec "shape:update-shape" "{\"shapeId\": \"$1\", \"shapeProps\": $2, \"convertColors\": true}"
+    ;;
+
+  delete)
+    [[ $# -lt 1 ]] && { echo "Usage: delete <id> [id...]" >&2; exit 1; }
+    local_arr=$(ids_to_json_array "$@")
+    frame0_exec "edit:delete" "{\"shapeIdArray\": $local_arr}"
+    ;;
+
+  move)
+    [[ $# -lt 3 ]] && { echo "Usage: move <id> <dx> <dy>" >&2; exit 1; }
+    frame0_exec "shape:move" "{\"shapeId\": \"$1\", \"dx\": $2, \"dy\": $3}"
+    ;;
+
+  duplicate)
+    [[ $# -lt 1 ]] && { echo "Usage: duplicate <id> [dx] [dy]" >&2; exit 1; }
+    local_dx="${2:-0}"
+    local_dy="${3:-0}"
+    frame0_exec "edit:duplicate" "{\"shapeIdArray\": [\"$1\"], \"dx\": $local_dx, \"dy\": $local_dy}"
+    ;;
+
+  group)
+    [[ $# -lt 2 ]] && { echo "Usage: group <id> <id> [id...]" >&2; exit 1; }
+    local_arr=$(ids_to_json_array "$@")
+    frame0_exec "shape:group" "{\"shapeIdArray\": $local_arr}"
+    ;;
+
+  ungroup)
+    [[ $# -lt 1 ]] && { echo "Usage: ungroup <group-id>" >&2; exit 1; }
+    frame0_exec "shape:ungroup" "{\"shapeIdArray\": [\"$1\"]}"
+    ;;
+
+  create-connector)
+    [[ $# -lt 2 ]] && { echo "Usage: create-connector <tail-id> <head-id> [json-props]" >&2; exit 1; }
+    local_props="${3:-{}}"
+    frame0_exec "shape:create-connector" "{\"tailId\": \"$1\", \"headId\": \"$2\", \"shapeProps\": $local_props, \"convertColors\": true}"
+    ;;
+
+  create-icon)
+    [[ $# -lt 2 ]] && { echo "Usage: create-icon <name> <json-props>" >&2; exit 1; }
+    frame0_exec "shape:create-icon" "{\"iconName\": \"$1\", \"shapeProps\": $2, \"convertColors\": true}"
+    ;;
+
+  add-page)
+    [[ $# -lt 1 ]] && { echo "Usage: add-page <name>" >&2; exit 1; }
+    frame0_exec "page:add" "{\"pageProps\": {\"name\": \"$1\"}}"
+    ;;
+
+  get-page)
+    if [[ $# -ge 1 ]]; then
+      frame0_exec "page:get" "{\"pageId\": \"$1\", \"exportShapes\": true}"
+    else
+      local_id
+      local_id=$(frame0_exec "page:get-current-page")
+      # Strip quotes from returned ID
+      local_id=$(echo "$local_id" | tr -d '"')
+      frame0_exec "page:get" "{\"pageId\": \"$local_id\", \"exportShapes\": true}"
+    fi
+    ;;
+
+  list-pages)
+    local_shapes="false"
+    [[ "${1:-}" == "--shapes" ]] && local_shapes="true"
+    frame0_exec "doc:get" "{\"exportPages\": true, \"exportShapes\": $local_shapes}"
+    ;;
+
+  current-page)
+    frame0_exec "page:get-current-page"
+    ;;
+
+  set-page)
+    [[ $# -lt 1 ]] && { echo "Usage: set-page <page-id>" >&2; exit 1; }
+    frame0_exec "page:set-current-page" "{\"pageId\": \"$1\"}"
+    ;;
+
+  export)
+    local_page_id=""
+    local_format="image/png"
+    while [[ $# -gt 0 ]]; do
+      case "$1" in
+        --format) local_format="$2"; shift 2 ;;
+        *) local_page_id="$1"; shift ;;
+      esac
+    done
+    local_page_arg=""
+    [[ -n "$local_page_id" ]] && local_page_arg="\"pageId\": \"$local_page_id\", "
+    frame0_exec "file:export-image" "{${local_page_arg}\"format\": \"$local_format\", \"fillBackground\": true}"
+    ;;
+
+  fit)
+    frame0_exec "view:fit-to-screen"
+    ;;
+
+  --help|-h|help)
+    usage
+    ;;
+
+  *)
+    echo "Unknown command: $CMD" >&2
+    usage
+    ;;
+esac
@@ -0,0 +1,159 @@
+#!/usr/bin/env bash
+# Batch export wireframes from JSON to PNG via Frame0.
+#
+# Finds all .json wireframe files under docs/design/wireframes/ and exports
+# each to a matching .png. Skips files whose PNG is already newer than the
+# JSON, unless --force is passed.
+#
+# Usage:
+#   frame0-export-batch.sh [--dry-run] [--force] [--category CAT] [--root DIR]
+#
+# Options:
+#   --dry-run       Print manifest only, don't touch Frame0.
+#   --force         Re-export even if PNG already exists and is up to date.
+#   --category CAT  Limit to one subdirectory (e.g. --category dialogue)
+#   --root DIR      Wireframes root dir (default: docs/design/wireframes)
+#
+# Exit codes:
+#   0  All exports succeeded (or nothing to do)
+#   1  One or more exports failed
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../../../.." && pwd)"
+SYNC="$SCRIPT_DIR/frame0-sync.py"
+DEFAULT_ROOT="$REPO_ROOT/docs/design/wireframes"
+
+DRY_RUN=false
+FORCE=false
+CATEGORY=""
+WF_ROOT="$DEFAULT_ROOT"
+
+# Parse arguments
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --dry-run)    DRY_RUN=true; shift ;;
+    --force)      FORCE=true; shift ;;
+    --category)   CATEGORY="$2"; shift 2 ;;
+    --root)       WF_ROOT="$2"; shift 2 ;;
+    -h|--help)
+      sed -n '/^# /p' "$0" | sed 's/^# //'
+      exit 0
+      ;;
+    *) echo "Unknown option: $1" >&2; exit 1 ;;
+  esac
+done
+
+if [[ ! -d "$WF_ROOT" ]]; then
+  echo "ERROR: Wireframes directory not found: $WF_ROOT" >&2
+  exit 1
+fi
+
+# Collect JSON files, optionally filtered by category subdirectory
+mapfile -t JSON_FILES < <(
+  if [[ -n "$CATEGORY" ]]; then
+    find "$WF_ROOT/$CATEGORY" -name "*.json" ! -name ".*" | sort
+  else
+    find "$WF_ROOT" -name "*.json" ! -name ".*" | sort
+  fi
+)
+
+if [[ ${#JSON_FILES[@]} -eq 0 ]]; then
+  echo "No wireframe JSON files found."
+  exit 0
+fi
+
+# Classify files into to-export and to-skip
+TO_EXPORT=()
+TO_SKIP=()
+
+for json in "${JSON_FILES[@]}"; do
+  png="${json%.json}.png"
+  if $FORCE || [[ ! -f "$png" ]] || [[ "$json" -nt "$png" ]]; then
+    TO_EXPORT+=("$json")
+  else
+    TO_SKIP+=("$json")
+  fi
+done
+
+# Print manifest
+if [[ ${#TO_EXPORT[@]} -gt 0 ]]; then
+  echo ""
+  echo "Will export (${#TO_EXPORT[@]} files):"
+  for json in "${TO_EXPORT[@]}"; do
+    png="${json%.json}.png"
+    rel="${json#$REPO_ROOT/}"
+    if [[ ! -f "$png" ]]; then
+      status="new"
+    else
+      status="updated"
+    fi
+    printf "  [%-7s]  %s\n" "$status" "$rel"
+  done
+else
+  echo ""
+  echo "Nothing to export (all PNGs up to date)."
+fi
+
+if [[ ${#TO_SKIP[@]} -gt 0 ]]; then
+  echo ""
+  echo "Will skip (${#TO_SKIP[@]} files already up to date):"
+  for json in "${TO_SKIP[@]}"; do
+    rel="${json#$REPO_ROOT/}"
+    printf "  [skip   ]  %s\n" "$rel"
+  done
+fi
+
+if $DRY_RUN; then
+  echo ""
+  echo "Dry run — no exports performed."
+  exit 0
+fi
+
+if [[ ${#TO_EXPORT[@]} -eq 0 ]]; then
+  exit 0
+fi
+
+echo ""
+PASSED=0
+FAILED=0
+FAILED_FILES=()
+
+TOTAL=${#TO_EXPORT[@]}
+IDX=0
+
+for json in "${TO_EXPORT[@]}"; do
+  IDX=$((IDX + 1))
+  png="${json%.json}.png"
+  rel="${json#$REPO_ROOT/}"
+
+  printf "[%d/%d]  %s ... " "$IDX" "$TOTAL" "$rel"
+
+  output=$(python3 "$SYNC" export "$json" "$png" 2>/tmp/frame0-batch-err.txt)
+  rc=$?
+  if [[ $rc -eq 0 ]]; then
+    size=$(echo "$output" | tail -1 | grep -oP '\(\K[^)]+' || true)
+    echo "ok  $size"
+    PASSED=$((PASSED + 1))
+  else
+    echo "FAILED"
+    cat /tmp/frame0-batch-err.txt >&2
+    FAILED=$((FAILED + 1))
+    FAILED_FILES+=("$rel")
+  fi
+done
+
+echo ""
+echo "$PASSED exported, $FAILED failed."
+
+if [[ $FAILED -gt 0 ]]; then
+  echo ""
+  echo "Failed:" >&2
+  for f in "${FAILED_FILES[@]}"; do
+    echo "  $f" >&2
+  done
+  exit 1
+fi
+
+exit 0
@@ -0,0 +1,414 @@
+#!/usr/bin/env python3
+"""Frame0 sync: push local JSON wireframes to Frame0, pull pages back.
+
+Local JSON is source of truth. Frame0 is a renderer.
+A mapping file tracks local_id <-> frame0_id across push/pull cycles.
+
+Usage:
+    frame0-sync.py push <wireframe.json> [--port PORT]
+    frame0-sync.py pull <page-id|page-name> <output.json> [--port PORT]
+    frame0-sync.py export <wireframe.json> <output.png> [--port PORT] [--format MIME]
+"""
+
+import argparse
+import json
+import os
+import sys
+import urllib.request
+import urllib.error
+
+DEFAULT_PORT = 58320
+
+
+def api(port, command, args=None):
+    """Execute a Frame0 API command. Returns the data field on success."""
+    url = f"http://localhost:{port}/execute_command"
+    payload = json.dumps({"command": command, "args": args or {}}).encode()
+    req = urllib.request.Request(url, data=payload, headers={"Content-Type": "application/json"})
+    try:
+        with urllib.request.urlopen(req) as resp:
+            result = json.loads(resp.read())
+    except urllib.error.HTTPError as e:
+        body = e.read().decode()
+        print(f"ERROR: {command}: HTTP {e.code}: {body[:500]}", file=sys.stderr)
+        sys.exit(1)
+    except urllib.error.URLError as e:
+        print(f"ERROR: Cannot connect to Frame0 on port {port}: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if not result.get("success"):
+        print(f"ERROR: {command}: {result.get('error', 'unknown')}", file=sys.stderr)
+        sys.exit(1)
+
+    return result.get("data")
+
+
+# -- Mapping file management --------------------------------------------------
+
+def mapping_path(wireframe_path):
+    """Derive the idmap path from the wireframe JSON path."""
+    d = os.path.dirname(wireframe_path)
+    base = os.path.splitext(os.path.basename(wireframe_path))[0]
+    return os.path.join(d, f".{base}.idmap.json")
+
+
+def load_mapping(wireframe_path):
+    p = mapping_path(wireframe_path)
+    if os.path.exists(p):
+        with open(p) as f:
+            return json.load(f)
+    return {"page_id": None, "shapes": {}, "connectors": {}}
+
+
+def save_mapping(wireframe_path, mapping):
+    p = mapping_path(wireframe_path)
+    os.makedirs(os.path.dirname(p) or ".", exist_ok=True)
+    with open(p, "w") as f:
+        json.dump(mapping, f, indent=2)
+        f.write("\n")
+
+
+# -- Push: local JSON -> Frame0 -----------------------------------------------
+
+# Frame0 returns different type names from get vs what create accepts.
+# Map internal types back to create-API types.
+TYPE_TO_CREATE = {
+    "Box": "Rectangle",
+    "box": "Rectangle",
+}
+
+
+def topo_sort_shapes(shapes):
+    """Sort shape IDs so parents come before children."""
+    order = []
+    visited = set()
+
+    def visit(sid):
+        if sid in visited:
+            return
+        visited.add(sid)
+        shape = shapes[sid]
+        parent = shape.get("parent")
+        if parent and parent in shapes:
+            visit(parent)
+        order.append(sid)
+
+    for sid in shapes:
+        visit(sid)
+    return order
+
+
+def find_or_create_page(port, name, mapping):
+    """Find existing page by mapping or name, or create a new one."""
+    # Try mapped page_id first
+    if mapping.get("page_id"):
+        try:
+            page = api(port, "page:get", {"pageId": mapping["page_id"]})
+            if page:
+                return mapping["page_id"]
+        except SystemExit:
+            pass  # Page no longer exists, fall through
+
+    # Search by name in existing pages
+    doc = api(port, "doc:get", {"exportPages": True, "exportShapes": False})
+    if doc and "children" in doc:
+        for page in doc["children"]:
+            if page.get("name") == name:
+                return page["id"]
+
+    # Create new page
+    page = api(port, "page:add", {"pageProps": {"name": name}})
+    return page["id"]
+
+
+def clear_page(port, page_id):
+    """Delete all shapes on a page."""
+    page = api(port, "page:get", {"pageId": page_id, "exportShapes": True})
+    if not page or "children" not in page:
+        return
+    shape_ids = [s["id"] for s in page["children"]]
+    if shape_ids:
+        api(port, "edit:delete", {"shapeIdArray": shape_ids})
+
+
+def push(wireframe_path, port):
+    """Push local wireframe JSON to Frame0."""
+    with open(wireframe_path) as f:
+        wireframe = json.load(f)
+
+    name = wireframe.get("name", os.path.splitext(os.path.basename(wireframe_path))[0])
+    shapes = wireframe.get("shapes", {})
+    connectors = wireframe.get("connectors", {})
+
+    mapping = load_mapping(wireframe_path)
+
+    # Find or create page
+    page_id = find_or_create_page(port, name, mapping)
+    mapping["page_id"] = page_id
+
+    # Switch to page and clear it
+    api(port, "page:set-current-page", {"pageId": page_id})
+    clear_page(port, page_id)
+
+    # Reset ID mappings (shapes are recreated)
+    mapping["shapes"] = {}
+    mapping["connectors"] = {}
+
+    # Create shapes in dependency order
+    order = topo_sort_shapes(shapes)
+    for local_id in order:
+        shape = shapes[local_id]
+        raw_type = shape.get("type", "Rectangle")
+        shape_type = TYPE_TO_CREATE.get(raw_type, raw_type)
+        parent_local = shape.get("parent")
+
+        # Build shapeProps from everything except meta fields
+        meta_keys = {"type", "parent"}
+        props = {k: v for k, v in shape.items() if k not in meta_keys}
+
+        # Set name to local_id if not explicitly set
+        if "name" not in props:
+            props["name"] = local_id
+
+        create_args = {
+            "type": shape_type,
+            "shapeProps": props,
+            "convertColors": True,
+        }
+
+        # Resolve parent ID
+        if parent_local and parent_local in mapping["shapes"]:
+            create_args["parentId"] = mapping["shapes"][parent_local]
+
+        f0_id = api(port, "shape:create-shape", create_args)
+        mapping["shapes"][local_id] = f0_id
+
+    # Create connectors
+    for local_id, conn in connectors.items():
+        tail_local = conn.get("tailId")
+        head_local = conn.get("headId")
+
+        if tail_local not in mapping["shapes"] or head_local not in mapping["shapes"]:
+            print(f"WARNING: connector '{local_id}' references unknown shape, skipping", file=sys.stderr)
+            continue
+
+        meta_keys = {"tailId", "headId"}
+        props = {k: v for k, v in conn.items() if k not in meta_keys}
+        if "name" not in props:
+            props["name"] = local_id
+
+        f0_id = api(port, "shape:create-connector", {
+            "tailId": mapping["shapes"][tail_local],
+            "headId": mapping["shapes"][head_local],
+            "shapeProps": props,
+            "convertColors": True,
+        })
+        mapping["connectors"][local_id] = f0_id
+
+    # Fit to screen
+    api(port, "view:fit-to-screen")
+
+    save_mapping(wireframe_path, mapping)
+    total = len(mapping["shapes"]) + len(mapping["connectors"])
+    print(f"Pushed '{name}' to Frame0: {len(mapping['shapes'])} shapes, {len(mapping['connectors'])} connectors")
+
+
+# -- Pull: Frame0 -> local JSON -----------------------------------------------
+
+def pull(page_ref, output_path, port):
+    """Pull a Frame0 page into local wireframe JSON."""
+    # Resolve page_ref: could be an ID or a name
+    page_id = None
+    doc = api(port, "doc:get", {"exportPages": True, "exportShapes": False})
+    if doc and "children" in doc:
+        for page in doc["children"]:
+            if page["id"] == page_ref or page.get("name") == page_ref:
+                page_id = page["id"]
+                page_name = page.get("name", page_ref)
+                break
+
+    if not page_id:
+        print(f"ERROR: Page not found: {page_ref}", file=sys.stderr)
+        sys.exit(1)
+
+    # Load existing mapping for reverse lookup
+    mapping = load_mapping(output_path)
+    reverse_map = {v: k for k, v in mapping.get("shapes", {}).items()}
+    reverse_conn = {v: k for k, v in mapping.get("connectors", {}).items()}
+
+    # Get full page with shapes
+    page = api(port, "page:get", {"pageId": page_id, "exportShapes": True})
+
+    shapes = {}
+    connectors = {}
+    new_mapping = {"page_id": page_id, "shapes": {}, "connectors": {}}
+    auto_id_counter = [0]
+
+    def auto_id(f0_shape):
+        """Generate a stable local ID from shape name or auto-number."""
+        # Prefer existing mapping
+        f0_id = f0_shape["id"]
+        if f0_id in reverse_map:
+            return reverse_map[f0_id]
+        # Use sanitized name
+        name = f0_shape.get("name", "")
+        if name:
+            sanitized = name.lower().replace(" ", "-").replace("_", "-")
+            if sanitized not in shapes:
+                return sanitized
+        # Fallback: auto-number
+        auto_id_counter[0] += 1
+        return f"s{auto_id_counter[0]:03d}"
+
+    def process_shape(f0_shape, parent_local_id=None):
+        f0_id = f0_shape["id"]
+        local_id = auto_id(f0_shape)
+        new_mapping["shapes"][local_id] = f0_id
+
+        # Extract shape properties — only strip structural keys that our
+        # ID mapping replaces. Everything else passes through as-is so the
+        # local JSON speaks Frame0's native vocabulary.
+        shape_type = f0_shape.get("type", "Box")
+        skip_keys = {"id", "type", "children", "pageId", "parentId"}
+        props = {k: v for k, v in f0_shape.items() if k not in skip_keys and v is not None}
+
+        entry = {"type": shape_type}
+        if parent_local_id:
+            entry["parent"] = parent_local_id
+        entry.update(props)
+
+        # Remove name if it matches local_id (redundant)
+        if entry.get("name") == local_id:
+            del entry["name"]
+
+        shapes[local_id] = entry
+
+        # Process children recursively
+        for child in f0_shape.get("children", []):
+            child_type = child.get("type", "")
+            if child_type == "Connector":
+                process_connector(child)
+            else:
+                process_shape(child, local_id)
+
+    def process_connector(f0_conn):
+        f0_id = f0_conn["id"]
+        local_id = reverse_conn.get(f0_id)
+        if not local_id:
+            auto_id_counter[0] += 1
+            local_id = f"c{auto_id_counter[0]:03d}"
+
+        new_mapping["connectors"][local_id] = f0_id
+
+        tail_f0 = f0_conn.get("tail", {}).get("id")
+        head_f0 = f0_conn.get("head", {}).get("id")
+
+        entry = {}
+        if tail_f0:
+            # Will be resolved after all shapes are processed
+            entry["_tailF0"] = tail_f0
+        if head_f0:
+            entry["_headF0"] = head_f0
+
+        skip_keys = {"id", "type", "children", "pageId", "tail", "head"}
+        props = {k: v for k, v in f0_conn.items() if k not in skip_keys and v is not None}
+        entry.update(props)
+
+        connectors[local_id] = entry
+
+    # Process all top-level shapes
+    for child in page.get("children", []):
+        child_type = child.get("type", "")
+        if child_type == "Connector":
+            process_connector(child)
+        else:
+            process_shape(child)
+
+    # Resolve connector references to local IDs
+    f0_to_local = {v: k for k, v in new_mapping["shapes"].items()}
+    for conn in connectors.values():
+        tail_f0 = conn.pop("_tailF0", None)
+        head_f0 = conn.pop("_headF0", None)
+        if tail_f0 and tail_f0 in f0_to_local:
+            conn["tailId"] = f0_to_local[tail_f0]
+        if head_f0 and head_f0 in f0_to_local:
+            conn["headId"] = f0_to_local[head_f0]
+
+    wireframe = {"name": page_name}
+    if shapes:
+        wireframe["shapes"] = shapes
+    if connectors:
+        wireframe["connectors"] = connectors
+
+    os.makedirs(os.path.dirname(output_path) or ".", exist_ok=True)
+    with open(output_path, "w") as f:
+        json.dump(wireframe, f, indent=2)
+        f.write("\n")
+
+    save_mapping(output_path, new_mapping)
+    print(f"Pulled '{page_name}' -> {output_path}: {len(shapes)} shapes, {len(connectors)} connectors")
+
+
+# -- Export: push then export as image -----------------------------------------
+
+def export_image(wireframe_path, output_path, port, fmt="image/png"):
+    """Push wireframe to Frame0 and export the page as an image."""
+    import base64
+
+    # Push first to ensure Frame0 is up to date
+    push(wireframe_path, port)
+
+    mapping = load_mapping(wireframe_path)
+    page_id = mapping.get("page_id")
+    if not page_id:
+        print("ERROR: No page_id in mapping after push", file=sys.stderr)
+        sys.exit(1)
+
+    image_b64 = api(port, "file:export-image", {
+        "pageId": page_id,
+        "format": fmt,
+        "fillBackground": True,
+    })
+
+    image_bytes = base64.b64decode(image_b64)
+    with open(output_path, "wb") as f:
+        f.write(image_bytes)
+
+    print(f"Exported: {output_path} ({len(image_bytes) // 1024}KB)")
+
+
+# -- CLI -----------------------------------------------------------------------
+
+def main():
+    parser = argparse.ArgumentParser(description="Sync wireframe JSON with Frame0")
+    parser.add_argument("--port", type=int, default=int(os.environ.get("FRAME0_PORT", DEFAULT_PORT)))
+    sub = parser.add_subparsers(dest="command")
+
+    p_push = sub.add_parser("push", help="Push local JSON to Frame0")
+    p_push.add_argument("wireframe", help="Path to wireframe .json file")
+
+    p_pull = sub.add_parser("pull", help="Pull Frame0 page to local JSON")
+    p_pull.add_argument("page", help="Page ID or page name")
+    p_pull.add_argument("output", help="Output .json path")
+
+    p_export = sub.add_parser("export", help="Push and export as image")
+    p_export.add_argument("wireframe", help="Path to wireframe .json file")
+    p_export.add_argument("output", help="Output image path (e.g. wireframe.png)")
+    p_export.add_argument("--format", default="image/png",
+                         help="Export MIME type (default: image/png)")
+
+    args = parser.parse_args()
+
+    if args.command == "push":
+        push(args.wireframe, args.port)
+    elif args.command == "pull":
+        pull(args.page, args.output, args.port)
+    elif args.command == "export":
+        export_image(args.wireframe, args.output, args.port, args.format)
+    else:
+        parser.print_help()
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()
@@ -1,8 +1,8 @@
 ---
-name: commit
+name: git-commit
 description: >
  Commit changes with clean, structured messages. Use when the user says
-  "commit", "save my work", "commit changes", or invokes /commit. Enforces
+  "commit", "save my work", "commit changes", or invokes /git-commit. Enforces
  conventional commit format, groups changes into logical commits, and maintains
  CHANGELOG.md. Never squash unrelated changes into one commit.
 user-invocable: true
@@ -93,7 +93,7 @@ Updated briefings for Tyre and Troblum with new requirements.
 chore(agents): add Stig UI developer agent

 Standby agent for UI implementation phase. Configured with
-briefing reference and Commonwealth-themed personality.
+briefing reference and Settled Reach-themed personality.
 ```

 ## CHANGELOG.md Format
@@ -136,7 +136,5 @@ chore(meta): release v0.1.0

 ## Staging Rules

- Stage files by name — never use `git add -A` or `git add .`
- Verify no secrets, saves, or binary blobs are staged
- Skip files in `.gitignore`
- The `.claude/` directory IS tracked — skills belong in the repo
+See `.claude/rules/git-safety.md` for staging rules (always-loaded).
+These apply to ALL git operations, not just this skill.
@@ -1,5 +1,5 @@
 ---
-name: asset-gen
+name: image-gen
 description: >
  Generate themed visual assets for the Lords of Ash CK3 total conversion mod
  using the generate_image MCP tool (Nano Banana / Gemini 2.5 Flash Image).
@@ -0,0 +1,144 @@
+---
+name: pr-push
+description: >
+  Push commits and create or update a pull request. Use when the user says
+  "push pr", "push and create pr", "update pr", "create a pr", "open a pr",
+  or invokes /pr-push. NOT triggered by plain "push" (that's just git push).
+  Pushes the current branch, creates a PR if none exists, or confirms the
+  existing PR was updated. NEVER merges the PR into main — this skill only
+  pushes to the branch and manages the PR lifecycle.
+user-invocable: true
+allowed-tools: Bash, Read, Grep, Glob, AskUserQuestion, Skill
+---
+
+# Push PR Skill
+
+Push commits to remote and create or update a PR. Operates exclusively on the
+current branch — never touches main.
+
+## Safety Rules (NON-NEGOTIABLE)
+
+- **NEVER merge a PR into main.** No `tea pr merge`, no `git merge` into main.
+- **NEVER checkout or push to main.**
+- **NEVER force-push** unless the user explicitly requests it.
+- **NEVER use `--no-verify` or skip hooks.**
+- Only push to the current working branch.
+
+## Workflow
+
+### 1. Validate branch
+
+```bash
+git branch --show-current
+```
+
+If on `main`, stop: "You're on main. Switch to a team branch first."
+
+### 2. Commit uncommitted changes
+
+```bash
+git status
+```
+
+If there are uncommitted changes (staged or unstaged), run the **commit skill**
+first. Use the `/git-commit` skill to group changes into logical commits with
+proper conventional commit messages. Wait for commit to complete before
+proceeding.
+
+If the working tree is clean (no uncommitted changes), skip to step 3.
+
+### 3. Check for unpushed commits
+
+```bash
+git fetch --all
+git log --oneline origin/<branch>..<branch>
+```
+
+If no unpushed commits, skip to step 5 (PR check).
+
+### 4. Check for conflicts with main
+
+```bash
+git merge-tree --write-tree origin/main HEAD 2>&1
+```
+
+If conflicts reported, merge main into current branch:
+
+```bash
+git merge origin/main --no-edit
+```
+
+If merge conflicts, **stop and report** — let the user resolve.
+If clean, continue.
+
+### 5. Push
+
+```bash
+git push origin <branch>
+```
+
+If push fails, stop and report. Never force-push without explicit request.
+
+### 6. Check for existing PR
+
+```bash
+tea pr list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
+```
+
+Match current branch name in PR list.
+
+- **PR exists**: Report "Pushed N commits to `<branch>`. PR #X updated." Done.
+- **No PR**: Continue to step 7.
+
+### 7. Create a new PR
+
+```bash
+git log --oneline main..<branch>
+git diff --stat main...<branch>
+```
+
+Draft title (`<type>(<scope>): <summary>`, max 70 chars) and description.
+
+```bash
+tea pr create \
+  --repo jpmschweitzer/settled-reach \
+  --login schweitz \
+  --title "<title>" \
+  --description "## Summary ..." \
+  --base main \
+  --head <branch>
+```
+
+Report PR URL when done.
+
+### 8. Update ticket status to review
+
+Scan all commit messages in the PR for ticket references (`#NNN`):
+
+```bash
+git log --oneline main..<branch>
+```
+
+Extract ticket IDs from `#NNN` patterns. For each ticket that is
+currently `in_progress`, update it to `review`:
+
+```bash
+tooling/db/ticket status <id> review
+```
+
+Report which tickets were moved to review. Skip tickets that are
+already `done`, `review`, `cancelled`, or `backlog` (only transition
+`in_progress` → `review`).
+
+### 9. Next steps
+
+If a sprint team is active (you are the team lead), do NOT shut down
+agents after pushing. The team should remain alive for PR review and
+potential comment fixes.
+
+Suggest: "PR created/updated. Run `/pr-review` to review before merge."
+
+## Arguments
+
+If the user passes arguments (e.g., `/pr-push "my title"`), use them as the
+PR title instead of generating one.
@@ -0,0 +1,237 @@
+---
+name: pr-review
+description: >
+  Review a branch diff with team-appropriate agents before merge. Use when the
+  user says "review-pr", "review this PR", "review this branch", or invokes
+  /pr-review. Spawns reviewers matched to the branch type (code, copy, visual,
+  audio) in parallel. Reports approve/reject with inline comments.
+user-invocable: true
+allowed-tools: Bash, Read, Grep, Glob, Task
+---
+
+# PR Review Skill
+
+Multi-agent review of a branch diff against main. Reviewer composition depends
+on the branch type. All reviewers must approve for a clean review.
+
+## Workflow
+
+### 0. Branch guard — MUST be run by a Claude instance in the `main` worktree
+
+```bash
+git branch --show-current
+```
+
+If the current branch is **not `main`**, stop immediately and tell the user:
+"PR reviews must be run by a Claude instance in the `main` worktree."
+Do NOT proceed with the review. Do NOT work around this by reading files
+from another worktree — the review agent itself must be running in main.
+Stop and wait for the user to invoke `/pr-review` from main.
+
+### 1. Determine the branch to review
+
+If the user provided a branch name as argument, use it. Otherwise list open
+PRs and ask the user which branch to review.
+
+To list open PRs on Gitea:
+```bash
+tea pr list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
+```
+
+Fetch remote branches first:
+```bash
+git fetch --all
+```
+
+### 2. Determine reviewer team
+
+Map the branch name to a reviewer set. Use the branch prefix (before any `/`
+or `-` suffix) to classify:
+
+| Branch type | Branches | Reviewers |
+|-------------|----------|-----------|
+| **code** | `server`, `client`, `ci`, or unknown | Hoshe (code quality) + Tyre (architecture) |
+| **copy** | `copy` | Hoshe (QA) + Paula (narrative depth) + Miri (world consistency) |
+| **visual** | `visual` | Hoshe (QA) + Araminta (art direction) |
+| **audio** | `audio` | Hoshe (QA) + Ozzie (player experience) |
+
+If the branch name doesn't match any known type, default to **code** reviewers.
+
+### 3. Generate the diff and read source files
+
+```bash
+git log --oneline main..<branch>
+git diff main...<branch> --stat
+```
+
+If the diff is empty, report "No changes to review" and stop.
+
+**Exclude generated/vendor files from the review diff.** Common exclusions:
+- `Cargo.lock` (auto-generated)
+- `client/addons/gdUnit4/` (vendor test framework)
+- `*.uid` (Godot-generated)
+- `docs/backups/settledreach.db.backup` (binary)
+
+Three-dot diff with pathspec exclusions is unreliable. Instead, either:
+1. Use `git diff main...<branch>` (full diff) and filter in the prompt, or
+2. Read source files directly from the team directory (see below).
+
+For large diffs (>1000 lines of source), provide **source files** rather than
+raw diff to reviewers — cleaner context, better reviews.
+
+**IMPORTANT — use team directory paths for ALL agents.** Each team branch
+is checked out in its own directory at:
+
+```
+/var/mnt/data/projects/settled-reach/<branch>/
+```
+
+For example, the `copy` team directory is at:
+```
+/var/mnt/data/projects/settled-reach/copy/content/dialogue/...
+```
+
+**All reviewer agents** (regardless of Bash access) should read source files
+from the team directory using the Read tool. This is more reliable than
+`git show origin/<branch>:<path>` because:
+- All agents have Read access (no Bash dependency)
+- Files are always the actual branch checkout (no stale cache)
+- No risk of accidentally reading from main's working directory
+
+When constructing reviewer prompts, tell agents to read files from the
+team directory. Example instruction for agents:
+
+```
+Read the changed files from the team directory. The branch is checked
+out at: /var/mnt/data/projects/settled-reach/<branch>/
+
+For example, to read `content/dialogue/the-terminal/kael-davan.yaml`,
+use: /var/mnt/data/projects/settled-reach/<branch>/content/dialogue/the-terminal/kael-davan.yaml
+```
+
+Also tell agents to read relevant `decisions/*.md` files from the same
+directory (they're identical to main, but using the team directory path
+keeps agents grounded in the correct location).
+
+### 4. Spawn reviewers in parallel
+
+Use the Task tool to spawn **all reviewers simultaneously** in a single message.
+
+Read `references/reviewer-profiles.md` for the full per-branch-type reviewer
+specifications (agent types, models, prompt focus areas). Match the branch type
+from step 2 to the corresponding section.
+
+All reviewers: request structured verdict: APPROVE or REQUEST_CHANGES with
+file-specific comments.
+
+### 5. Present results
+
+Format the combined review as a table per reviewer. Include one section per
+reviewer that was spawned (2 for code/visual/audio, 3 for copy):
+
+```
+## Review: <branch> -> main  (type: code|copy|visual|audio)
+
+### <Reviewer Name> (<Focus>): [APPROVE | REQUEST_CHANGES]
+[Summary]
+| # | File | Severity | Issue |
+|---|------|----------|-------|
+| 1 | path:line | critical/warning/suggestion | description |
+
+### <Reviewer Name> (<Focus>): [APPROVE | REQUEST_CHANGES]
+...
+
+### Verdict: [APPROVED | CHANGES REQUESTED]
+```
+
+The overall verdict is APPROVED only if **all** reviewers approve.
+
+## Prompt template for reviewers
+
+Use this structure when constructing the agent prompts (adapt as needed):
+
+```
+Review the following {branch_type} branch diff for merge into main.
+
+Branch: {branch}
+Branch type: {branch_type} (code|copy|visual|audio)
+Commits:
+{commit_log}
+
+Diff stats:
+{diff_stat}
+
+[Source files or diff here — exclude vendor/generated code]
+
+Your review focus: {focus_area}
+
+Respond with:
+1. Verdict: APPROVE or REQUEST_CHANGES
+2. Summary: 2-3 sentence overall assessment
+3. Comments: List of specific issues, each with:
+   - File path and approximate location
+   - Severity: critical / warning / suggestion
+   - Description of the issue
+
+Verdict rules:
+- Any **critical** or **warning** issue → REQUEST_CHANGES
+- Only **suggestion**-level issues (or none) → APPROVE
+If no issues found, say APPROVE with a brief positive summary.
+```
+
+## 6. Posting results to Gitea
+
+After presenting results to the user, post the review as a PR comment.
+
+Note: `tea pr reject` does not work on your own PRs. Use `tea comment` instead.
+
+Post using the `tea-comment` wrapper (handles temp files and cleanup):
+
+```bash
+tooling/tea-comment <PR_NUMBER> "review markdown here"
+```
+
+## 7. Merging approved PRs
+
+`tea pr merge` fails (405) when branches have conflicts with main. Merge
+locally instead:
+
+```bash
+git fetch --all
+git merge origin/<branch>        # resolve conflicts if any
+git push origin main
+tea pr close --login schweitz --repo jpmschweitzer/settled-reach <PR_NUMBER>
+```
+
+Gitea does **not** auto-close PRs when you push a local merge — always close
+manually with `tea pr close` after pushing.
+
+### 8. Post-review team actions
+
+If a sprint team is active and you are the team lead, handle the
+review outcome:
+
+**CHANGES_REQUESTED:**
+The sprint-start lifecycle (step 9c) handles dispatching review
+comments to agents. After presenting results, remind the lead:
+"Review requested changes. Create tasks from the warnings/critical
+issues and dispatch to idle agents, then re-push and re-review."
+
+**APPROVED:**
+The sprint-start lifecycle (step 9c) handles shutdown. After
+presenting results, remind the lead: "Review approved. Proceed with
+team shutdown per sprint-start step 9c."
+
+## Tips from practice
+
+- **Vendor code**: Explicitly note vendor code in the prompt so reviewers focus
+  on project code. Mention it as a separate architectural concern (should it be
+  gitignored? submoduled?).
+- **Large PRs**: For PRs touching many files, provide file-by-file source code
+  rather than a single massive diff. Reviewers give better feedback.
+- **Multiple PRs**: When reviewing several PRs, spawn all reviewers in one
+  parallel batch (4 agents for 2 PRs). This is faster than sequential.
+- **Tyre reads decisions**: Always tell Tyre to read the relevant `decisions/*.md`
+  files — this grounds the review in project-specific architectural choices.
+- **Binary/DB files**: Exclude binary files from the diff. Note them in the
+  prompt as "also changed" if relevant.
@@ -0,0 +1,117 @@
+# Reviewer Profiles by Branch Type
+
+Use `model: sonnet` for all reviewers — sufficient for review, saves cost.
+
+**All reviewer agents read from team directories.** Each team branch is
+checked out in its own directory at:
+`/var/mnt/data/projects/settled-reach/<branch>/`
+
+Tell every reviewer agent to read source files from the team directory
+using the Read tool. Include the directory path and a list of changed
+files in every prompt. Do NOT rely on `git show` or paste file contents —
+agents can read directly from the directory.
+
+Note: cross-directory reading is only permitted for review agents spawned
+from the `main` team. Team agents must stay within their own directory.
+
+## Code reviews (`server`, `client`, `ci`)
+
+**Hoshe (Code Quality)**
+- `subagent_type`: `hoshe`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, and commit log.
+  Tell Hoshe to read source files from the team directory, then review for:
+  - Correctness and bug risks
+  - Error handling gaps
+  - Test coverage (are new features tested?)
+  - Code style and clarity
+  - Security concerns (OWASP top 10, injection risks)
+  - Performance issues
+
+**Tyre (Architecture)**
+- `subagent_type`: `tyre`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, and commit log.
+  Tell Tyre to read the relevant `decisions/*.md` files from the team directory
+  first, then review for:
+  - Architectural consistency with project decisions
+  - API/interface design quality
+  - Dependency and coupling concerns
+  - Scalability implications
+  - Whether the change respects non-negotiable baselines (D-010, D-012)
+
+## Copy reviews (`copy`)
+
+**Hoshe (QA)**
+- `subagent_type`: `hoshe`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, and commit log.
+  Tell Hoshe to read the changed files from the team directory, then review for:
+  - Formatting consistency (markdown, file naming, frontmatter)
+  - Broken references or links
+  - Spelling and grammar
+  - File organization and structure
+  - Missing or orphaned files
+
+**Paula (Narrative Depth)**
+- `subagent_type`: `paula`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, commit log, and
+  list of relevant `decisions/*.md` files to read. Tell Paula to read all
+  files from the team directory using the Read tool, then review for:
+  - Narrative quality and character voice consistency
+  - Whether dialogue and monologue feel authentic to the characters
+  - Consequences and stakes — do choices carry weight?
+  - Political and interpersonal depth
+  - Emotional resonance — does the text make you feel something?
+
+**Miri (World Consistency)**
+- `subagent_type`: `miri`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, commit log, and
+  list of relevant `decisions/*.md` files to read. Tell Miri to read all
+  files from the team directory using the Read tool, then review for:
+  - Lore accuracy — do facts match established setting?
+  - Internal consistency across files
+  - IP originality — nothing should read as a copy from another franchise
+  - Faction, technology, and location details match the worldbuilding docs
+  - Setting serves gameplay mechanics (asymmetric information, perception)
+
+## Visual reviews (`visual`)
+
+**Hoshe (QA)**
+- `subagent_type`: `hoshe`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, and commit log.
+  Tell Hoshe to read the changed files from the team directory, then review for:
+  - File format and naming conventions
+  - Asset organization and directory structure
+  - Missing or broken references in scene/resource files
+  - Import settings consistency
+
+**Araminta (Art Direction)**
+- `subagent_type`: `araminta`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, and commit log.
+  Tell Araminta to read the style guide and relevant design docs from the
+  worktree first, then review for:
+  - Visual consistency with the established style guide
+  - Color palette adherence
+  - UI pattern consistency (diegetic-first, clarity over beauty)
+  - Whether assets scale gracefully (boxes-with-labels to full-art)
+  - Mood and tone — sleek, advanced, subtle Settled Reach aesthetic
+
+## Audio reviews (`audio`)
+
+**Hoshe (QA)**
+- `subagent_type`: `hoshe`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, and commit log.
+  Tell Hoshe to read the changed files from the team directory, then review for:
+  - File format and naming conventions
+  - Audio asset organization and directory structure
+  - Missing or broken references
+  - Import/bus configuration consistency
+
+**Ozzie (Player Experience)**
+- `subagent_type`: `ozzie`, `model`: `sonnet`
+- Prompt: Provide the team directory path, list of changed files, and commit log.
+  Tell Ozzie to read all files from the team directory using the Read tool, then
+  review for:
+  - Emotional impact — does the audio enhance the moment?
+  - Atmosphere and tone — does it feel like the Settled Reach?
+  - Player feedback clarity — can the player tell what just happened?
+  - Pacing — do sounds support or fight the gameplay rhythm?
+  - Memorable moments — will players remember these audio cues?
@@ -1,193 +0,0 @@
---
-name: review-pr
-description: >
-  Review a branch diff with dual agents before merge. Use when the user says
-  "review-pr", "review this PR", "review this branch", or invokes /review-pr.
-  Spawns Hoshe (code quality) and Tyre (architecture) in parallel to review
-  the diff against main. Reports approve/reject with inline comments.
-user-invocable: true
-allowed-tools: Bash, Read, Grep, Glob, Task
---
-
-# PR Review Skill
-
-Dual-agent review of a branch diff against main. Hoshe reviews code quality,
-Tyre reviews architecture. Both must approve for a clean review.
-
-## Workflow
-
-### 1. Determine the branch
-
-If the user provided a branch name as argument, use it. Otherwise use the
-current branch (`git branch --show-current`). If on `main`, ask the user
-which branch to review.
-
-To list open PRs on Gitea:
-```bash
-tea pr list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
-```
-
-Fetch remote branches first:
-```bash
-git fetch --all
-```
-
-### 2. Generate the diff
-
-```bash
-git log --oneline main..<branch>
-git diff main...<branch> --stat
-```
-
-If the diff is empty, report "No changes to review" and stop.
-
-**Exclude generated/vendor files from the review diff.** Common exclusions:
- `Cargo.lock` (auto-generated)
- `client/addons/gdUnit4/` (vendor test framework)
- `*.uid` (Godot-generated)
- `db/commonwealth.db` (binary)
-
-Three-dot diff with pathspec exclusions is unreliable. Instead, either:
-1. Use `git diff main...<branch>` (full diff) and filter in the prompt, or
-2. Have Tyre read source files directly from the branch:
-   `git show origin/<branch>:<path>`
-
-For large diffs (>1000 lines of source), provide **source files** rather than
-raw diff to reviewers — cleaner context, better reviews. Read files with
-`git show origin/<branch>:<path>` and include them in the prompt.
-
-### 3. Spawn both reviewers in parallel
-
-Use the Task tool to spawn **two agents simultaneously** in a single message.
-Use `model: sonnet` for both — sufficient for review, saves cost.
-
-**Agent 1 — Hoshe (Code Quality)**
- `subagent_type`: `hoshe`
- `model`: `sonnet`
- Prompt: Include source code and commit log. Ask Hoshe to review for:
-  - Correctness and bug risks
-  - Error handling gaps
-  - Test coverage (are new features tested?)
-  - Code style and clarity
-  - Security concerns (OWASP top 10, injection risks)
-  - Performance issues
- Request structured verdict: APPROVE or REQUEST_CHANGES with file-specific comments
-
-**Agent 2 — Tyre (Architecture)**
- `subagent_type`: `tyre`
- `model`: `sonnet`
- Prompt: Include source code and commit log. Tell Tyre to read the relevant
-  `decisions/*.md` files first, then review for:
-  - Architectural consistency with project decisions
-  - API/interface design quality
-  - Dependency and coupling concerns
-  - Scalability implications
-  - Whether the change respects non-negotiable baselines (D-010, D-012)
- Tyre can read files directly from the branch using `git show origin/<branch>:<path>`
- Request structured verdict: APPROVE or REQUEST_CHANGES with file-specific comments
-
-### 4. Present results
-
-Format the combined review as a table per reviewer:
-
-```
-## Review: <branch> -> main
-
-### Hoshe (Code Quality): [APPROVE | REQUEST_CHANGES]
-[Summary]
-| # | File | Severity | Issue |
-|---|------|----------|-------|
-| 1 | path:line | critical/warning/suggestion | description |
-
-### Tyre (Architecture): [APPROVE | REQUEST_CHANGES]
-[Summary]
-| # | File | Severity | Issue |
-|---|------|----------|-------|
-| 1 | path:line | critical/warning/suggestion | description |
-
-### Verdict: [APPROVED | CHANGES REQUESTED]
-```
-
-The overall verdict is APPROVED only if **both** reviewers approve.
-
-## Prompt template for reviewers
-
-Use this structure when constructing the agent prompts (adapt as needed):
-
-```
-Review the following branch diff for merge into main.
-
-Branch: {branch}
-Commits:
-{commit_log}
-
-Diff stats:
-{diff_stat}
-
-[Source files or diff here — exclude vendor/generated code]
-
-Review focus: {focus_area}
-
-Respond with:
-1. Verdict: APPROVE or REQUEST_CHANGES
-2. Summary: 2-3 sentence overall assessment
-3. Comments: List of specific issues, each with:
-   - File path and approximate location
-   - Severity: critical / warning / suggestion
-   - Description of the issue
-If no issues found, say APPROVE with a brief positive summary.
-```
-
-## Posting results to Gitea
-
-After presenting results to the user, post the review as a PR comment:
-
-```bash
-tea comment --login schweitz --repo jpmschweitzer/settled-reach <PR_NUMBER> "<review markdown>"
-```
-
-Use a heredoc for multi-line review bodies:
-```bash
-tea comment --login schweitz --repo jpmschweitzer/settled-reach <PR_NUMBER> "$(cat <<'REVIEW'
-## Dual-Agent Review: <branch> -> main
-...review content...
-REVIEW
-)"
-```
-
-Note: `tea pr reject` does not work on your own PRs. Use `tea comment` instead.
-
-**Heredoc bodies hang** in `tea comment`. Write review to a temp file instead:
-```bash
-# Write review to temp file, then pass via cat
-tea comment --login schweitz --repo jpmschweitzer/settled-reach <PR_NUMBER> "$(cat /tmp/review.md)"
-```
-
-## Merging approved PRs
-
-`tea pr merge` fails (405) when branches have conflicts with main. Merge
-locally instead:
-
-```bash
-git fetch --all
-git merge origin/<branch>        # resolve conflicts if any
-git push origin main
-tea pr close --login schweitz --repo jpmschweitzer/settled-reach <PR_NUMBER>
-```
-
-Gitea does **not** auto-close PRs when you push a local merge — always close
-manually with `tea pr close` after pushing.
-
-## Tips from practice
-
- **Vendor code**: Explicitly note vendor code in the prompt so reviewers focus
-  on project code. Mention it as a separate architectural concern (should it be
-  gitignored? submoduled?).
- **Large PRs**: For PRs touching many files, provide file-by-file source code
-  rather than a single massive diff. Reviewers give better feedback.
- **Multiple PRs**: When reviewing several PRs, spawn all reviewers in one
-  parallel batch (4 agents for 2 PRs). This is faster than sequential.
- **Tyre reads decisions**: Always tell Tyre to read the relevant `decisions/*.md`
-  files — this grounds the review in project-specific architectural choices.
- **Binary/DB files**: Exclude binary files from the diff. Note them in the
-  prompt as "also changed" if relevant.
@@ -1,98 +0,0 @@
---
-name: search-docs
-description: >
-  Search project documents using semantic search (Qdrant + ollama) or grep fallback.
-  Use when the user asks "did we discuss X?", "find references to Y", "search docs",
-  or invokes /search-docs. Wraps the qdrant_connector.py for semantic document search.
-user-invocable: true
-allowed-tools: Bash, Read, Grep, Glob
---
-
-# Search Docs Skill
-
-Semantic search across Commonwealth project documents using Qdrant vector database and ollama embeddings.
-
-## Access Method
-
-**Use the connector script:**
-```bash
-python3 db/connectors/qdrant_connector.py <command> [args]
-```
-
-## Commands
-
-### Search
-Find documents semantically related to a query:
-```bash
-python3 db/connectors/qdrant_connector.py search "asymmetric information design"
-python3 db/connectors/qdrant_connector.py search "what did we decide about fog of war"
-python3 db/connectors/qdrant_connector.py search "engine requirements"
-```
-
-Returns top 5 matching document chunks with source file, heading, and relevance score.
-
-### Index a file
-Add or update a document in the search index:
-```bash
-python3 db/connectors/qdrant_connector.py index-file decisions/architecture.md
-python3 db/connectors/qdrant_connector.py index-file decisions/perception.md
-python3 db/connectors/qdrant_connector.py index-file docs/discussions/round-10-map-fog-borderless.md
-python3 db/connectors/qdrant_connector.py index-file docs/briefings/tyre.md
-```
-
-Files are chunked by markdown headings (# and ##). Each chunk is embedded via ollama and stored in Qdrant with metadata (source_file, heading, chunk_index).
-
-### Index a single chunk
-For precise indexing of specific content:
-```bash
-python3 db/connectors/qdrant_connector.py index "unique-id" "Text content to index" --metadata source=manual heading="Custom heading"
-```
-
-### Health check
-Verify connectivity to Qdrant and ollama:
-```bash
-python3 db/connectors/qdrant_connector.py health
-```
-
-### Collection info
-Check how many documents are indexed:
-```bash
-python3 db/connectors/qdrant_connector.py count
-```
-
-### Create collection
-Initialize the Qdrant collection (run once during setup):
-```bash
-python3 db/connectors/qdrant_connector.py create-collection
-```
-
-## Endpoints
-
-Configured in `db/connectors/config.json`:
- **Qdrant:** `http://tower-of-joy:6333`
- **Ollama:** `http://tower-of-joy:11434` (model: nomic-embed-text)
- **Collection:** `commonwealth` (768 dimensions, cosine distance)
-
-## Fallback
-
-If Qdrant or ollama is unreachable, fall back to grep-based search:
-```bash
-# Search across all project docs
-grep -r -i "search term" decisions/ DISCUSSION.md docs/ --include="*.md"
-```
-
-## Workflow
-
-1. **Qatux (Librarian)** is the primary user of this skill
-2. After each discussion round, index the archived round file
-3. After briefing updates, re-index affected briefings
-4. After decision changes, re-index the relevant decisions/*.md domain files
-5. Use search to answer "did we discuss this?" questions with citations
-
-## Bulk indexing
-To index all project documents at once:
-```bash
-for f in decisions/*.md DISCUSSION.md TEAM.md docs/discussions/*.md docs/briefings/*.md; do
-  python3 db/connectors/qdrant_connector.py index-file "$f"
-done
-```
@@ -1,5 +1,5 @@
 ---
-name: create-skill
+name: skill-create
 description: >
  Guidance for creating effective Claude Code skills (.skill packages).
  Use when the user wants to create, build, design, or iterate on a skill —
@@ -149,14 +149,14 @@ Establish a list of reusable resources: scripts, references, and assets.

 ### Step 3: Initialize the Skill

-Run the init script to generate a template skill directory:
+Create the skill directory manually:

 ```
-scripts/init_skill.py <skill-name> --path <output-directory>
+mkdir -p <output-directory>/<skill-name>
 ```

-Creates: skill directory, SKILL.md template with TODO placeholders, example
-resource directories with sample files.
+Then create `SKILL.md` with frontmatter and body. Add `scripts/`, `references/`,
+and `assets/` subdirectories only as needed.

 Skip if iterating on an existing skill.

@@ -178,26 +178,24 @@ For design patterns, consult:
 **Writing guidelines:** Always use imperative/infinitive form.

 **Frontmatter:**
- `name`: The skill name
+- `name`: The skill name — use **domain-action** naming: `{domain}-{action}`.
+  The domain is the system/area the skill operates on, the action is what it does.
+  Examples: `pr-review`, `sprint-plan`, `docs-search`, `git-commit`, `debt-scan`.
+  Multi-action wrappers (like `ticket`) can use the domain name alone.
+  The directory name must match the `name` field.
 - `description`: Primary triggering mechanism. Include what the skill does AND
  specific triggers/contexts. All "when to use" info goes here (not in body).

 **Body:** Instructions for using the skill and its bundled resources.

-### Step 5: Package the Skill
+### Step 5: Validate the Skill

-```
-scripts/package_skill.py <path/to/skill-folder>
-```
-
-Optional output directory:
-```
-scripts/package_skill.py <path/to/skill-folder> ./dist
-```
-
-The script validates (frontmatter, naming, description, file organization) then
-packages into a `.skill` file (zip with .skill extension). Fix any validation
-errors and re-run if needed.
+Check the skill manually:
+- Frontmatter has `name` and `description`
+- SKILL.md body is under 500 lines
+- No extraneous files (README.md, CHANGELOG.md, etc.)
+- Scripts are executable and tested
+- References are referenced from SKILL.md

 ### Step 6: Iterate

@@ -0,0 +1,216 @@
+---
+name: sprint-plan
+description: >
+  Plan the next sprint and generate team briefing files. Use when the user says
+  "plan sprint", "prep sprint briefing", "plan next sprint", "sprint planning",
+  or invokes /sprint-plan. Gathers current sprint status, scans the backlog,
+  proposes ticket selection, and writes briefing files per team to
+  docs/sprints/sprint-N/.
+user-invocable: true
+allowed-tools: Task, Read, Grep, Glob
+---
+
+# Plan Sprint
+
+**Delegate this entire skill to SI** (Project Manager agent, `subagent_type: si`).
+
+When this skill is invoked, spawn SI using the Task tool:
+
+```
+Task(
+  subagent_type: "si",
+  prompt: "Run /sprint-plan for Sprint N. Read the skill at
+    .claude/skills/sprint-plan/SKILL.md for the full workflow,
+    then execute it. Use the arguments provided: {args}",
+  description: "Plan sprint N"
+)
+```
+
+Pass through any arguments the user provided (e.g. sprint number).
+Present SI's output to the user when done. Do NOT run the workflow yourself.
+
+---
+
+The remainder of this file is SI's reference for executing the workflow.
+
+Generate sprint briefing files for each active team (e.g. `server.md`,
+`client.md`, `copy.md`, `joint.md`) for the next sprint based on current
+project state. Only generate briefings for teams that have tickets in the sprint.
+
+## Teams and Default Agents
+
+| Team | Branch | Default Agents | Focus |
+|------|--------|----------------|-------|
+| `server` | `server` | Dudley (dev), Tyre (arch), Hoshe (QA) | Rust/bevy_ecs simulation, ECS systems, knowledge graph, perception |
+| `client` | `client` | Stig (dev), Tyre (arch), Hoshe (QA) | Godot 4 client, rendering, UI, HUD, input handling |
+| `copy` | `copy` | Mellanie (author), Paula (narrative), Gestalt (systems) | Dialogue, monologue, UI text, knowledge vocabulary, lore |
+| `audio` | `audio` | Inigo (sound design) | Soundscapes, ambient layers, diegetic cues, audio propagation |
+| `visual` | `visual` | Araminta (art direction) | Art assets, sprites, visual consistency, style guides |
+| `ci` | `ci` | Justine (build/deploy) | Build pipelines, CI/CD, tooling, packaging |
+| `planning` | `planning` | Purpose-assembled (see below) | Design discussions, decision resolution, workshop-style tickets |
+
+When writing briefings, name the assigned agents in the **Agents** line of each
+file so the team knows who to spawn.
+
+### Planning Team Tickets
+
+Some tickets need **design discussion** before implementation can begin — tagged
+"NEEDS DESIGN DISCUSSION" or blocking multiple downstream tickets with open
+questions. These run on the `planning` branch as structured discussions with
+the user and a purpose-assembled agent panel.
+
+**When to create a planning ticket:**
+- Ticket description says "NEEDS DESIGN" or "NEEDS DESIGN DISCUSSION"
+- Ticket blocks 2+ downstream tickets across different teams
+- Open Q-NNN items that block sprint candidates
+- Architectural decisions that need multi-domain input before implementation
+
+**Planning briefing format** (differs from implementation briefings):
+- **Agents line**: List agents by domain relevance, not fixed team roster.
+  Pick from: Gestalt (systems), Miri (worldbuilding), Araminta (visual/spatial),
+  Tyre (technical), Paula (narrative), Ozzie (player experience), Gore (themes),
+  Nigel (replayability). Typically 4-6 domain agents, plus Qatux (documenter —
+  records decisions, updates domain files) and SI (project manager — creates
+  follow-up tickets, updates sprint assignments).
+- **Discussion rounds**: Structure the conversation into 2-3 rounds
+  (inventory → proposals → convergence)
+- **Context section**: List all existing design docs, decisions, and related
+  tickets that participants must read before the discussion
+- **Output specification**: What the discussion must produce — typically a
+  D-record in `decisions/`, possibly a design doc in `docs/design/`
+- **Decision questions**: Specific questions the discussion must answer,
+  not open-ended exploration
+
+## Workflow
+
+### 1. Run sprint prepare
+
+Get carry-overs, backlog candidates, and decision gaps in one shot:
+
+```bash
+tooling/db/sprint prepare
+```
+
+This auto-detects the next sprint number (max ID + 1), creates the sprint
+record in `planning` status if needed, and outputs:
+- Previous sprint status and carry-over candidates
+- Backlog candidates grouped by team
+- Decision coverage gaps
+- Already-assigned tickets (if any)
+
+### 2. Deepen the scan
+
+For critical epics, check their children for granular candidates:
+
+```bash
+tooling/db/ticket children <epic_id>
+```
+
+Use `tooling/db/ticket show --brief <id> [<id>...]` to quickly scan multiple tickets.
+
+### 3. Read existing code state
+
+Scan what's already built to write accurate "what exists" notes:
+
+```bash
+# Server modules
+ls server/src/ server/src/*/
+
+# Client scripts
+ls client/scripts/ client/scripts/*/
+```
+
+Read key files that sprint tickets will build on (bridge types, existing
+renderers, etc.) to reference specific integration points in the briefing.
+
+### 4. Select tickets — propose to user
+
+Based on the backlog scan, propose a sprint with:
+
+- **Sprint theme** — a short name (Sprint 1 was "Run", Sprint 2 was "See")
+- **Sprint goal** — one sentence shared across all teams
+- **Server tickets** — stories from server-side epics
+- **Client tickets** — stories from client-side epics
+- **Joint tasks** — integration proofs, pre-sprint decisions, schema work
+
+Present the proposal using AskUserQuestion for the user to approve or adjust.
+
+Selection heuristics:
+- Follow dependency chains (don't pick a ticket if its blocker isn't in scope)
+- Respect D-030 test priority phases (sprint 1-2: infra, sprint 3-4: integration)
+- Mix carry-overs with new work
+- Aim for 3-6 tickets per team, with parallel tracks where possible
+- Check `decisions/questions.md` for open Q-NNN items that block candidates
+
+### 5. Read relevant decisions
+
+For the selected tickets, identify which `decisions/*.md` files are relevant.
+Read them to provide accurate cross-references in the briefing.
+
+### 6. Write briefing files
+
+Create `docs/sprints/sprint-N/` and write one file per team.
+
+Read the template at `references/briefing-template.md` in this skill directory
+for the exact file structure.
+
+**IMPORTANT — relative paths only:** Each team works in its own directory
+containing the full repo (`server/`, `client/`, `docs/`, etc.). All file
+paths in briefings must be relative to the working directory. Example:
+`server/src/bridge/types.rs`, not `/absolute/path/to/server/src/...` or
+paths that navigate outside (`../sibling-dir/...`).
+Agents must stay within their team's working directory.
+
+Key requirements per file:
+- **server.md**: Carry-overs, new tickets, dependency chain, key decisions, notes
+  referencing existing Rust modules by path from worktree root (e.g. `server/src/simulation/movement.rs`)
+- **client.md**: Same structure, notes referencing existing GDScript files by path from worktree root (e.g. `client/scripts/rendering/fog.gd`)
+- **copy.md**: In-game text tasks — dialogue, UI copy, tooltips, flavor text, lore
+- **audio.md**: Sound design, music, audio integration tasks
+- **visual.md**: Art direction, asset creation, visual consistency tasks
+- **ci.md**: Build pipeline, CI/CD, tooling, infrastructure tasks
+- **joint.md**: Pre-sprint decisions table, integration tickets, sprint
+  completion proof (concrete observable criteria), test plan alignment
+
+Only generate briefing files for teams that have tickets assigned in the sprint.
+Not every sprint will have work for every team.
+
+### 7. Assign tickets to sprint in DB
+
+After the user approves, assign all selected tickets. The sprint record
+was already created by `sprint prepare` in step 1 (status: `planning`).
+Update it with the theme and goal, then assign tickets:
+
+```bash
+# Update the sprint with theme and goal
+tooling/db/sqlite-exec "UPDATE sprints SET name='Sprint N: Theme', goal='goal' WHERE id=N"
+
+# Assign tickets
+tooling/db/ticket sprint assign <ticket_id> <sprint_id>
+```
+
+The sprint stays in `planning` status until explicitly activated via
+`tooling/db/sprint start`. This prevents starting an unplanned sprint.
+
+### 8. Commit and push
+
+Stage the briefing files and any other changes (db backup, closed tickets),
+then commit and push so worktree branches can pull the planning artifacts:
+
+```bash
+git add docs/sprints/sprint-N/
+make db-backup
+git add docs/backups/settledreach.db.backup
+git commit -m "chore(meta): plan Sprint N: Theme"
+git push
+```
+
+### 9. Present summary
+
+Output:
+- Sprint number, theme, and goal
+- Ticket count per team
+- Carry-over count
+- Open questions that need early resolution
+- Files written
+- Commit pushed to main
@@ -0,0 +1,79 @@
+# Sprint Briefing Template
+
+Each team gets one briefing file at `docs/sprints/sprint-N/<team>.md`.
+
+## File structure
+
+```markdown
+# Sprint N: <Theme> — <Team> Tasks
+
+**Goal:** <One-sentence sprint goal, shared across all teams>
+
+**Branch:** `<team>`
+**Agents:** <Agent names and roles>
+
+## Carry-over from Sprint N-1
+
+(Only if there are incomplete tickets from the previous sprint)
+
+| # | Title | Status | Notes |
+|---|-------|--------|-------|
+| #ID | Title | status | Why it carried over |
+
+## New Tickets
+
+| # | Title | Blocked by |
+|---|-------|------------|
+| #ID | Title | #dependency or — |
+
+Use `tooling/db/ticket show <id>` for full details.
+
+## Key Decisions
+
+- `decisions/<domain>.md` — D-NNN (short name), D-NNN (short name)
+
+## Open Questions to Resolve Early
+
+(Only if there are Q-NNN items that block sprint tickets)
+
+- **Q-NNN: Title** — Brief context. Resolve before #ID starts.
+
+## Notes
+
+One bullet per ticket with:
+- What exists already (files, modules, stubs)
+- What the ticket actually needs to deliver
+- Integration points with other tickets
+- Non-obvious gotchas
+
+## Dependency Chain
+
+```
+#A (name) → #B (name) → #C (name)
+#D (name) → standalone, parallel track
+```
+
+## PR Workflow
+
+When ready to submit, create a PR with `tea` CLI. **All flags are required** to avoid TTY prompts (see CLAUDE.md "Gitea access" section):
+\```bash
+tea pr create --repo jpmschweitzer/settled-reach --login schweitz --title "feat(<scope>): description" --description "body" --base main --head <branch>
+\```
+```
+
+## Joint briefing extras
+
+The `joint.md` file additionally includes:
+
+- **Pre-Sprint** table: decisions/schema work that must happen before implementation
+- **Sprint Completion Proof**: concrete observable criteria (what you can see/do when the sprint is done)
+- **Test plan** alignment with D-030 phases
+
+## Team assignments
+
+| Team | Branch | Agents | Scope |
+|------|--------|--------|-------|
+| server | `server` | Dudley (simulation), Oscar (networking) | Rust/bevy_ecs simulation |
+| client | `client` | Stig (UI), Oscar (networking) | Godot client rendering |
+| joint | both | All implementation agents | Integration, proofs, cross-team schema |
+| content | (none) | Mellanie, Paula, Miri, Araminta | Content authoring, no code branch |
@@ -0,0 +1,425 @@
+---
+name: sprint-start
+description: >
+  Manage the sprint lifecycle from main, or start sprint work on a team
+  branch. Use when the user says "start sprint", "start working on the
+  server/client/copy", "begin sprint", or invokes /sprint-start. On main:
+  assesses sprint state and does the next right thing (close, activate, or
+  guide). On a team branch: merges main, loads the briefing, presents the
+  work plan.
+user-invocable: true
+allowed-tools: Bash, Read, Grep, Glob, TeamCreate, Task, TaskCreate, TaskUpdate, TaskList, SendMessage, AskUserQuestion
+---
+
+# Start Sprint Skill
+
+Prepare a team branch for sprint work: sync with main, load the sprint
+briefing, and present actionable next steps.
+
+## Workflow
+
+### 1. Determine the team
+
+The current branch IS the team. Read it with:
+```bash
+git branch --show-current
+```
+
+Valid team branches: `server`, `client`, `copy`, `audio`, `visual`, `ci`.
+
+If on `main`, follow the **Main branch workflow** below instead of
+the team branch workflow (steps 2–8).
+
+---
+
+## Main branch workflow (sprint lifecycle management)
+
+When `/sprint-start` is run on `main`, assess the current sprint state
+and do the next right thing. Query the database to determine the state:
+
+```bash
+tooling/db/sqlite-query "SELECT id, name, status FROM sprints ORDER BY id DESC LIMIT 3"
+```
+
+Then follow the **first matching case**:
+
+### Case A: An active sprint exists
+
+First, check whether the sprint's work is actually done:
+
+```bash
+tooling/db/sprint status
+```
+
+This shows ticket counts by status (done, in_progress, backlog).
+
+Also check for open PRs that may contain completed work waiting for
+review or merge:
+
+```bash
+tea pr list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
+```
+
+Report the full picture to the user:
+- Ticket progress (done / in_progress / backlog counts)
+- Open PRs (if any — these represent work that's done but not merged)
+
+**If tickets remain unfinished** (in_progress or backlog) **or open PRs
+exist**, do NOT close the sprint. Instead, report the current progress
+and ask the user what they want to do:
+
+- **Continue working** — switch to a team branch and run `/sprint-start`
+  there to resume work
+- **Review & merge PRs first** — (only if open PRs exist) merge pending
+  work before deciding whether to close
+- **Close anyway** — proceed with the close workflow below (carries over
+  unfinished tickets)
+
+Use `AskUserQuestion` to confirm. Do not proceed to A1 unless the user
+explicitly chooses to close.
+
+#### A1. Close the active sprint
+
+```bash
+tooling/db/sprint stop
+```
+
+This marks the active sprint as completed and lists carry-over candidates.
+Note the sprint number (N) from the output.
+
+#### A2. Bump the version
+
+The project version scheme is `v0.1.{sprint_number}`. After closing
+sprint N, the version is `v0.1.N`.
+
+Update `project.yaml`:
+- Set the `version` field to `0.1.N` (this is the source of truth).
+
+Update `server/Cargo.toml`:
+- Set `version = "0.1.N"` in `[package]`.
+
+Update `CHANGELOG.md`:
+- Move all entries under `## [Unreleased]` into a new section
+  `## [v0.1.N] — YYYY-MM-DD` (using today's date).
+- Leave `## [Unreleased]` as an empty section above the new version.
+- Keep the existing sub-headings (Added, Fixed, Changed, Removed) —
+  only move entries that have content.
+
+#### A3. Commit the release
+
+Stage and commit `project.yaml`, `server/Cargo.toml`, and `CHANGELOG.md`:
+```
+chore(meta): release v0.1.N
+```
+
+#### A4. Tag the release
+
+```bash
+git tag v0.1.N
+```
+
+#### A5. Push
+
+```bash
+git push && git push --tags
+```
+
+#### A6. Check for a planned sprint
+
+After closing, re-query the database. If a sprint in `planning` status
+exists, continue to **Case B**. Otherwise, report the close and suggest
+running `/sprint-plan`.
+
+---
+
+### Case B: No active sprint, but a planned sprint exists
+
+A sprint is ready to activate. Verify it looks complete:
+
+1. Check that briefing files exist at `docs/sprints/sprint-N/`:
+   ```bash
+   ls docs/sprints/sprint-N/
+   ```
+2. Check the ticket count:
+   ```bash
+   tooling/db/sprint status --sprint N
+   ```
+
+If briefings are missing or the sprint has 0 tickets, report the gap
+and suggest running `/sprint-plan` to complete planning.
+
+If everything looks ready, activate the sprint:
+
+```bash
+tooling/db/sprint start
+```
+
+Then report:
+- Sprint activated (name, ticket count per team)
+- Remind the user to switch to a team branch and run `/sprint-start`
+  there (or `cd` into the relevant worktree)
+
+---
+
+### Case C: No active sprint and no planned sprint
+
+Nothing is ready. Report the state and suggest running `/sprint-plan`
+to plan the next sprint.
+
+---
+
+## Team branch workflow
+
+### 2. Sync with main
+
+```bash
+git fetch --all
+git merge origin/main --no-edit
+```
+
+If the merge has conflicts, report them and stop — do not force-resolve.
+
+### 3. Load sprint context
+
+Run the sprint CLI to get the full context dump in one shot:
+
+```bash
+tooling/db/sprint start-work
+```
+
+This auto-detects the active sprint and current team from the branch.
+It outputs: sprint metadata, briefing paths, decision refs, actionable
+tickets, blocked tickets, and done tickets.
+
+If no active sprint is found, report that and stop.
+
+### 4. Read the sprint briefing
+
+Read the briefing file(s) listed in the `start-work` output
+(e.g. `docs/sprints/sprint-6/server.md` and `joint.md`).
+If no matching briefing exists for the team, suggest running
+`/sprint-plan` to generate one.
+
+### 5. Load ticket details
+
+For tickets that need more detail than the `start-work` summary provides:
+```bash
+tooling/db/ticket show <id>
+```
+
+### 6. Read key decisions
+
+Read the decision files referenced in the sprint briefing so the agent has
+full architectural context before starting work.
+
+### 7. Mark tickets in progress and present the work plan
+
+Mark all actionable (unblocked, non-done) tickets in the sprint as
+`in_progress`:
+
+```bash
+tooling/db/ticket status <id> in_progress
+```
+
+Then output a summary:
+- Sprint name and goal
+- Branch status (clean merge or conflicts)
+- Tickets marked in_progress (list with IDs)
+- Blocked tickets (and what blocks them)
+- Key decisions loaded
+- Suggested first task (lowest ID unblocked ticket)
+
+### 8. Confirm and spawn the team
+
+Before spawning agents, use `AskUserQuestion` to confirm the work plan and
+agent lineup with the user. If declined, stop.
+
+Once confirmed:
+
+#### 8a. Parse agents from the briefing
+
+Extract agent names from the `**Agents:**` line. Format:
+```
+**Agents:** Name (role), Name (role), ...
+```
+
+Map each name to its `subagent_type` (lowercase):
+- "Dudley (simulation)" → `dudley`
+- "Stig (UI)" → `stig`
+- "Tyre (architecture)" → `tyre`
+- "Hoshe (QA)" → `hoshe`
+- "Mellanie (author)" → `mellanie`
+- etc. (see `.claude/agents/` for full roster)
+
+#### 8b. Create the team
+
+```
+TeamCreate(team_name: "sprint-{N}-{team}")
+```
+
+This makes you the team lead.
+
+#### 8c. Create tasks from tickets
+
+For each ticket in the briefing, create a task:
+
+```
+TaskCreate(
+  subject: "#{id}: {title}",
+  description: "Full ticket details from step 5, plus briefing notes
+    and integration points for this ticket.",
+  activeForm: "Working on #{id}: {short_title}"
+)
+```
+
+After creating all tasks, mirror the dependency chain from the briefing
+using `TaskUpdate` with `addBlockedBy`.
+
+#### 8d. Spawn agents
+
+For each agent from the `**Agents:**` line, spawn a teammate in the
+background. Spawn all agents in parallel (one message, multiple Task calls):
+
+```
+Task(
+  subagent_type: "{name_lowercase}",
+  team_name: "sprint-{N}-{team}",
+  name: "{name_lowercase}",
+  prompt: "You are on the {team} team for Sprint {N}.
+    Branch: `{team}`
+
+    RULES (NON-NEGOTIABLE):
+
+    0. TEAM BOUNDARY: Your team is `{team}` ($WORKTREE_TEAM). Stay
+       within the current working directory. Do NOT navigate to
+       parent or sibling directories. Do NOT follow .git pointers
+       to other directories.
+
+    1. GIT: Do NOT run any git commands (commit, push, pull, merge,
+       checkout, branch, stash, tag, etc.). All git operations are
+       handled by the team lead. No exceptions.
+
+    2. DB SCRIPTS: When calling ticket/sprint/sqlite scripts, use
+       the exact command with no wrappers or chaining. Examples:
+         tooling/db/ticket show 528
+         tooling/db/ticket list --sprint {N}
+       Do NOT prepend python3, do NOT chain with && or ;, do NOT
+       add cleanup commands. Just the bare command.
+
+    3. READ BEFORE WRITE: Before modifying ANY file, Read it first.
+       Before creating a new file, Glob for similar files to learn
+       the existing patterns (naming, structure, imports). Follow
+       the conventions you find — do not invent new ones.
+
+    4. VERIFY AFTER WRITE: After implementing a change, grep for
+       all references to functions/properties/classes you modified
+       or removed. If you renamed, moved, or deleted something,
+       update EVERY call site. Missing a call site breaks tests
+       and blocks the team.
+
+    5. NO PARTIAL WORK: Do not mark a task completed unless ALL
+       parts of the ticket are implemented. If the ticket says
+       'deliver A, B, and C', all three must exist and work. If
+       you cannot complete part of a task, message the team lead
+       explaining what is blocked and what remains — do NOT mark
+       it completed.
+
+    6. MESSAGE WHEN BLOCKED: If you hit a problem you cannot solve
+       in 3 attempts, stop and message the team lead immediately.
+       Do not silently skip work or leave stubs. Do not move to
+       the next task while the current one is incomplete.
+
+    7. BACKWARD COMPATIBILITY: When extracting, moving, or
+       refactoring code, ensure all existing consumers still work.
+       Add proxy methods/properties if needed. Grep for the old
+       name to find every call site.
+
+    WORKFLOW:
+
+    1. Read the sprint briefing: docs/sprints/sprint-{N}/{team}.md
+    2. Read the decision files referenced in the briefing.
+    3. Check TaskList for available work.
+    4. Claim an unblocked task (TaskUpdate with owner: your name),
+       mark it in_progress, and implement it.
+    5. Before marking done, verify:
+       - All deliverables from the ticket exist (not just some)
+       - No broken references (grep for changed names/signatures)
+       - New files follow existing naming and directory conventions
+       - Modified files still parse (no syntax errors)
+    6. Mark the task completed and check TaskList for the next
+       available task.
+    7. If no tasks remain, message the team lead. Do NOT shut down
+       on your own.
+
+    Use `tooling/db/ticket show <id>` for full ticket specs.",
+  description: "Sprint {N} {team}: {name}",
+  run_in_background: true
+)
+```
+
+#### 8e. Report
+
+Output to the user:
+- Team name: `sprint-{N}-{team}`
+- Agents spawned (names and roles)
+- Tasks created (count actionable vs blocked)
+- How to interact: `SendMessage` to talk to agents, `TaskList` to
+  check progress
+
+You are now the team lead. Agents work autonomously — monitor via
+`TaskList`, communicate via `SendMessage`, and handle blockers as
+they arise.
+
+**When all tasks complete:** Do NOT shut down agents. The team stays
+alive through the PR review cycle. Follow step 9 (post-work lifecycle).
+
+### 9. Post-work lifecycle
+
+When all tasks are complete (TaskList shows all completed):
+
+#### 9a. Commit and push
+
+Run `/git-commit` to commit all changes, then `/pr-push` to create or
+update the PR. Do NOT shut down agents — the team stays alive for review.
+
+#### 9b. Review
+
+Run `/pr-review` to spawn temporary reviewers. Wait for results.
+
+#### 9c. Handle review outcome
+
+**If CHANGES_REQUESTED:**
+
+1. Parse the review comment table (from the Gitea PR comment or the
+   review output). Extract each warning/critical issue with:
+   - File path and approximate line
+   - Severity (critical / warning / suggestion)
+   - Description
+
+2. Create a task per warning/critical issue:
+   ```
+   TaskCreate(
+     subject: "Review: {short description}",
+     description: "{full issue description from review table, including
+       file path, severity, and reviewer name}",
+     activeForm: "Fixing review comment: {short description}"
+   )
+   ```
+   Skip suggestion-severity items unless they are trivial (1-line fixes).
+
+3. Dispatch to idle agents: send each a message via SendMessage telling
+   them to check TaskList for new review-fix tasks. Agents claim and
+   work tasks as usual.
+
+4. After all review-fix tasks are complete, re-run `/git-commit` then
+   `/pr-push` to update the PR. Then re-run `/pr-review`.
+
+5. Repeat this loop until review returns APPROVED.
+
+**If APPROVED:**
+
+1. Send `shutdown_request` to all sprint agents.
+2. Wait for all `shutdown_response` confirmations.
+3. Call `TeamDelete` to clean up.
+4. Report: "Sprint {N} {team} complete. PR #{X} approved and ready for
+   merge on main."
@@ -0,0 +1,94 @@
+---
+name: sprint-status
+description: >
+  Sprint health check and cleanup sweep. Lists all tickets in the active
+  sprint grouped by status, detects bookkeeping issues (stale tickets,
+  orphan PRs, done-but-open PRs, unassigned work), and shows open work
+  by team. Use when checking sprint progress, before sprint close, or
+  when housekeeping feels off. Triggers on "sprint status", "cleanup
+  sweep", "what's open", "sprint health".
+user-invocable: true
+allowed-tools: Task, Read, Grep, Glob
+---
+
+# Sprint Status
+
+**Delegate this entire skill to a subagent** (general-purpose, model: haiku).
+
+When this skill is invoked, spawn a subagent using the Task tool:
+
+```
+Task(
+  subagent_type: "general-purpose",
+  model: "haiku",
+  prompt: "Run /sprint-status. Read the skill at
+    .claude/skills/sprint-status/SKILL.md for the full workflow
+    (below the --- separator), then execute it.",
+  description: "Sprint status report"
+)
+```
+
+Present the subagent's output to the user verbatim. Do NOT run the
+workflow yourself.
+
+---
+
+The remainder of this file is the subagent's reference for executing
+the workflow.
+
+## Step 1 — Gather data
+
+Run these two commands in parallel:
+
+```bash
+tooling/db/sprint sweep
+```
+
+```bash
+tea pr list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
+```
+
+The `sweep` command returns JSON with:
+- `sprint` — id, name, goal
+- `progress` — total, done, pct
+- `by_status` — tickets grouped into done, review, in_progress, blocked, backlog
+- `by_team` — per-team counts
+- `issues` — bookkeeping problems with suggested fix commands
+
+The `tea pr list` returns open PRs as `#N title` lines.
+
+## Step 2 — Cross-reference PRs with tickets
+
+Parse PR head branches from the `tea pr list` output. Known team branches:
+`server`, `client`, `copy`, `audio`, `visual`, `ci`.
+
+Detect additional issues:
+
+- **done_team_open_pr**: A team's tickets are all done but an open PR
+  still exists for that team branch.
+- **orphan_pr**: An open PR exists on a branch that has no tickets in
+  the active sprint.
+
+Add these to the issues list from step 1.
+
+## Step 3 — Format output
+
+Read `references/output-template.md` for the exact format spec.
+
+Render the report using data from steps 1-2. Key rules:
+- Sections ordered: Completed, In Review, In Progress, Blocked, Backlog
+- Sort tickets within sections by team then ticket ID
+- Empty sections: show header with "(0)" and "(none)" — no empty table
+- Bookkeeping Issues: two-column table (Issue, Fix)
+- Open Work by Team: summary table at the bottom
+- Issue type labels: `stale_backlog` → "Stale backlog",
+  `unassigned_in_progress` → "Unassigned in_progress",
+  `assigned_but_done` → "Assigned but done",
+  `done_team_open_pr` → "Done team with open PR",
+  `orphan_pr` → "Orphan PR"
+
+## Step 4 — Suggest actions
+
+After the formatted report, if there are bookkeeping issues, add a
+"Suggested fixes" section with the fix command for each issue. Group
+by issue type for readability.
@@ -0,0 +1,54 @@
+# Sprint Status Output Template
+
+## Sprint {N}: {Theme} — Status Report
+
+**Goal:** {goal}
+**Status:** {status} | {done}/{total} tickets ({pct}%)
+**Open PRs:** {count} ({branches})
+
+---
+
+### Completed ({count})
+
+| # | Team | Title | Assigned |
+|---|------|-------|----------|
+| #{id} | {team} | {title} | {assigned} |
+
+### In Review ({count})
+
+| # | Team | Title | PR |
+|---|------|-------|----|
+| #{id} | {team} | {title} | #{pr} |
+
+### In Progress ({count})
+
+| # | Team | Title | Assigned | Note |
+|---|------|-------|----------|------|
+| #{id} | {team} | {title} | {assigned} | |
+
+### Blocked ({count})
+
+| # | Team | Title | Blocked by |
+|---|------|-------|------------|
+| #{id} | {team} | {title} | #{ids} |
+
+### Backlog ({count})
+
+| # | Team | Title | Note |
+|---|------|-------|----|
+| #{id} | {team} | {title} | not started |
+
+---
+
+### Bookkeeping Issues
+
+| Issue | Fix |
+|-------|-----|
+| {type}: {detail} | `{command}` |
+
+### Open Work by Team
+
+| Team | Backlog | In Progress | Review | Blocked | Done |
+|------|---------|-------------|--------|---------|------|
+| {team} | {n} | {n} | {n} | {n} | {n} |
+| **Total** | **{n}** | **{n}** | **{n}** | **{n}** | **{n}** |
@@ -0,0 +1,55 @@
+---
+name: sprite-gen
+description: >
+  Render a 3D model to 2D sprites via the Godot render pipeline. Produces
+  sprites at 3 resolutions (1024, 256, 64) from 4 cardinal directions (north,
+  east, south, west) with outline applied at working resolution. Use when the
+  user says "render sprite", "render model", "run the render pipeline",
+  "test the pipeline", "/sprite-gen", or asks to render a specific model
+  (e.g., "render wall_structural"). Output: 12 PNG files in renderer/output/.
+---
+
+## Render Pipeline
+
+Run the render script with the model name:
+
+```bash
+.claude/skills/sprite-gen/scripts/render.sh <model_name>
+```
+
+### Available Models
+
+Models live at `renderer/models/<name>.tscn`. List them:
+
+```bash
+ls renderer/models/*.tscn | xargs -I{} basename {} .tscn
+```
+
+### Output
+
+12 files per model in `renderer/output/`:
+
+```
+<model>_north_1024.png   <model>_north_256.png   <model>_north_64.png
+<model>_east_1024.png    <model>_east_256.png    <model>_east_64.png
+<model>_south_1024.png   <model>_south_256.png   <model>_south_64.png
+<model>_west_1024.png    <model>_west_256.png    <model>_west_64.png
+```
+
+### After Rendering
+
+1. Read the 64x64 output files to visually inspect the runtime sprites
+2. Read the 256x256 files to check outline quality
+3. Report: does it read as the intended object at runtime scale?
+
+### Troubleshooting
+
+- **No output files**: Godot needs a display. If running headless, prefix with `xvfb-run`.
+- **Model not found**: Check the model .tscn exists in `renderer/models/`.
+- **Godot not found**: Pass path as second arg: `render.sh wall_structural /path/to/godot`
+
+### Adding New Models
+
+1. Create model scene at `renderer/models/<name>.tscn`
+2. Apply texture from `renderer/textures/` via StandardMaterial3D
+3. Run: `.claude/skills/sprite-gen/scripts/render.sh <name>`
@@ -0,0 +1,47 @@
+#!/bin/bash
+# Render a 3D model to 2D sprites at 3 resolutions from 4 cardinal directions.
+# Usage: render.sh <model_name> [godot_path]
+# Example: render.sh wall_structural
+set -euo pipefail
+
+MODEL_NAME="${1:?Usage: render.sh <model_name> [godot_path]}"
+GODOT="${2:-$HOME/bin/godot}"
+REPO_ROOT="$(cd "$(dirname "$0")" && git rev-parse --show-toplevel)"
+PROJECT="$REPO_ROOT/renderer"
+SCENE="res://render_scene.tscn"
+OUTPUT="$PROJECT/output"
+
+# Verify model exists
+MODEL_FILE="$PROJECT/models/${MODEL_NAME}.tscn"
+if [ ! -f "$MODEL_FILE" ]; then
+    echo "ERROR: Model not found: $MODEL_FILE"
+    echo "Available models:"
+    ls "$PROJECT/models/"*.tscn 2>/dev/null | xargs -I{} basename {} .tscn
+    exit 1
+fi
+
+echo "Rendering: $MODEL_NAME"
+echo "Godot: $GODOT"
+echo "Project: $PROJECT"
+
+# Ensure resources are imported (headless, no display needed)
+echo "Importing resources..."
+"$GODOT" --path "$PROJECT" --headless --import 2>&1 || echo "Warning: import step had errors (may be non-fatal)"
+
+# Run Godot with the render scene, passing model name as user arg
+"$GODOT" --path "$PROJECT" "$SCENE" -- "$MODEL_NAME" 2>&1
+
+# Check output
+EXPECTED_FILES=0
+for dir in north east south west; do
+    for res in 1024 256 64; do
+        f="$OUTPUT/${MODEL_NAME}_${dir}_${res}.png"
+        if [ -f "$f" ]; then
+            EXPECTED_FILES=$((EXPECTED_FILES + 1))
+        fi
+    done
+done
+
+echo ""
+echo "Generated $EXPECTED_FILES/12 files in $OUTPUT/"
+ls -la "$OUTPUT/${MODEL_NAME}"_*.png 2>/dev/null || echo "No output files found."
@@ -1,83 +0,0 @@
---
-name: start-sprint
-description: >
-  Start sprint work on a team branch. Use when the user says "start sprint",
-  "start working on the server/client", "begin sprint", or invokes /start-sprint.
-  Merges main into the team branch, finds the active sprint, reads the sprint
-  briefing, and presents the work plan with ticket details.
-user-invocable: true
-allowed-tools: Bash, Read, Grep, Glob
---
-
-# Start Sprint Skill
-
-Prepare a team branch for sprint work: sync with main, load the sprint
-briefing, and present actionable next steps.
-
-## Workflow
-
-### 1. Determine the team
-
-The current branch IS the team. Read it with:
-```bash
-git branch --show-current
-```
-
-Valid team branches: `server`, `client`. If on `main`, ask the user which
-team branch to check out first.
-
-### 2. Sync with main
-
-```bash
-git fetch --all
-git merge origin/main --no-edit
-```
-
-If the merge has conflicts, report them and stop — do not force-resolve.
-
-### 3. Find the active sprint
-
-```bash
-db/connectors/ticket sprint --active
-```
-
-Extract the sprint ID and name from the JSON output. If no active sprint,
-report that and stop.
-
-### 4. Read the sprint briefing
-
-Read `docs/sprints/sprint-N/<team>.md` where N is the sprint ID and team
-matches the branch name. If the branch is `server` or `client`, use that
-directly. For other branches, check if a matching briefing exists.
-
-Also check for a `joint.md` briefing — joint tasks involve both teams and
-should be mentioned.
-
-### 5. Load ticket details
-
-For each ticket listed in the briefing, run:
-```bash
-db/connectors/ticket show <id>
-```
-
-Identify which tickets are actionable now (no open blockers) vs blocked.
-
-### 6. Read key decisions
-
-Read the decision files referenced in the sprint briefing so the agent has
-full architectural context before starting work.
-
-### 7. Present the work plan
-
-Output a summary:
- Sprint name and goal
- Branch status (clean merge or conflicts)
- Actionable tickets (unblocked, ready to start)
- Blocked tickets (and what blocks them)
- Key decisions loaded
- Suggested first task (lowest ID unblocked ticket)
-
-Then mark the first actionable ticket as `in_progress`:
-```bash
-db/connectors/ticket status <id> in_progress
-```
@@ -10,76 +10,67 @@ allowed-tools: Bash, Read, Grep, Glob

 # Ticket Skill

-Manage the Commonwealth project ticketing database at `db/commonwealth.db`.
-
-## Access Method
-
-**Use the `ticket` CLI for all ticket operations:**
-```bash
-db/connectors/ticket <command> [args...]
-db/connectors/ticket --help
-```
-
-All output is JSON on stdout.
-
-For raw SQL access (rare), use the wrapper scripts:
-| Script | Purpose |
-|--------|---------|
-| `db/connectors/sqlite-query "<SQL>"` | Run SELECT queries |
-| `db/connectors/sqlite-exec "<SQL>"` | Run INSERT/UPDATE/DELETE |
-| `db/connectors/sqlite-init` | Create/update database from schema |
-| `db/connectors/sqlite-seed` | Seed initiatives from DECISIONS.md |
+Manage the project ticketing database. Basic usage is in CLAUDE.md's CLI tools
+section. This skill covers the full command reference.

 ## Commands

-### List tickets
+### List tickets (full flags)
 ```bash
-db/connectors/ticket list [--status S] [--priority P] [--epic N] [--sprint N] [--assigned A]
+tooling/db/ticket list [--status S] [--priority P] [--epic N] [--sprint N] [--assigned A] [--team T]
 ```

-### Show ticket detail
-```bash
-db/connectors/ticket show <id>
-```
-Returns full ticket with children, blockers, and dependents.
-
 ### Create ticket
 ```bash
-db/connectors/ticket create <type> <title> [--parent N] [--priority P] [--decision D]
+tooling/db/ticket create <type> <title> [--parent N] [--priority P] [--decision D] [--team T]
 ```
 Types: `initiative`, `epic`, `story`, `task`, `bug`
 Priorities: `critical`, `high`, `medium`, `low`

 ### Update status
 ```bash
-db/connectors/ticket status <id> <new_status>
-db/connectors/ticket done <id> [<id> ...]
+tooling/db/ticket status <id> <new_status>
+tooling/db/ticket done <id> [<id> ...]
 ```
 Statuses: `backlog`, `ready`, `in_progress`, `review`, `done`, `cancelled`

 ### Assignment
 ```bash
-db/connectors/ticket assign <id> <agent>
-db/connectors/ticket unassign <id>
+tooling/db/ticket assign <id> <agent>
+tooling/db/ticket unassign <id>
 ```

+### Team assignment
+```bash
+tooling/db/ticket team <id> <teams>
+```
+Teams are comma-separated, e.g. `server`, `client`, `server,client`.
+
 ### Sprint management
 ```bash
-db/connectors/ticket sprint [--active]
-db/connectors/ticket sprint assign <id> <sprint_id>
+tooling/db/ticket sprint [--active]
+tooling/db/ticket sprint assign <id> <sprint_id>
 ```

+For sprint-scoped operations (status overview, context dumps, lifecycle),
+use the dedicated sprint CLI instead: `tooling/db/sprint --help`
+
 ### Dependencies
 ```bash
-db/connectors/ticket deps <id>
+tooling/db/ticket deps <id>
 ```

 ### Search and browse
 ```bash
-db/connectors/ticket search <keyword>
-db/connectors/ticket epics [--status S]
-db/connectors/ticket children <id>
-db/connectors/ticket count [--status S]
+tooling/db/ticket search <keyword>
+tooling/db/ticket epics [--status S]
+tooling/db/ticket children <id>
+tooling/db/ticket count [--status S]
+```
+
+### Batch show
+```bash
+tooling/db/ticket show --brief <id> [<id>...]
 ```

 ## Workflow
@@ -0,0 +1,147 @@
+---
+name: workshop-start
+description: >
+  Start a multi-agent design workshop from a workshop brief. Use when the user says
+  "start workshop", "run workshop", "let's start the workshop", or invokes /workshop-start.
+  Parses the workshop brief to extract participants, questions, and round format.
+  Creates a team, tasks, and spawns agents as teammates via the Task tool.
+---
+
+# Start Workshop
+
+## Prerequisites
+
+A workshop brief must exist at `docs/workshops/{name}/{name}-workshop-brief.md` containing:
+- **Participants** line (comma-separated agent names)
+- **Questions for participants** sections with numbered questions tagged by agent name
+- **Workshop Format** section defining number of rounds and their purpose
+
+## Workflow
+
+### 1. Parse the Brief
+
+Read the workshop brief. Extract:
+- Workshop name (from directory name)
+- Participant list (from `**Participants:**` line)
+- Per-participant questions (scan for `**{AgentName}**:` patterns in questions sections)
+- Round count and round descriptions (from `**Workshop Format**` section)
+
+### 2. Create Team
+
+```
+TeamCreate: team_name = "{workshop-name}", description from brief title
+```
+
+### 3. Always-Present Agents
+
+Two agents join every workshop regardless of the participant list:
+
+| Agent | Role | Task | Participates in discussion? |
+|-------|------|------|-----------------------------|
+| **Qatux** | Documenter | Captures all decisions, questions, dissent, consensus. Writes `workshop-notes.md` per round, produces final `workshop-outcomes.md`. | No — observes and records only |
+| **SI** | Sprint prep | Suggest adding when outputs include tickets. Creates tickets from decisions, links to sprint backlog. | No — execution prep only |
+
+Qatux and SI are **never dismissed early.** If the user reduces the team mid-workshop, keep qatux and si (if added). Documenting everything prevents loss of valuable information.
+
+### 4. Create Tasks (Round 1)
+
+One task per participant containing:
+- Instruction to read the full brief at its path
+- The specific questions assigned to that participant (extracted from all layers)
+- The output format from the brief's round description
+- **IMPORTANT — file output requirement:** Instruct each agent to write their full output to `docs/workshops/{name}/{agent}-round{N}.md` (e.g., `docs/workshops/test-architecture/gestalt-round1.md`). Agents must write to disk, not just send messages. This ensures Qatux and other agents can read all outputs directly without relying on message forwarding.
+
+One task for Qatux: "Document Round N — read all agent output files at `docs/workshops/{name}/*-round{N}.md` and capture decisions, questions, and dissent."
+
+Assign all tasks using TaskUpdate with `owner` = agent name.
+
+### 5. Spawn Agents
+
+Use the Task tool to spawn each agent as a teammate. Each call should:
+- Set `team_name` to the workshop team name
+- Set `name` to the agent name (e.g., "gestalt")
+- Set `subagent_type` to the matching agent type (same as name — see reference table)
+- Provide a prompt telling the agent to check TaskList for their assigned task
+
+Spawn all agents in parallel (one Task call per agent in a single message). Agents will appear as teammates in the Claude Code UI and pick up their tasks from the shared task list.
+
+For large workshops (>6 agents), spawn participants in batches to avoid overwhelming the system. Always-present agents (Qatux, SI) can run in background via `run_in_background: true`.
+
+### 6. Monitor
+
+- TaskList to check progress
+- SendMessage to nudge idle agents or provide clarification
+- Agents work autonomously — claim tasks, read the brief, produce responses
+
+### 7. Between Rounds
+
+When all Round N tasks are complete:
+1. Verify all agents wrote output files to `docs/workshops/{name}/`. If any are missing, nudge the agent or extract from their message and write the file yourself.
+2. Qatux reads all `*-round{N}.md` files and produces round summary in `round-{N}-notes.md`
+3. Create Round N+1 tasks (integration pass, synthesis, etc.) — include the same file output requirement
+4. Assign to agents with TaskUpdate
+5. Agents continue working
+
+### 8. Wrap Up
+
+**Always ask the user before wrapping up.** There may be more to discuss or additional rounds needed. Only proceed to wrap-up when the user confirms.
+
+Wrap-up sequence:
+1. Qatux produces final `workshop-outcomes.md` from accumulated notes
+2. Qatux creates or updates diagrams (via `/d2-diagram`) for any new D-records produced by the workshop
+3. If SI is present, SI creates tickets from decided items
+4. Send shutdown_request to all agents (qatux and si last, after they finish their output tasks)
+5. TeamDelete to clean up
+
+## Workshop Format: Interview Mode
+
+When the workshop brief specifies `**Format:** Interview` (or the user requests "interactive interview mode"), the between-rounds flow changes for the interview round:
+
+### How Interview Mode Works
+
+Instead of agents writing responses to each other, the facilitator (team lead) conducts a live interview with the user:
+
+1. **Collect all agent questions** — Read all Round 1 output files to gather every question.
+2. **Group thematically** — Organize questions into 5-7 thematic clusters (e.g., "The Vision," "The Confusion Type," "The Emotional Loop"). Questions from different agents that probe similar territory go together.
+3. **Present via AskUserQuestion** — Present each group using the `AskUserQuestion` tool, one group at a time (1-3 questions per group). For each question:
+   - Include the asking agent's name and domain
+   - Include the full question text with context
+   - Include the agent's reasoning for why the question matters
+   - Provide 2-4 option choices that represent distinct answer categories
+   - Always allow free-text via the "Other" option (automatic)
+4. **Capture nuance** — The user's free-text notes often contain the most important insights. Capture these verbatim in the transcript.
+5. **Summarize between groups** — After each group, briefly reflect back the key finding before moving to the next group.
+6. **Write full transcript** — When all groups are done, write the complete interview to `docs/workshops/{name}/lead-interview.md` with:
+   - Every question and full answer (verbatim where the user provided free text)
+   - Key findings per answer
+   - An interview summary section with the major revelations
+   - "What Survives" and "What Changes" sections
+
+### Why AskUserQuestion
+
+The user CANNOT see agent messages, task details, or file contents in the conversation. They only see your text output and AskUserQuestion prompts. Present all question context directly — never assume the user has read agent outputs.
+
+### Distributing Interview Results
+
+When creating Round 3 (proposal) tasks after an interview round, include the full transcript path and a summary of the major reframe in every agent's task description. If the user requests it, instruct agents to read the verbatim transcript.
+
+## Agent Type Reference
+
+Agent name maps directly to subagent_type:
+
+| Name | Domain | Typical workshop role |
+|------|--------|-----------------------|
+| gestalt | Systems design | Mechanics, fun factor, system interactions |
+| ozzie | Player experience | Wow moments, feel, emotional response |
+| tyre | Technical architect | Feasibility, performance, architecture |
+| stig | UI developer | Interface patterns, layout, interaction flows |
+| dudley | Server developer | Server-side systems, data flow, ECS |
+| paula | Narrative | Story, dialogue, character, political depth |
+| araminta | Visual design | Art direction, visual treatment, aesthetics |
+| nigel | Replayability | Emergent stories, second-playthrough, sandbox |
+| gore | Themes/endgame | What the game is about, philosophical questions |
+| mellanie | Copywriter | In-game text, voice, tone |
+| miri | Worldbuilder | Setting, factions, lore, consistency |
+| inigo | Sound design | Audio, soundscape, spatial audio |
+| troblum | Tech consultant | Second opinion on architecture/tech choices |
+| hoshe | QA/testing | Test plans, verification, quality |
@@ -0,0 +1,125 @@
+---
+name: worktree-update
+description: >
+  Sync worktree branches with main. Use when the user says "update worktrees",
+  "sync branches", "merge main", "worktree update", or invokes /worktree-update.
+  When on main: shows which worktree branches are ahead and lets the user pick
+  which to merge into main (flags branches with open PRs). When on a non-main
+  branch: merges main into the current branch. All operations are non-destructive.
+user-invocable: true
+allowed-tools: Bash, Read, AskUserQuestion
+---
+
+# Worktree Update Skill
+
+Sync worktree branches safely. Direction depends on the current branch.
+
+## Safety Rules (NON-NEGOTIABLE)
+
+- **Never force-push, reset --hard, rebase, or delete branches.**
+- **Never use `--no-verify` or skip hooks.**
+- **Always use `--no-edit` on merges** to avoid interactive editor prompts.
+- **Stop on merge conflicts** — report them and let the user decide. Never
+  auto-resolve or abort a conflicted merge without asking.
+- **Fetch before comparing** — always `git fetch --all` first so commit
+  comparisons are accurate.
+- **Dry-run first on main** — show the user exactly what will happen before
+  merging anything into main.
+
+## Workflow
+
+### 1. Detect current branch
+
+```bash
+git branch --show-current
+```
+
+Branch determines the mode: `main` → outbound sync, anything else → inbound sync.
+
+### 2a. On `main` — merge worktree branches into main
+
+#### Fetch and compare
+
+```bash
+git fetch --all
+```
+
+Discover all worktree branches (excluding `main` itself):
+
+```bash
+git worktree list | grep -v '\[main\]' | sed 's/.*\[//;s/\]//'
+```
+
+For each worktree branch, check if it has commits ahead of main:
+
+```bash
+git rev-list --count main..origin/<branch>
+```
+
+Skip branches with 0 commits ahead. For branches that ARE ahead, collect:
+- Branch name
+- Number of commits ahead
+- One-line log of those commits: `git log --oneline main..<branch>`
+
+#### Check for open PRs
+
+```bash
+tea pr list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
+```
+
+Cross-reference open PR head branches with the ahead-of-main branches.
+
+#### Present results
+
+Show a summary table of branches ahead of main. For each branch, indicate:
+- `[PR]` if it has an open pull request — warn that it should go through
+  normal review channels (use `/pr-review` instead)
+- Commit count and summary
+
+Use `AskUserQuestion` to let the user pick which branches to merge.
+Exclude PR-flagged branches from the default options (but allow the user to
+override via "Other").
+
+#### Merge selected branches
+
+For each selected branch, one at a time:
+
+```bash
+git merge <branch> --no-edit
+```
+
+If a merge conflicts, **stop immediately**. Report the conflict and do NOT
+continue to the next branch. The user must resolve before proceeding.
+
+After all merges, show the final state with `git log --oneline -N` (where N
+covers the new commits).
+
+#### Backup the shared database
+
+After successful merges on main, snapshot the database for git tracking:
+
+```bash
+make db-backup
+```
+
+This copies the shared `settledreach.db` (in the parent directory) to
+`docs/backups/settledreach.db.backup`. Stage and commit it with the merge
+if the file changed.
+
+### 2b. Not on `main` — merge main into current branch
+
+```bash
+git fetch --all
+git merge origin/main --no-edit
+```
+
+If clean, report the result (fast-forward or merge commit, files changed).
+If conflicts, report them and stop.
+
+### 3. Push
+
+After a successful merge, push the branch:
+
+```bash
+git push origin <current-branch>
+```
@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+# Pre-commit hook dispatcher. Runs modular checks from tooling/.
+# Installed via: git config core.hooksPath .config/hooks
+set -euo pipefail
+
+REPO_ROOT="$(git rev-parse --show-toplevel)"
+ERRORS=0
+
+run_check() {
+    local script="$1"
+    local label="$2"
+    if [ -x "$REPO_ROOT/$script" ]; then
+        if ! "$REPO_ROOT/$script"; then
+            ERRORS=$((ERRORS + 1))
+        fi
+    else
+        echo "pre-commit: WARNING — $label skipped ($script not found or not executable)"
+        echo "  Run 'make setup' or check that $script exists and is executable."
+    fi
+}
+
+# --- Checks ---
+run_check "tooling/check-fact-ids" "fact_id validation"
+run_check "tooling/check-decision-ids" "decision ID duplication"
+
+if [ "$ERRORS" -gt 0 ]; then
+    echo ""
+    echo "pre-commit: $ERRORS check(s) failed. Commit aborted."
+    exit 1
+fi
@@ -1,16 +1,28 @@
 # Build and cache
 .cache/
+.tmp/
 server/target/
+tooling/content-converter/target/
+tooling/line-previewer/target/
+tooling/test-client/target/
+content-ron/

-# Godot
+# Godot client (further ignores managed by client team)
 client/.godot/
 client/export/
 client/reports/
-client/*.import

-# Database journal files (transient, not the DB itself)
-db/commonwealth.db-wal
-db/commonwealth.db-shm
+# Renderer (separate Godot project for sprite pipeline)
+renderer/.godot/
+renderer/**/*.import
+renderer/**/*.uid
+renderer/output/*.png
+
+# Database (shared across worktrees at ../settledreach.db, not tracked)
+db/commonwealth.db*
+
+# Frame0 ID mapping files (ephemeral, per-machine)
+*.idmap.json

 # Python
 __pycache__/
@@ -27,8 +39,8 @@ Thumbs.db
 *.swp
 *.swo

-# Claude Code internals (plans, session transcripts, local settings)
-# Note: .claude/agents/ and .claude/skills/ ARE tracked
+# Claude Code internals (plans, session transcripts)
+# Note: .claude/agents/, .claude/skills/, and .claude/settings.json ARE tracked
 .claude/plans/
 .claude/projects/
-.claude/settings.json
+.claude/agent-memory/
@@ -6,10 +6,891 @@ Format based on [Keep a Changelog](https://keepachangelog.com/).

 ## [Unreleased]

+## [v0.1.24] — 2026-03-06
+
+### Changed
+- Replaced all in-universe "Commonwealth" references with "the Settled Reach" across 44 files (agents, decisions, docs, tooling, server). Historical discussion transcripts and Hamilton book references kept as-is.
+
 ### Added
+- Character archetype select screen — two-card UI (Smuggler/Detective) between New Game and session start, keyboard+mouse selection, ESC cancels (#588, D-027)
+- Triangle activation consumer — urgent monologue chime fires once per triangle per session when triangle_crisis_events received (#590, D-039)
+- News ticker HUD — scrolling marquee visible in The Last Shift zone, hidden elsewhere, reads current_ticker from snapshot (#592, D-039)
+- Triangle activation proximity monologue lines — 5 smuggler lines (Kael Davan) and 5 detective lines (Sera Venn/Torek Lintar) that fire when observing triangle anchor NPCs post-activation (#597, D-035, D-039)
+
+### Changed
+- Protocol version bumped to 19 — StartupMessage includes character_archetype, snapshot includes triangle_crisis_events and current_ticker (#588, #590, #592)
+
+## [v0.1.23] — 2026-03-04
+
+### Added
+- TileKind enum (Floor/Wall/Void/Restricted) on WalkabilityMap with per-tile type data alongside walkability (#576, D-094)
+- Location YAML tile format — hand-author tiles as string arrays (F/W/V/R characters), loaded into WalkabilityMap on production startup (#577)
+- Chunk streaming system — ChunkLoadRadius and cadence-gated load/unload around player position, v0.1 covers full district (#578, D-012)
+- EngagementRecord component — per-NPC observation time, conversation count, and monologue trigger count tracked by perception/dialogue/monologue systems (#570)
+- MovementHistoryBuffer resource — 3000-tick ring buffer of player positions with co-presence proximity query (#571)
+- Storyteller lifecycle rules — single activation per session, no concurrency, terminal resolution constants (#572)
+- Storyteller activation_pass() — gate/proximity/engagement scoring/routing/module selection/TriangleActivatedEvent on 10-tick cadence (#579)
+- Debug console server — 10 DebugCommandKind variants (AdvanceTicks, SkipToContamination, TeleportToPosition, InspectNpc, ListTriangles, etc.) with DebugResponsePayload on ObserverSnapshot (#580)
+- Debug console client — tilde-toggle UI panel with command input, output log, settings toggle, and full DebugCommandKind dispatch via protocol v18 (#581)
+- Entity-bound dialogue speaker colors — NPC colors assigned by entity ID (not screen position) with per-conversation lifecycle and round-robin palette (#573)
+- Sova Transit District tile maps — 5 locations authored: The Terminal (44×28), The Last Shift (34×22), Maintenance Corridors (58×6), Gate Ground (40×34), Gate Gallery (32×10) (#582, #583)
+
+### Fixed
+- LOS boundary walls — 1-tile wall margin beyond vision cone included in visible_tiles as BoundaryWall sector, walls at fog edge now render instead of bleeding into fog (#584)
+- LOS boundary walls client — BoundaryWall tiles render through fog without marking explored, 4 new fog tests verify lifecycle (#585)
+- Entity renderer test failures — updated 7 stale ColorRect/position assertions for Sprite2D migration, fixed SoundIndicatorRenderer class cache (#574)
+- Dialogue speaker color contrast — re-enforce contrast floor after desaturation for passive (overheard) lines
+- PROTOCOL_VERSION 17 → 18 mismatch — client rejected every server snapshot
+- Debug console D-088 pause — sim now pauses while console is open, matching dialogue/settings overlay behavior
+- Debug console settings toggle reads live state instead of ConfigFile, preventing checkbox divergence
+
+### Changed
+- PROTOCOL_VERSION bumped 17 → 18 (debug_response field on ObserverSnapshot, DebugCommand PlayerAction variant)
+
+## [v0.1.22] — 2026-03-03
+
+### Added
+- Visual test harness — `make screenshot`, `make test-visual`, `make visual-update` for automated visual regression testing with golden PNGs across 11 scenarios (fog, HUD, dialogue, minimap)
+- Visual movie mode — `make visual-movie` captures interaction flows as frame sequences with contact sheet generation
+- World seed protocol — StartupMessage carries world_seed from client to server after handshake, enabling deterministic NPC population seeding (D-010, D-029)
+- EntanglementConfig — per-seed NPC population ratios (flat/mundane/intrigue) sampled from seeded RNG with D-029 bounds, ensuring same seed = same world (#175, #178)
+- Fog debug mode — toggle FogState.debug_exploration to render raw exploration texture as colored overlay for diagnostic use
+- D-110 through D-112: z-level addressing, subterranean architecture, no instancing decisions
+- Q-051: speech bubble indicator over speaking NPCs
+- Sprint 22 "Wire" briefings (server, client, visual, CI, planning, joint)
+
+### Added (server)
+- Production NPC pool generation — 23 authored Sova NPCs spawn with EntanglementTag (Flat/Intrigue) based on triangle membership (#176, D-029)
+- Authored triangle instantiation — 5 Sova triangles (3 active forks, 2 passive tensions) loaded from content YAML with deterministic IDs (#188, D-087)
+- Contamination activation mechanic — timer-based storyteller fires after 30 game-minutes, pressures active triangles, emits ContaminationEvent (#254)
+- Modifications data model stub — Vec<Modification> on chunk entities, round-trips through save/load for future construction DLC (#567, D-112)
+- Zone Gate gauntlet room — two-zone test room with door boundary, zone crossing detection system (#512)
+- Fuzzy map tests — 50-seed randomized testing of procedural maps against 4 structural invariants (#509)
+
+### Fixed
+- Fog shader: silent compilation failure in OpenGL3 compat mode — removed `return` statements from fragment() which are not supported, causing fog overlay to render as no-op (root cause of Sprint 22 fog regression)
+- Fog system: blocky stair-stepped edges at vision cone boundary — doubled Gaussian blur step size for D-066 compliant 6-8 tile smooth gradient (#569)
+- Fog system: zero visibility in explored areas — switched bounds calculation from visible_tiles (empty in live server mode) to visible_positions, and removed shader guard that cut off gradient bleed into unexplored tiles (#569)
+- Fog shader alpha tuned to D-059 spec: light fog 0.25-0.35 (was 0.25-0.55), deep fog 0.55-0.70 (was 0.78-0.90) — world content now visible through fog instead of hidden behind it (#563)
+
+### Changed
+- Fog shader now distinguishes light fog (near cone, neutral dark) from deep fog (far from cone, zone temperature tint) with separate Perlin noise breathing cycles (8-10s / 15-20s)
+- Zone temperature tint populated per-tile from server zone_id: bar=warm amber-dark, hub=cool blue-dark, corridor=neutral dark (D-059/D-046/D-077)
+- Simplified vision cone from 3-sector (forward/peripheral/blind) to forward-only 120° arc — server sends only forward-cone tiles, client renders explored tiles behind the player with light fog overlay
+- Simplified fog shader from 5-layer to 3-layer model (clear, explored, unexplored)
+- Fog texture resize now preserves exploration data — tiles behind the player stay as light fog instead of reverting to unexplored black
+- Updated D-015/D-017 perception decisions to reflect simplified cone model
+- Moved connector scripts from db/connectors/ to tooling/db/ (#274) — backwards-compat symlink removed in #568
+
+### Removed
+- db/connectors symlink — all references now use tooling/db/ directly (#568)
+
+## [v0.1.20] — 2026-02-25
+
+### Added
+- Social site template schema — RoleSchema (#163), SpaceSpec (#164), TriangleDef (#106) with YAML deserialization, sample templates at server/data/templates/
+- Single-ownership model — TemplateOwnership component, TemplateReferenceMap resource, cross-template reference links preserved across save/load and tier eviction (#165, D-025)
+- Triangle generation — intra-template constraint satisfaction assigns NPCs to triangle roles, minimum 2 triangles per template with fallback on imperfect seeds (#107)
+- Triangle escalation system — tick_triangle_escalation runs per game-minute, tension increments toward ToleranceThreshold, TriangleCrisisEvent emitted on Active phase entry, ResolveTriangle stub command (#250, D-087)
+- Protocol v16 — TriangleCrisisEventWire on ObserverSnapshot for future client rendering of triangle crises
+- D-093: Sova Transit District spatial layout — 4 social sites (Terminal, Bar, Gate Cluster, Sector 3), 2 encounter nodes, zone palette, gate cluster 7-zone spec, z-level scheme (z=0 maintenance, z=1 main, z=2 observation gallery), 3 investigation paths, corridor widths
+- D-094: Spatial hierarchy — chunk (64×64 sim) → block (128×128 sim) → district (4×4 blocks, 256×256 visual), supersedes D-014 estimate
+- D-095: Horizon stations and transport lore — span gates (human-built, dual-use), horizon stations (alien-built, 4-8 apertures), "The Ring" per-system naming, sequential hop travel, The Loop internal tram
+- Generator architecture workshop brief (ticket #562) — top-down pipeline for district generation, targeting Q-036 resolution
+- SnapshotEventRouter — callable-based snapshot dispatch replaces inline if-has blocks in main.gd (#559)
+- YamlParser shared utility — unified YAML parsing for UI strings and checklist conditions (#560)
+
+### Fixed
+- Wire triangle crisis event queue into observer snapshot — clients now receive TriangleCrisisEventWire via protocol v16 (was always empty)
+- Persist TriangleState in SaveStateV1 — triangle phase and tension survive save/load cycles
+- Validate dangling with_role references in TriangleDef constraint validation
+- Replace O(n²) fallback NPC assignment with BTreeSet; prevent same NPC assigned to two roles in one triangle
+- Replace O(N*M) scan in apply_resolve_triangle with BTreeMap index for O(1) per-command lookup
+- Add From impls for RoleId, TriangleId, StableId, TriangleCrisisEventWire — eliminate fragile .0 newtype access
+- Consolidate near-identical unit tests with integration counterparts
+
+### Changed
+- Sova station profile updated — horizon gates located at The Krenn Ring (800 AU), not on Station Sova; Admin Hub houses transit processing facility only
+- game_state.gd: stationary_ticks and zone_id now read from server snapshot with deprecated client-side fallbacks (#557, D-020)
+- dialogue_box.gd: decoupled from GameState and AudioManager via signals — zero direct autoload references (#558, D-020)
+- main.gd: snapshot dispatch via SnapshotEventRouter, dialogue signal coordinator handlers (#559, #558)
+- ui_strings.gd and checklist_evaluator.gd: delegate to YamlParser, ~140 lines of duplication removed (#560)
+
+## [v0.1.19] — 2026-02-25
+
+### Added
+- Sprint 20: Shape planned — 11 tickets (server 6, client 4, planning 1) covering template/triangle schemas, client refactors, and district layout design discussion
+- Planning team ticket type in sprint-plan skill — supports design discussions with purpose-assembled agent panels, Qatux and SI for bookkeeping
+- Client PR #70 merged — save/load client UI, F5/F6 quicksave/quickload (#554)
+- Server PR #68 merged — Sprint 19 save/load, tier eviction, test infra (7 tickets, 2714 lines)
+- Client PR #67 merged — Sprint 19 test infra, session management, debug overlay (5 tickets, 2547 lines)
+- CI PR #69 merged — Sprint 19 test runners, IPC fixtures, protocol handshake, benchmark (4 tickets, 1297 lines)
+- Test runner scripts — 7 bash scripts (run-rust, run-godot, run-ipc-fixtures, run-ipc-protocol, run-ipc-integration, run-ipc-benchmark, run-all) with structured JSON output (#270, D-030)
+- IPC serialization fixtures — 5 msgpack fixtures with Rust generator, cross-language GDScript validation (22 assertions) (#271, D-030)
+- Protocol handshake client — HANDSHAKING state in SimBridge, HandshakeMessage decode with 5s timeout (#556, D-020)
+- IPC round-trip benchmark — p50/p95/p99 latency reporting, 5ms threshold (#342, D-020)
+- Protocol version handshake — `HandshakeMessage` as first IPC frame before tick loop, forward-compatible input handling (#555, D-020)
+- Protocol v15 — `save_result` field on ObserverSnapshot for client save/load confirmation
+- State serialization primitives — `serialize_npc_to_frozen`/`deserialize_npc_from_frozen` with full D-024 10-axis coverage for tier eviction freeze/thaw (#96, D-026)
+- Scope tag system — `ScopeTagKind` (Neighborhood, ActiveQuest, Colleague, KnownContact), `ScopePinned` marker, automatic assignment from KnowledgeGraph and RelationshipGraph (#98, D-026)
+- Timestamp-based eviction — `LastInteractionTick` LRU tracking, `SimSpacePressure` resource, BinaryHeap eviction respecting scope-pinned entities, Active cap 80 (#97, D-026)
+- Save/load ECS extraction — `save_to_file`/`load_from_file` via MessagePack, `SaveGame`/`LoadGame` IPC commands, `SaveLoadResultWire` on ObserverSnapshot (#553, D-085)
+- ScopePinned eviction regression test — adversarial at-scale test proving pinned NPCs survive eviction even with oldest ticks
+- Test infrastructure — Layer 3 integration test entry point, three-layer architecture per D-030 (#200)
+- Information boundary negative tests — 4 tests proving no passive KG leakage, LOS fog holds, tier boundary holds, per-NPC save isolation (#272, D-010)
+- gdUnit4 CI runner script — headless test execution via `run_gdunit4.gd` with exit code for CI (#205)
+- Scene testing utilities — SceneHelper class with node existence, signal, and path helpers for gdUnit4 (#206)
+- GameState apply_snapshot tests — 14 tests covering v2+ fields: game_time, facing, interactions, monologue, stance, inventory (#206)
+- Game session management — per-game save directories under `user://saves/<timestamp>-<seed>/` per D-085, SessionManager autoload, main menu scene (#258)
+- Debug visualization overlay — F3-toggled dev overlay with LOS rays, vision cone arcs, NPC path trails, knowledge confidence tags, tick timing sparkline (#348)
+- SimBridge→TestHarness extraction — test simulation logic separated into dedicated RefCounted class with backward-compat proxy API
+- Workshop outcomes files — formal closure for content-gap-analysis, KG-information-boundaries, v01-content-scoping, v01-gap-analysis, wiki-review
+- D-087 through D-092 — recovered decisions from v01-content-scoping and wiki-review workshops (triangle config, pause system, content scope, voice registers, anchor lines, complicity theme)
+- Q-030 through Q-039 — open questions from workshop backlog (seed schema, style guide, cultural ingredients, NPC architecture, PC archetypes, sacred/profane framework, district skeleton, generator pipeline, authored content estimate, gate topology)
+- Decision ID claim system — `db/connectors/decision` CLI with `next`, `claim`, `check-dupes` commands to prevent cross-worktree D/Q/R ID collisions, pre-commit duplicate check
+- D-085: Per-game save directory structure — every new game creates `user://saves/<game-id>/`, F5 quicksave, F6 quickload
+- Q-029: Save file format design — long-term considerations for versioning, compression, integrity, metadata headers
+- D-086: Renumbered insert icon system (was D-084 on visual branch) to resolve cross-worktree ID collision
+- Save/load wireframe updated for D-085 — LOAD tab shows games grouped by directory with expand/collapse, QUICKSAVE slot, F5/F6 hints
+- Sprint 19: Persist planned — 16 tickets (server 7, client 5, CI 4) covering save/load, tier eviction/scope, test infrastructure
+- Character creation & game setup workshop brief — covers creation model, seed boundary, gate activation, quest seeding, game toggles (resolves Q-011)
+- Protocol v14 — `poi_list`, `examine_result`, `player_knowledge` ObserverSnapshot wire types with live KG serialization (#151, #174, #264)
+- Minimap rendering — circular 160px diegetic insert overlay with POI dots (colored by category), border arrows for distant POIs, player-centered fixed-north (#151)
+- Dialogue UI hardening — confrontation italic voice (D-063), examine result overlay with 5s auto-dismiss and confidence coloring (#174)
+- Knowledge/journal panel — right-side insert panel (J key), facts grouped by entity, contradicted entries in amber with strikethrough, stale entries dimmed, mutual exclusion with dialogue (#264)
+- Sprint 18 client test suite — 50 gdUnit4 tests for dialogue (D-062, D-063, D-064) and journal (KG parsing, scene structure, UIStrings), plus test plan document
+- D-084: dual-namespace line ID scheme for auto-generated NPCs — role pool (shared, unchanged) + instance override (opt-in, seeded counter). Resolves Q-028 (#544)
+- Tier 1 drama module schema (`content/schemas/drama_module.schema.yaml`) — entry conditions, NPC requirements, event sequences, outcomes, pool format (#158)
+- Smuggling ring v0.1 stub module (`content/modules/tier1/smuggling_ring_v0_1.yaml`) — vertical slice Tier 1 module with 6 NPC roles, dual event sequences, 5 outcomes (#158)
+- Line ID authoring guide (`docs/design/line-id-authoring-guide.md`) — dual-namespace conventions for hand-authored and auto-generated NPC content
+- Tier 1 module authoring guide (`docs/design/tier1-module-authoring.md`) — field reference, NPC pattern/motivation tables, design principles, pre-submission checklist
+- Background tier state machines — schedule, mood, relationships, job tick once per game-minute for Background NPCs (#95, D-026)
+- NPC vision system — symmetric shadowcasting for Active-tier NPCs, NpcMemory with last-known-position and zone inference (#115, D-011)
+- NPC player-awareness behavior — PlayerAwareness component tracks LOS duration, suspicion accumulation, routine deviation triggers (#244)
+- Skill system & combat flag — SkillSet component (BTreeMap<String, u8>), CombatCapability marker from combat_trained skill (#91, D-024)
+- Player-action social propagation — three-order trust ripple (100%/40%/20%) through RelationshipGraph with cycle prevention (#249, D-029)
+- Examine mechanic — process_examine_interaction with character-filtered observation text, KG DirectObservation write, examine_result in ObserverSnapshot (#242)
+- Character goal/pressure framework — CharacterPressure component (exposure/institutional/relationship), wired to snapshot HUD data (#248)
+- Save state data model — SaveStateV1 struct with MessagePack serialization, roundtrip tests for entity/KG/relationship/clock state (#256)
+- Tell state derivation wired into ObserverSnapshot — integration tests for Nervous tell on Major secret + high stress (#337)
+- Sprint 18: Touch planned — 14 tickets (server 9, client 3, copy 2) covering examine mechanic, NPC awareness, social propagation, minimap, dialogue UI, save state model
+- `.claude/rules/` directory — modular auto-loaded instructions (tea-cli, git-safety, project-structure, team-patterns, local-services)
+- KnowledgeGrant untagged enum with Fact and Entity variants, ContentEntityRegistry for NPC spawn-time entity resolution (D-079, #545)
+- KnowledgeGranted event processing — grants fire at dialogue line selection, runtime NPC KG guardrail (D-079, #546)
+- ContradictionClaim struct with 600-tick window detection in observe_entity, epistemic neutrality for both sources (D-083, #547)
+- NPC-to-NPC knowledge transfer system — trust-gated fact exchange, confidence capping at KnowsOf, ToldBy source construction (D-080, #548)
+- tell_state KG awareness — NPC relationship reads from KG for other-entity state, MVP information boundary (D-082, #549)
+- Contradiction monologue with pre-resolved entity names, PersonOfInterest relationship shift, THE FRIEND arc event chain (D-083, #550)
+- Unprompted disclosure system — DisclosureCandidates component, 7 trigger gates, three-layer rate limiting, two-stage trait filter (D-081, #551)
+- Trait modifier system — Cautious/Gossipy/Loyal/Talkative filter predicates via content-authorable config (D-081, #173)
+- POI data model and proximity-based discovery system via KnowledgeGranted events (#148, #149)
+- Protocol versioning tests — version round-trip, mismatch detection, serde_default migration pattern, full variant coverage (#232)
+- Team monitoring rules — heartbeat rule for stuck agent detection, bottleneck detection pattern
+- `tooling/tea-comment` — single-command wrapper for posting Gitea PR/issue comments with multi-line bodies
+- D-086: Insert icon system — custom SVG icons over icon fonts, authored to insert geometric constraints with lattice_profile weight scaling
+- Insert/HUD wireframe and visual spec (#314) — dual character variants (smuggler social network view, detective investigation overlay) with pixel-precise layout, entity markers, time display, border arrows, commission grid, and all interaction states
+- Contradiction monologue lines — 16 hand-authored lines (8 detective, 8 smuggler) for Sera/Kael FRIEND arc, Phase 2 blindsiding + Phase 3 pattern recognition, cognitive-dissonance-not-accusation tone per D-083 (#552)
+- Diegetic tutorial monologue — 20 lines (10 per character) teaching movement, fog, sound, NPC interaction, and insert/HUD through character voice, fire-once on first-time events (#330)
+- Diegetic time display on insert HUD — station local time (HH:MM), day phase with cycle-tinted color, day number on InsertOverlay (#263)
+- Relationship color accent on E-Talk overlay — 3px left-edge bar using D-033 palette signals NPC relationship at a glance (#537)
+- `Constants.format_game_time()` helper for converting game-minutes to HH:MM station time
+- `/sprint-status` cleanup sweep skill — consistent health report with tickets by status, PR cross-reference, bookkeeping issue detection, and open work by team
+- `sprint sweep` CLI subcommand — structured JSON output for sprint health checks (grouped tickets, per-team summary, issue detection)
+- Knowledge Flow & NPC Boundaries workshop — 5 D-records (D-079–D-083) covering grant architecture, NPC-to-NPC propagation, unprompted disclosure, NPC information boundaries MVP, contradiction detection pipeline
+- 7 knowledge graph implementation tickets (#545–#551) with full dependency chain and line estimates
+- Contradiction monologue content ticket (#552) for Sera/Kael FRIEND arc
+- Sprint 17 completion proofs: contradiction detection fires, NPC-to-NPC knowledge transfers
+- Entity renderer migrated from ColorRect placeholders to Sprite2D with D-019 angle sprites — self_modulate for D-033 tinting, 8→4 octant direction mapping, feet-anchored y-sort (#540)
+
+### Fixed
+- Client protocol version bumped to 15 to match server (was still at 14 after server PR #68 added save_result field)
+- gen_fixtures.rs version comments changed from hardcoded 14 to PROTOCOL_VERSION constant
+- run-ipc-benchmark dead --iterations flag removed (Rust compile-time constant governs rounds)
+
+### Changed
+- Team boundary framing — replaced worktree-centric language with `$WORKTREE_TEAM` env var identity across CLAUDE.md and skills (sprint-start, sprint-plan, pr-review) to prevent agents from following `.git` pointers across boundaries
+- CLAUDE.md compacted from 188 to 67 lines — CLI references, endpoints, and patterns moved to `.claude/rules/`
+- `/sprint-status` delegates to haiku subagent — keeps sweep JSON, template read, and PR list out of main context window
+- `sprint sweep` JSON trimmed — removed unused fields (`ok`, `sprint.status`, `priority`, `ticket_id`), shortened issue detail strings
+- Sprint status output template condensed — rendering rules moved to skill definition, bookkeeping table simplified to 2 columns
+- Model selection documented in CLAUDE.md — `/model sonnet[1m]` and `/model opus[1m]` for 1M context sessions
+- Sprint 17 briefings updated with workshop results — server (14 tickets), copy (2 tickets), client (2), visual (1)
+- Q-024 (gossip timing), Q-025 (KG memory), Q-026 (contradiction detection) closed
+- Sprint 16 closed (8/8 done)
+- 3D sprite render pipeline — Camera3D at D-019 angle (-72.5° from horizontal), three-point studio lighting rig, orthographic projection, resolution chain 1024→256→64
+- Generic NPC capsule model (24×32px footprint per D-044) and structural wall model for pipeline validation
+- Test sprites: 8 runtime 64px sprites (NPC + wall × 4 directions) deployed to client/assets/sprites/
+- Pipeline documentation (renderer/README.md) — camera spec, lighting rig, resolution chain, model authoring guide
+- DialogueResponse verb handler — players pick dialogue options and receive follow-up lines via full D-028 four-layer pipeline (#539)
+- Trust-gated gossip verification — integration tests confirm Secret/Real/Surface tier gating per D-075 (#171)
+- Line variety tracker wiring — DialogueCooldownTracker prevents repeat lines within 600-tick window (#338)
+- DialogueResponse cross-language fixture for GDScript testing
+- Sprint team lifecycle through PR review — teams stay alive for commit → push → review → fix loop → approve → shutdown
+- Zone_id extraction in game_state.gd optimized from O(N) tile scan to O(1) dictionary lookup — builds _tile_by_coord from member visible_tiles covering both test and live paths (#543)
+- Shared run_dialogue_pipeline() helper eliminates ~60 lines of duplication between Talk and DialogueResponse systems
+- Dialogue and monologue line IDs migrated from location-scoped (the-terminal_d_039) to NPC-scoped (kael-davan_d_001) namespace — each NPC has an independent sequence per D-035 (#542)
+- DialogueCooldownTracker documented as per-player-global by design (NPC-scoped line IDs per D-035 prevent collision)
+- CONFRONTATION_LINES marked TODO for migration to D-028/D-035 content pipeline
+- pr-push and pr-review skills updated with team lifecycle awareness
+
+### Fixed
+- PR #59 review: stale mood vocabulary updated in line-pool-format.md, style-guide, and content-directory-structure.md to post-Sprint 14 values
+- PR #59 review: orphaned location-scoped IDs in maintenance-tech.yaml comments and smuggler-inventory.yaml cross-references updated to NPC-scoped
+- PR #59 review: Lera Sessik tenure corrected from "twelve years" to "eighteen years", NPC header fixed
+- PR #59 review: ring-operative.yaml fact_id corrected from `location.surveillance_gaps` to `investigation.surveillance_gaps`
+- Dialogue systems moved from BridgePlugin to NpcPlugin — game logic registers where it belongs (#538)
+- Schedule ambiguity: emit_observation_events now has explicit .before(advance_tick) constraint
+- process_dialogue_response updates ActiveDialogue tick and InteractionMemory on follow-up
+- DialogueResponse range check added (CLOSE_RANGE, matching Talk/Confront pattern)
+- Weighted selection fallback replaced with unreachable!() — dead code removed
+- assert!(false) → panic!() in serialization tests (clippy)
+- SetFacing and TeleportToHub added to roundtrip test coverage
+
+## [v0.1.15] — 2026-02-23
+
+### Added
+- Sprint 16 "Converse" briefings — 8 tickets across server/client/copy/visual teams
+- 19 UI wireframes — HUD, dialogue, monologue, popups, menus in v0.1 and v1.0 variants with D-record cross-references
+- d2-diagram skill — text-to-diagram generation with project defaults (theme 200, dagre, PNG)
+- frame0-wireframe skill — UI wireframing via Frame0 HTTP API, replaces MCP dependency with bash+curl
+- 16 decision diagrams — architecture, data-flow, entity, state, and UI categories covering all project decisions
+
+### Changed
+- frame0-wireframe skill rewritten — JSON-as-truth workflow with frame0-sync.py, batch export, renderer-only guidance
+- pr-review skill — all reviewer agents now use worktree paths instead of git show
+- Dialogue panel is always visible as permanent insert UI element (D-061)
+- Makefile: check-protocol target verifies server/client protocol versions match before build
+- D-035 amended: line ID namespace changed from location-scoped to NPC-scoped (Sprint 15)
+- Tilemap z-layer filtering — FloorTiles renders z=0 only, z=1/z>1 reserved for future layer nodes (#71, D-049)
+- Entity 24x32 footprint per D-044 visual hierarchy — split ENTITY_SIZE into WIDTH/HEIGHT with separate offsets (#72)
+- Follow target stub on GameState — `follow_target_id` field ready for server #241 Follow verb
+- Manual exponential camera smoothing — CAMERA_SMOOTHING_SPEED constant (8.0), same lerp pattern as entity renderer (#117)
+- 31 new Sprint 15 validation tests — camera smoothing, UI framework z-layers, entity footprint, Sprint 14 regressions
+- SpatialIndex trait with naive Vec implementation — entities_in_range, entities_at, update methods with Manhattan distance (#340)
+- NPC generation pipeline — procedural seeding of all 10 D-024 axes via SimRng with constraint validation (#92)
+- Personality and tell system — 5 tell categories (Nervous, Angry, Friendly, Guarded, RoutineDeviation) derived from NPC axis values each tick (#90)
+- Tolerance threshold monitoring — ToleranceBreachEvent on stress exceeding per-NPC threshold, mood FSM integration (#105)
+- Routine deviation detection — RoutineDeviationEvent on wrong location/activity for day phase, absence detection, pathfinding-aware (#243)
+- Follow mechanic — Follow verb, proximity/LOS tracking, double-frequency observation events, NPC suspicion accumulation, configurable thresholds (#241)
+- Monologue event triggers — observe_npc, hear_sound, observe_anomaly, witness_interaction, post_conversation with D-035 context tags (#119)
+- Protocol v13 — tell_state on VisibleEntity, follow_state on ObserverSnapshot, Follow verb
+
+## [v0.1.14] — 2026-02-21
+
+### Added
+- Unified dialogue log — player-NPC and overheard NPC-NPC conversations in one chronological scrolling panel (#535, D-061/D-078)
+- F3 debug overlay — real-time game state display with tick, FPS, position, entity counts, dialogue/monologue status (#511)
+- Monologue display — multi-line priority queue with character colours, italic BBCode, stagger animation (#122)
+- Protocol v9 — conversation_events, conversation_ended, dialogue_response fields with carry-forward logic
+- Dialogue theme system — configurable NPC name colour palette, entry timing, passive opacity via dialogue-theme.yaml
+- Monologue display system visual spec — typography, positioning, stacking, priority, fade animation, character color differentiation, 80-char line constraint (#315)
+- Entity color system spec — D-033 relationship-to-player mapping, transition animations, color blindness assessment (#304)
+- Text display hierarchy spec — 4 content pipelines (dialogue, monologue, observation, environmental) with z-layers and positioning (#316)
+- Sound indicator visual design — fog-edge pulse for D-018 three-range sound model with direction encoding and range differentiation (#317)
+- THE FRIEND visual treatment spec — 3-phase earned visual detail for Kael Davan and Sera Venn (#318)
+- Environmental text visual standards — signage, terminal, and news ticker rendering with bilingual Concordat/Krenn treatment (#334)
+- Tell visual/behavioral expression spec — 5 tell categories mapped to 6 Tier 2 behaviors (#251)
+- Monologue line pool maxLength raised from 160 to 256 chars (soft guidance ≤160)
+- NPC name masking infrastructure — entity-anchored dialogue log with server-side role labels, retroactive name update on learning, NpcColorIndex for stable color assignment
+- Dialogue option keyboard selection (1/2/3 number keys) and numbered option labels
+- Interaction list chrome — background panel, mouse hover highlighting, click-to-interact, pointing hand cursor
+
+### Changed
+- D-061 updated to document unified conversation log architecture from Sprint 14
+- Dialogue options switched from RichTextLabel to Label for reliable VBoxContainer sizing
+
+### Fixed
+- Visual grammar dialogue max-width corrected from "~70% screen width" to 640px per D-076
+- BBCode injection in dialogue log formatting — server-sourced strings now escaped with [lb]
+- Per-frame dialogue log rebuild replaced with dirty flag (performance)
+- dialogue_active lifecycle — now cleared after panel fade completes per D-064
+- PAUSE/UNPAUSE routed through main.gd input recording for bug report replay (#507)
+- WASD input freeze after filing bug report — LineEdit focus not released before queue_free() across CanvasLayers
+- WASD not reactivating after Talk — dialogue_active held for entry_lifetime instead of cleared immediately
+- Recognition chime spam — entity IDs now tracked permanently per room instead of expiring
+- Audio path warning — res://audio/ corrected to res://assets/audio/ in AudioManager
+- world_radial.tscn anchors_preset warning — changed from 15 to 0
+- bug_report_dialog.gd push_warning changed to print for informational message
+
+## [v0.1.13] — 2026-02-20
+
+### Added
+- D-078: Overheard NPC conversation — passive dialogue panel with server-authoritative stochastic word occlusion
+- Sprint 14 "Live" briefings — 22 tickets across server (7), client (3), copy (6), visual (6)
+
+## [v0.1.12] — 2026-02-19
+
+### Added
+- Tier marker components (#93), active tier simulation (#94), tier transition logic (#99)
+- Information tag schema (#138), component-level access control (#139)
+- Line previewer CLI (#193)
+- Sound event system — server pipeline (#124)
+- Close-range stereo audio — client positional 2D (#125)
+- Medium-range visual indicators — fog-edge directional arrows (#126)
+- HashMap ban in simulation crate via clippy (#343)
+- Tracing crate infrastructure — JSON format, tick duration logging (#344)
+- System dependency graph debug command — `--dump-schedule` CLI flag (#346)
+- rng_seed field on ObserverSnapshot for deterministic replay (#527)
+- v0.1 Visual Grammar Document (#303)
+- Placeholder art specification (#252)
+- Spatial layouts: Logistics Hub (#311), Bar (#312), Smuggling corridors (#313)
+- Cultural generation guide — 5-dimension framework for Sova Transit District cultural voice (#189)
+- Sova Texture Appendix — 20-term slang glossary, sensory profile, Meridian self-censorship rules (#302)
+- Contraband specification — unlicensed lattice components, supply chain, street terminology (#321)
+- Sova Station Profile — 6 districts, governance, off-station references (#320)
+- Span Gate Transit Schedule — hourly schedule, maintenance windows, ring operational calendar (#336)
+- Meridian Coverage Map — 10 named zones from Commission-grade to dead air (#335)
+- Character definition schema and both character builds — smuggler + detective (#179, #180, #181)
+- Divergent starting knowledge and relationships per character (#182, #183)
+- Detective institutional chain of command (#322)
+- Contradiction arc design document — reusable FRIEND pattern (#332)
+- Mirror moment design document — 7 core dual-perspective observation triggers (#329)
+- First 5 minutes experience design — systemic opening per character (#259)
+- Opening hook content per character (#260)
+- Knowledge vocabulary for v0.1 content — entity/world categories, prerequisite format (#368)
+- Knowledge state vocabulary — author-facing quick reference (#309)
+- Knowledge fact catalogs — 10 YAML files in content/global/knowledge/, 73 canonical facts
+- D-075 endorsement — archetype dimension review recorded in decisions/content.md
+- Flat NPC memorable trait pass — Pael, Ren, Tev with noise-floor profiles (#307)
+- Environmental text content — 20 items across Terminal, Bar, and Corridors with dual-lens notes (#262)
+- Diegetic insert flavor text — per-character labels and notification strings (#331)
+- News ticker / Meridian feed — 30 lines including batch 44xx recall dual-lens moment (#306)
+- Workplace content pack — The Terminal: 5 NPC dialogue files (#190)
+- Bar content pack — The Last Shift: 3 NPC dialogue files (#191)
+- Smuggling ring content pack — maintenance corridors: coded vocabulary, dual registers (#192)
+- Generation pass expansion — 80 ambient variant lines across all 9 dialogue files (#194)
+- Sprint 13 "Sound" briefings — 9 tickets across server, client, audio, visual teams; full audio architecture + gauntlet expansion + monologue display spec
+
+### Fixed
+- Entity renderer field name bug — `id` vs `entity_id` (#345)
+- Dialogue max-width pixel value — 640px per D-076 (#447)
+- Routine tests missing ActiveSim — 3 of 5 tests passed trivially without the required tier marker
+- `_observer_pos` misleading unused prefix renamed to `observer_pos` (used for sound event filtering)
+- Stale protocol version doc comment "Current: 9" corrected to 10
+- FactionOnly non-numeric `faction_id` attribute now logs a tracing::warn instead of silently denying
+- SOUND_EVENT_ASSETS walk-speed key mismatch — `sfx_footstep_metal` corrected to `sfx_footstep_metal_walk`
+
+### Changed
+- Removed orphaned `SimulationTier`/`LastInteraction`/`ScopeTag`/`ScopeKind` types from tier.rs (unused outside own tests)
+- Sound pipeline documented as intentionally empty in v0.1 (no producers yet, full pipeline wired)
+- Observer test setup now inserts SoundEventQueue resource for integration coverage
+- Added FactionOnly positive test case and Medium-range occlusion TODO
+- Sound indicator colors sourced from Constants instead of duplicated hex literals
+- play_loop() null guard on stream.duplicate()
+- Camera zoom fallback uses Constants.CAMERA_DEFAULT_ZOOM
+
+## [v0.1.11] — 2026-02-19
+
+### Added
+- Sprint 12 "Build" briefings — 50 tickets across server, client, copy, visual, ci teams; production-layer foundations + all v0.1 copy authoring
+- `.tmp/` gitignored repo directory for agent temp files — avoids Bash permission prompts during PR review comment posting
+- `sed -n` blanket permission in shared settings
+
+### Changed
+- All skills renamed to domain-action convention (e.g. `commit`→`git-commit`, `review-pr`→`pr-review`, `gen-audio`→`audio-gen`, `render-sprite`→`sprite-gen`) — 12 renames total
+- `pr-review` skill uses Write tool into `.tmp/` instead of Bash heredocs to `/tmp/`
+
+## [v0.1.10] — 2026-02-19
+
+### Added
+- `project.yaml` — technical project descriptor with version, architecture, simulation, and content model as the canonical version source of truth
+- Scratchpad: asset generation pipeline idea (registry, status tracking, prompt versioning, pre-sprint cohesion)
+- Scratchpad: remote terminal proxy idea for mobile monitoring of Claude Code permission prompts and interactive elements
+- `make perf-baseline` — full plugin stack tick benchmark (50 measured ticks, 5 warmup) capturing per-tick timing, entity counts, process RSS, and shadowcast benchmarks; outputs structured JSON to `tests/perf/baseline.json` with `--compare` mode for regression detection (>20% threshold, D-026 budget check)
+- Michroma font integration (#517) — Michroma-Regular.ttf as game font with +1px tracking FontVariation, global Theme with cyan-white (#E0F7FA) implant text color, IMPLANT_TEXT_COLOR/DIM/PULSE constants
+- Mouse-relative facing and movement (#526, D-054) — mouse position determines facing direction (client-side float), WASD remapped to cursor-relative (W=toward, S=away, A/D=strafe), SET_FACING action sends octant to server, smooth facing indicator rotation
+- Room reset client UX (#502) — amber reset_plate tile type, 0.15s screen flash on room reset, 'Reset Room' interaction verb
+- Auto-checklist progress tracking (#503) — ChecklistEvaluator parses room YAML and evaluates 7 condition types against GameState with latching, ChecklistOverlay renders progress in gauntlet mode only, 48 new tests
+- 4 ambient zone loops: station base, workplace, bar, corridor — SAO-generated organic soundscape with crossfade loop points (#327)
+- 2 footstep SFX: metal walk and run — SAO hybrid with best-transient extraction (#327)
+- `audio-batch` command — batch audio generation from JSON manifests, supports SAO and harmonic synthesis, with `--dry-run`, `--only`, and `--skip-existing` flags
+- `--post` and `--output-ogg` flags on `audio-generate` — chain post-processing (trim, normalize, convert) into a single command
+
+### Changed
+- `push-pr` skill now runs `/commit` first when uncommitted changes are detected
+- Insert open/close now sends explicit PauseSimulation/ResumeSimulation (#518, D-058) — replaces toggle-style pause with idempotent pair
+- Interaction list colors reference Constants.IMPLANT_TEXT_COLOR instead of hardcoded values
+- World radial menu uses theme font instead of ThemeDB.fallback_font
+- Monologue chimes replaced with production-quality manual synthesis — insert-tech aesthetic per D-074, pure sine harmonics with mathematical envelopes (#327)
+
+### Fixed
+- Bidirectional relationship check (#515) — Check 9 tested `target in npc_rels` which missed NPCs with no relationship entries; changed to `target in self.npcs`
+
+## [v0.1.9] — 2026-02-18
+
+### Fixed
+- `make game` now builds client before launching — was missing `build-client` dependency, causing class_name registration failures after `make clean`
+- `build-client` uses `--import --quit` instead of just `--quit` — ensures `.godot/` cache and `global_script_class_cache.cfg` are created from scratch
+- `make clean` preserves `client/.godot/` directory (clears contents only) to avoid Godot startup issues
+
+### Added
+- `--description TEXT` flag for `ticket create` CLI — previously required raw SQL workaround to set ticket descriptions
+
+### Changed
+- UI audio assets revised — monologue chimes re-generated (0.8s, insert-tech aesthetic), fog_recognition re-generated (was silent), all 8 assets normalized to 44.1kHz stereo LUFS -16 (#453)
+- review-pr skill: explicit verdict rules — critical/warning → REQUEST_CHANGES, suggestion-only → APPROVE
+
+### Added
+- `make golden-diff` + `make golden-update` targets (#486) — developer workflow for golden file comparison and regeneration; safe restore on cargo failure
+- Gauntlet checklist YAML schema (#497) — 7 condition types evaluable from ObserverSnapshot, per-room checklists for 3 rooms, `make checklist-validate` and `make checklist-generate` targets, wired into `pre-pr-content` gate
+- Gauntlet room timer + personal bests (#496) — GauntletHUD shows TIMER: MM:SS (PB: MM:SS), starts on room entry, resets on room change, persists stats to user://dev/gauntlet-stats.json, session summary on disconnect, hidden in non-gauntlet mode
+- WRONG button F12 MVP (#495) — bug report capture: pause sim, show modal prompt, save snapshot.json + render.txt + description.txt to user://bug-reports/, Esc to cancel
+- GameState.room_id and gauntlet_mode fields — parsed from ObserverSnapshot, enabling gauntlet UI
+- BUG_REPORT action in InputMapper (F12 binding) with SimBridge wire guard (client-only)
+- 24 new anti-tedium tests — GauntletHUD lifecycle (16: timer, PB, visibility, room change, session tracking) + BugReportDialog (8: pause/unpause, wire guard, text render, edge cases)
+- whatsinagame starter kit — reusable multi-agent team bootstrap for any project (3-tier profiles, 18 skills, 16 agent archetypes, stakeholder personas, ticketing DB, decision tracking)
+- Domain-action naming convention for skills documented in create-skill guide
+- `gauntlet` feature flag (default-on) — allows stripping Gauntlet test world from release builds with `--no-default-features`
+- `EXPECTED_ENTITY_COUNT` and `RESET_PLATE_STABLE_IDS` constants — entity counts derived from StableId ranges instead of hardcoded values
+- Debounce exact-boundary test for room reset (tick 9 rejected, tick 10 accepted)
+- Reset plate StableId verification in `stable_id_ranges_match_spec`
+- Runtime content test (`content_runtime.rs`) separated from structural loading tests
+- Client P2 tests (#492) — 16 gdUnit4 tests for camera (smoothing, zoom, viewport, follow, no-pan), entity alpha/color (peripheral, forward, NPC color, player constant), UI (monologue, interaction, inventory, dialogue, pause, fog blob, fog z_index)
+- Client P3 tests (#493) — 12 gdUnit4 tests for z-layer ordering (floor/ysort/fog/UI), entity lerp (snap, converge, LERP_SPEED=12.0), Tyre additions (recognition, facing, delta scaling, blob removal)
+- Anti-tedium regression tests (#494) — 5 tests: F12 no-crash guard, no queued input, gauntlet UI hidden in default/normal snapshot/multi-tick modes
+
+### Changed
+- Room reset API consolidated to `plan_reset` only — `execute_reset` removed (was a maintenance trap; production uses Commands via `plan_reset`)
+- `room_at()` documented with z-range and corridor overlap assumptions
+- TCP runtime test now has 10s read timeout and registers player in EntityRegistry
+
+### Removed
+- Dead `RoomMember` component from reset.rs (defined but never used)
+- Protocol v8: dialogue_response field decoding (DialogueResponseEvent with line_id, text, speaker_entity_id) from server #305/D-028
+- Test client binary scaffolding (#480) — standalone crate at `tooling/test-client/` with CLI (--connect, --replay, --text, --json, --quiet, --golden, --ticks), exit codes (0/1/2), golden file JSON diff, JSONL replay loader
+- Snapshot text renderer (#481) — `format_snapshot_text(&ObserverSnapshot)` pub-exported from server crate, entity labels as kind:entity_id sorted by distance, room name stub, 10 unit tests
+- Sprint 9 (Gauntlet) briefing files — server, client, CI, audio, joint — 23 tickets across 4 teams
+- Weapon aim lock audio (`sfx_weapon_aim_lock.ogg`) — clinical targeting confirmation tone for weapon aim state (#440)
+- Stance change audio (`sfx_stance_change.ogg`) — subtle mechanical click for stance toggle feedback (#440)
+
+### Fixed
+- MessagePack int_64 encoder dead code branch (#516) — `-(1 << 63)` overflowed making int_64 branch unreachable; negative values beyond int_32 now correctly encode as 0xd3 instead of 0xcf
+- Cross-encoder fixture pipeline hardened — encode failures now exit non-zero instead of writing empty .msgpack files (#475 review)
+- GDScript fixture test no longer silently skips on missing/empty fixture dir — asserts instead (#475 review)
+- GDScript fixture generator covers all PlayerAction variants (added MoveSouth, MoveEast, MoveWest, Unpause, ToggleStanceDown, WalkAway)
+- `make pre-pr` now checks GDScript fixture staleness alongside Rust fixtures
+- Protocol version bumped from 7 to 8 to match server — fixes 5 test failures from version mismatch
+- Interact action encoding changed from unit variant to struct variant to match server's PlayerAction::Interact { target_entity_id, verb }
+- Monologue duplication test (test_monologue_not_duplicated_after_consumption) fixed — was using poll_snapshot() which doesn't consume _last_snapshot in test mode
+- `make pre-pr` target — full pre-PR verification chain: lint → build → test → content validation → fixture staleness (#460, #465)
+- Branch-specific pre-PR variants: `make pre-pr-server`, `make pre-pr-client`, `make pre-pr-content`
+- Content cross-reference validation (9 checks) — canonical_id uniqueness, relationship targets, location slugs, dialogue locations, fact_ids, triangle membership, npc_count, dialogue line_ids, bidirectional relationships (#464)
+
+### Fixed
+- Dialogue schema missing `focused` (mood) and `greeting` (situation) values added in Sprint 7-8 content
+- Speaker wire ID silent fallback — dialogue now warns and skips when target entity missing from registry (was silently using 0)
+- Cross-plugin system ordering — trigger_recognition_monologue now runs after detect_anomalies (latent determinism bug)
+- Walk-away ordering — process_walk_away now runs after process_talk_interaction (prevents same-tick race)
+- ActiveDialogue overwrite — new Talk while in existing dialogue now emits IncompleteInteraction before replacing
+- Server-side Talk range check — handle_talk now enforces CLOSE_RANGE before setting TalkRequest (was client-only)
+- ExamineNpc label collision — VerbKind::ExamineNpc now uses "Examine NPC" label (was "Observe", same as generic Observe)
+- Dead conditional in main.rs collapsed (both branches were identical)
+- WalkAway variant added to all_player_action_variants_roundtrip serialization test
+
+### Changed
+- DialogueCooldownTracker.used changed from Vec to BTreeMap for O(log n) lookup (D-041 compliance)
+- MonologueState.shown_ids changed from Vec to HashSet for O(1) contains check (was O(n) per tick)
+- Secret trust tier documented as unreachable with TODO for Phase 2 KG-gated unlock
+
+### Added
+- Determinism test: different_seed_produces_different_replay — exercises SimRng via dialogue weighted selection
+- Dialogue selection pipeline (#305, D-028) — 4-layer filtering engine: access tier from KG relationship, situation derivation from game state, trust tier, weighted topic+mood scoring via SimRng. Full Talk verb → selected line → ObserverSnapshot pipeline with cooldown tracking
+- ContentSlug component (#452) — stable content identity from YAML (e.g. "kael-davan") independent of runtime Entity handles, for knowledge graph interaction memory across save/load
+- Walk-away KG recording (#427, D-064) — IncompleteInteraction knowledge events with Talk/Confront type, ActiveDialogue tracking, walk-away detection clears dialogue and records in KG
+- Anomaly detection for urgent recognition (#450, D-060) — AnomalyMarker flags PersonOfInterest/Contradicted entities for 0.3s cognitive delay instead of 0.6s normal
+- Recognition monologue during cognitive delay (#451, D-060) — monologue fires at delay START (grey blob phase), not completion. v0.1 fallback lines, anomaly prioritization, cooldown tracking
+- Server --test-mode, --port, --seed CLI flags (#459) — LISTENING:{port} stdout signal, OS-assigned ports, deterministic seed override, stderr-only tracing
+- Determinism gauntlet test (#466) — 20-tick replay determinism regression test with movement, stance, pause/unpause exercise
+- Pause guard test suite (#461-463, #468) — 7 tests covering movement, unpause, roundtrip, stance, interact, batch, tick_rate during pause
+- EntityRegistry lifecycle tests (#469) — stale mapping, re-register, unknown unregister edge cases
+- Boundary value encode/roundtrip tests (#471) — 41 values across all MessagePack integer format boundaries
+- Encoding asymmetry tests (#473) — Rust decoder accepts GDScript-style signed encodings for unsigned fields
+- Boundary fixture generation (#472) — 14 raw + 5 snapshot fixtures at integer format boundaries
+- Malformed batch rejection test (#479) — truncated, garbage, and mixed payloads rejected atomically
+- Per-fix determinism unit tests (#467) — equidistant NPC ordering, visible tile sorting, same-tile mover resolution
+
+### Fixed
+- Determinism: visible_ids HashSet → BTreeSet for stable iteration order (#456)
+- Determinism: visible entities in snapshot sorted by entity_id (#457)
+- Determinism: movers sorted by Entity bits in validate_movement (#458)
+- Pause guard blocks all actions except Pause/Unpause while paused (previously only blocked movement)
+
+### Changed
+- Protocol version bumped from v7 to v8 (dialogue_response field in ObserverSnapshot)
+
+### Added
+- AudioManager autoload (#255, D-068/D-069/D-073) — 5-bus architecture (Music, Ambient, WorldSFX, PlayerActions, UISounds), directory-scan asset registry, spatial/non-spatial playback, audio dip profiles (dialogue, confrontation, listening_focus) with low-pass filter sweep, zone crossfade stub
+- Dialogue response selection (#435, D-061/D-062) — structured options with response_id, priority sorting, max 3 visible, invisible locked options, RichTextLabel for BBCode support
+- Walk-away mechanic (#437, D-064) — WASD triggers WalkAway input during dialogue, 300ms fade, dialogue_active flag gates movement, re-show on server interrupt
+- Confrontation text styling (#436, D-063) — italic first-person options, 1.5s monologue beat with dialogue dim to 70%, audio dip via AudioManager, walk-away cancels in-flight beat
+- MessagePack boundary value tests (#470) — 41 values (25 positive, 16 negative), encode-only header verification, roundtrip, Rust-style unsigned decode overlap tests
+- Client P0 regression tests (#477) — monologue carry-forward (Bug #5), camera stability during pause (Bug #2)
+- Client P1 tests (#478) — fog shader state (4), entity lifecycle (2), pending recognition blob (1)
+
+### Changed
+- Fog byte magic numbers replaced with named constants (#476) — VIS_HIDDEN/PERIPHERAL/FORWARD, EXP_UNEXPLORED/EXPLORED/VISIBLE in FogState
+- Dialogue options now carry structured {text, response_id, priority, confrontation} instead of plain strings
+- Protocol v7 dialogue decode validates and skips malformed options
+
+### Added
+- QA test architecture workshop complete — 3-round, 7-agent workshop producing 60 tickets (epic #455): Gauntlet test world (7 rooms, 48 entities), test client binary (tooling/test-client/), determinism fixes, content validation, make pre-pr pipeline, 38 client tests, anti-tedium features, human tester workflow
+- Workshop skill updated — agents now write output files to disk instead of sending messages, fixing documenter access
+- Camera anchor test suite — 10 gdUnit4 tests verifying camera init, smoothing cycle, and player tracking
+- Entity position lerping — framerate-independent exponential smoothing so entities slide between tiles instead of snapping
+
+### Fixed
+- Server never sends snapshots — blocking TCP read in receive_bridge_inputs stalled the entire bevy Update schedule; switched to non-blocking I/O with WouldBlock handling
+- Camera doesn't center on player at startup — Camera2D smoothed_camera_pos starts at (0,0); now disable smoothing during init, snap to player, re-enable after first anchored frame
+- Player moves while game is paused — movement commands now discarded when TickRate is Paused (pause/unpause still process)
+- Spacebar only pauses, doesn't toggle — added UNPAUSE action with toggle logic based on tick_rate state
+- MessagePack encodes tick 128 as -128 — off-by-one in signed int boundary checks (<=128 instead of <128) across int8/16/32/64 branches
+- Monologue/dialogue lost on snapshot overwrite — one-shot events now carried forward when a newer snapshot replaces an unconsumed one
+- Fog shader white screen on load failure — ColorRect defaults to transparent, shader load failure logged instead of crashing
+- Fog desync during camera smooth pan — fog rect now tracks camera position instead of player position
+
+### Changed
+- Server game loop throttled to ~20 ticks/sec (50ms frames) — non-blocking TCP loop no longer spins; remaining frame budget available for NPC AI
+- Hold-to-move input model — movement polled each frame with stance-based throttle (Sprint=200ms, Walk=400ms, Careful=600ms, Crouch=800ms) and composite diagonals (W+D → northeast)
+- D-053 updated with client throttle rates and input model documentation
+
+### Added
+- Dialogue box UI skeleton (#434, D-061) — bottom screen, max 20% height, ~65% width, NPC speech + max 3 response options, insert-styled colors, WASD walk-away with 300ms fade, no close button, diegetic on InsertOverlay z-layer 6
+- Fog entity visualization (#431, D-059/D-060) — cognitive delay rendering: sonar-style sound pings (3 concentric rings, 1.5s fade), unrecognized grey blobs with 0.8s breathing pulse, D-033 color transition at 50% recognition progress, ±0.5 tile position drift, FogEntities node at z:950
+
+### Changed
+- Client protocol version bumped from 6 to 7 (pending_recognitions decode for cognitive delay)
+- GameState: current_dialogue and pending_recognitions fields wired from ObserverSnapshot v7
+- Scene tree: DialogueBox added to InsertOverlay, FogEntities at z:950 between fog shader and InsertOverlay
+- Test mode: mock dialogue (Kael NPC, 3 options) and mock cognitive delay entity (6-tick recognition cycle)
+
+### Added
+- Archetype evidence presentation spec (#443, D-065/D-034/D-033) — detective case file vs smuggler notebook design document: item definitions, knowledge graph presentation, contradiction markers, THE FRIEND arc walkthroughs, systems interaction map, authoring guidelines
+- Cognitive delay system (#423, D-060) — CognitiveDelay component buffers perception events before emitting KnowledgeEvents (0.6s base / 0.3s urgent at 10 tps), pending_recognitions in ObserverSnapshot v7 for client fog entity visualization, cancellation on entity LOS exit
+- ListeningFocus eavesdrop system (#426, D-053) — stationary_ticks tracking for eavesdrop positioning bonus, 30-tick threshold (20 for Careful stance), Sprint blocks accumulation, registered after validate_movement
+- YAML content loader with hot-reload (#326, D-028) — LinePool system parsing dialogue/monologue YAML into BTreeMap-indexed pools, 4-layer query filtering (access > situation > trust > topic+mood), timestamp-polling hot-reload (dev-only), graceful failure preserves previous content
+- Line pool format specification (#308) — formal spec at docs/architecture/line-pool-format.md defining YAML structure, tag enums, 4-layer filtering pipeline, prerequisite-to-KG mapping, ID format, and Rust loader interface
+- InteractionMemory KG schema design (#442, D-064) — design doc at docs/architecture/interaction-memory-schema.md extending FactKnowledge with interaction tracking, 5-state InteractionState enum, monologue prerequisite extension, NpcTolerance reconciliation
+- Audio discussion decisions D-067 through D-074: recognition chime timing, 5-bus architecture, audio dip profiles, confrontation as cognitive vulnerability, monologue chime placeholder strategy, universal conversation murmur, zone crossfade, hybrid audio generation
+- Asset pipeline documentation system (docs/assets/) with category-based index, sonic palette, and generation templates for audio, visual, and video pipelines
+- Stable Audio Open connector and post-processing wrappers (audio-generate, audio-health, audio-post) with timeout handling for 11GB VRAM constraint
+- gen-audio skill with prompt assembly system (sonic palette prefixes + category templates + asset descriptions)
+- 6 interaction UI audio assets (#440): cursor_hover, weapon_aim, implant_open, fog_recognition, sfx_monologue_chime, sfx_monologue_chime_urgent — generated via SAO, needs duration trimming (#453)
+- Dialogue/confrontation ambient dip implementation spec with full Godot AudioBus tween code
+- Synthesis tooling (tooling/synth_ui_sounds.py) for programmatic insert-tech sound generation
+
+### Changed
+- Protocol version bumped from 6 to 7 (pending_recognitions field in ObserverSnapshot)
+- MessagePack fixtures regenerated for protocol v7
+- Monologue trigger system uses .values() iterator (clippy fix)
+- Monologue schema: relationship prerequisite now requires target and state fields
+- 389 tests total (70 new) — cognitive delay pipeline, line pool loader, ListeningFocus, content watching, serialization
+- Renamed asset-gen skill to gen-image for consistent gen-* naming pattern
+- Client protocol v6 bridge — decode player_stance (4 variants) and player_inventory from ObserverSnapshot, TOGGLE_STANCE_UP/DOWN input actions, 25 gdUnit4 tests
+- Three-scope z-layer rendering pipeline (D-049) — world z:0-900 inside CanvasGroup, insert overlay CanvasLayer 10, UI CanvasLayer 20, modal CanvasLayer 30. Y-sort contract enforced, reserved VFX/airborne/lower-floor ranges documented
+- Cursor state machine (#429, D-056) — 4 states (Default/EntityHover/ObjectHover/WeaponAim), 150ms transitions, insert-styled geometric shapes
+- Fog shader rebuild (#430, D-059) — 5-layer fragment shader with animated Perlin noise, CanvasGroup compositing, FogState autoload for visibility/exploration textures
+- Entity interaction list (#432, D-057) — vertical multi-verb menu, insert-styled, sprint suppression, diegetic toggle
+- World radial menu (#433, D-058) — 2 spokes (Observe + Insert), drag-release and click-click input, 60-degree acceptance zones
+- Inventory UI (#438, D-065) — 3x3 grid, 40x40px slots, 1-9 hotkey selection
+- Stance indicator (#439, D-053) — color-coded HUD text, C/X keybinds
+- Architecture docs: z-layer gap analysis, fog shader spec, flying taxi feasibility analysis
+
+### Changed
+- Scene tree restructured: Entities z_index 3->0 (critical y-sort fix), FloorObjects->10, YSortGroup->100, Overhead->300, FogOverlay->900, ModalLayer added
+- constants.gd rewritten with three-scope z numbering and full reserved range documentation
+- Fog renderer replaced: TileMapLayer-based fog_renderer.gd deleted, replaced by shader-based fog_shader.gd + fog.gdshader
+
+### Added
+- ObserverSnapshot v6 wire protocol (#449) — player_stance (MovementStance) and player_inventory (Vec\<InventoryItem\>) fields with serde defaults for backward compatibility
+- Stance system (#417) — Sprint/Walk/Careful/Crouch movement stance with tick-based speed (1/2/3/4 ticks per move), monologue rate multipliers (40%/100%/150%/100%), PlayerMoveCooldown component, ToggleStanceUp/Down player actions
+- TilePresence posture layers (#420) — Standing/Prone/Seated/Fixture occupancy layers enabling same-tile coexistence (e.g. seated NPC + standing player), layer-based collision in validate_movement
+- ObjectType component (#421) — Readable/Container/Terminal/Door/Pickup/Furniture types with Phase 1 verb sets computed from type + proximity range
+- Phase 2 verb filter (#422) — KG-gated observer-side verb processing: POI priority flips (D-060), Confront injection at KnowsDetails+ confidence, contradiction marking, archetype-specific label relabeling (Smuggler sees Move/Stash, Detective sees Scan/Flag on containers)
+- CharacterArchetype component — Smuggler/Detective archetype for Phase 2 verb label differentiation (D-057)
+- VerbKind::Confront — Phase 2 only verb injected when observer has KnowsDetails+ on an NPC at close range
+- Smuggler inventory system (#424) — CarriedBy(StableId) component, Take/Place verbs, 9-slot (3x3 grid) capacity, auto-slot assignment, info boundary enforcement (carried items invisible to other observers)
+- MovementProfile component (#418) — per-archetype default stance (smuggler=Walk, detective=Walk), applied on spawn, factory methods for future archetypes
+- Sprint interaction buffer suppression (#419, D-055) — sprint stance explicitly clears interaction buffer, no verbs computed or sent during sprint, anomaly monologue pipeline unaffected
+- Sprint anomaly double-take monologue (#428, D-055) — SprintAnomalyQueue component detects Contradicted entities during sprint, fires delayed retroactive monologue after ~1.5s ("Wait — something wasn't right back there"), first-in-wins queue semantics, 3 hardcoded v0.1 lines
+
+### Changed
+- Protocol version bumped from 5 to 6 (stance, inventory, ObjectType, verb system fields)
+- MessagePack fixtures regenerated for protocol v6
+- Input processing queries expanded for stance and cooldown components with backward-compatible Option wrapping
+- Observer pipeline queries expanded for Stance and CharacterArchetype components
+- NearbyInteraction carries object_type and contradicted fields for Phase 2 context
+- BridgePlugin system ordering: process_sprint_anomaly_monologue runs after trigger_monologue, compute_observer_snapshot runs after anomaly processing
+- Player spawn includes MovementProfile, Stance, PlayerMoveCooldown, and SprintAnomalyQueue components
+- 331 tests total (131 new) — comprehensive QA coverage across stance, occupancy, Phase 2 verbs, sprint suppression, inventory, anomaly monologue, and wire format
+
+### Added
+- D-066: Dual-scale grid — 0.5m simulation tiles for stealth granularity, 1m visual tiles for proportional art (2x retina factor). All world geometry 2x2 sim tile minimum so cover/LOS maps 1:1 with visuals. Amends OQ-01.
+- Sprint CLI (`db/connectors/sprint`) — unified sprint lifecycle management with 5 subcommands: status, start, stop, start-work, prepare. Auto-detects sprint from DB state and team from git branch. Guards prevent activating unplanned sprints.
+- Shared permission settings in `.claude/settings.json` — git, ticket/sprint CLI, make, tea, and core skills pre-approved across all worktrees. Deny rules block destructive operations.
+- Decisions D-053 through D-065 from Control & Interaction Workshop — formalized interaction verb system, contextual actions, NPC awareness model, and related design decisions
+- Sprint 6 Touch briefings for server, client, copy, and joint teams
+- Control & Interaction Workshop outputs — full workshop notes and outcomes
+- Smuggler inventory item specs for transit district (#441)
+- Start-workshop skill for multi-agent design workshops
+
+### Fixed
+- Added worktree boundary rules to CLAUDE.md — agents must stay within the git root, no navigating to sibling worktrees or above the repo
+- Plan-sprint skill now enforces worktree-relative paths in generated briefings
+- Worktree-update skill now discovers branches dynamically via `git worktree list` instead of relying on hardcoded branch names — fixes missed branches like `planning`
+
+### Changed
+- Start-sprint and plan-sprint skills updated to use sprint CLI instead of manual multi-query workflows
+- Permission syntax migrated from deprecated `:*` suffix to modern space-wildcard format across all worktrees
+- Internal monologue trigger system (#414) — enter_location fires on first tick, time_idle fires after 100 ticks of no movement, 300-tick cooldown, dedup within session, random line selection from content pools via ChaCha20 RNG
+- MonologueEvent in ObserverSnapshot v5 — current_monologue field carries id, text, and display duration across the IPC bridge
+- Client monologue display wiring — protocol v5 decoding, GameState extraction, HUD display pass-through
+
+### Fixed
+- NPC spawn missing Interactable component (#413) — NPCs spawned from content and proof room now have Interactable, enabling E-prompt detection
+- PlayerAction::Interact was a no-op (#415) — changed from unit to struct variant with target_entity_id and verb fields, server logs interaction data
+
+### Changed
+- Protocol version bumped from 4 to 5 (MonologueEvent field, Interact variant change)
+- MessagePack fixtures regenerated for protocol v5
+
+### Changed
+- UIStrings YAML parser now handles arbitrary nesting depth and inline comments — adapts to copy team's restructured ui-strings.yaml with multi-level sections (relationship_states, health_values)
+- HUD uses new YAML keys: `hud.perception_mode_prefix`, `hud.time_prefix`, `hud.health` (empty prefixes display values directly)
+- Interaction prompt keybind hint ("E") hardcoded instead of loaded from YAML — keybinding is not copywriter text
+
+### Added
+- Pre-commit FactId validation hook (#393) — grep-based check validates fact_id references in content YAML against canonical knowledge catalogs; advisory mode when catalogs are stubs, enforcing mode when populated
+- Pre-commit hook infrastructure — `.config/hooks/` with modular dispatcher, `make setup-hooks` target, `core.hooksPath` config for worktree-safe hook installation
+- `make check-fact-ids` target for manual fact_id validation
+- UIStrings autoload with YAML-based UI string loading (#409) — minimal YAML parser, `get_text()` lookup with fallback-to-key
+- HUD and interaction prompt labels now loaded from `client/data/ui-strings.yaml` instead of hardcoded strings
+- Character voice speech patterns (#310) — sentence-level execution spec for smuggler and detective covering contractions, punctuation, stress markers, vocabulary, verbal tics, and authoring checklist
+- NPC authoring style guide (#379) — 954-line handbook: tier budgets, 9 NPC patterns, dialogue/monologue rules, tag taxonomy, dual-lens coordination, Krenn/Sova culture, FRIEND phase mapping, validation checklist
+- UI microcopy (#409) — 72 YAML strings for client integration: interaction verbs, relationship states, HUD labels, perception modes, notifications, knowledge panel, tutorial prompts
+- Kael Davan FRIEND pack (#297) — 86 hand-authored lines across 3 locations, 5-phase relationship arc with contradiction scene, dual-lens notes
+- Sera Venn FRIEND pack (#298) — 75 hand-authored lines at The Last Shift, trust-gated gossip, avoidance contradiction, contaminated trust arc
+- PC-as-NPC content (#401) — 70 authored items enabling second-playthrough recognition (D-039 wow moment #4)
+
+### Changed
+- Moved ui-strings.yaml from content/campaigns/_meta/ to client/data/ for direct Godot client loading
+
+### Fixed
+- Fact ID format collision across FRIEND content — normalized 73 flat IDs to dotted category.topic format, fixing broken detective evidence chain from Sera to Kael observations
+- Entity ref format inconsistency — normalized underscore format to npc:hyphenated across ~15 monologue references
+- Phase tag inconsistency between FRIEND packs — standardized to phase-N format, added missing phase-2 tags to Kael ring ops lines
+- Detective monologue gap for Kael — added 7 observation lines (7 → 15 total), added mood tags and bar_evening situation to Kael bar content
+- Hoshe QA briefing updated with integration test coverage priorities — test harnesses, dedicated client-server test map, edge case focus
+- Sprint 5 "Live" team briefings — copy (6 tickets), client (2), CI (1), joint coordination for content-at-scale sprint targeting FRIEND packs, voice patterns, NPC style guide, PC-as-NPC authoring, UI microcopy, FactId validation
+- Live server mode (`make game`) — single command builds server, launches client with TCP connection, auto-kills server on exit; `make stop` helper for manual cleanup
+- `SR_LIVE=1` environment variable switches SimBridge from test mode to real TCP server connection
+- TileKind in wire protocol (#412) — server sends Floor/Wall/Door/Object per visible tile, client renders walls and floors in live mode
+- Input roundtrip integration test (#411) — spawns real server, connects via TCP, validates full movement and interact pipeline
+- Debug logging for received player inputs on server (visible with `RUST_LOG=debug`)
+
+### Fixed
+- Interaction prompt target+verb data now attached to Interact action in game loop (#405) — was TODO stub, server receives `{target_entity_id, verb}` payload
+- Player entity detection uses `kind.variant == "Player"` instead of hardcoded `entity_id == 1` — fixes "player not found" warnings when connected to real server (which assigns different IDs)
+- Movement keys now work in live mode — client was sending millisecond timestamps as input tick, server only processes ticks <= current frame counter; now uses server tick from latest snapshot
+- Entity-to-tile alignment in live mode — server sends tile-center render coords (tile 16 → 16.5), entity renderer now floors to tile index before positioning
+
+### Added
+- Content loader Phase 2 (#408) — 2-phase spawn pipeline loads real YAML content into ECS entities: enums, entity attributes, pools, templates, triangles, NPC profiles with Want/Tolerance/Contentment/Personality/Tells/Skills axes plus cross-reference resolution for Secrets, Relationships, Information, and DailyRoutine
+- Global enum YAML files (#387) — 9 enum definitions (situations, topics, moods, triggers, access-tiers, trust-tiers, activities, patterns, motivations) from D-035 taxonomy
+- Entity attributes YAML (#388) — 16 canonical knowledge graph attribute keys from D-024 with A7 workshop updates
+- Seed-time pools (#389) — 5 single-candidate pools for deterministic v0.1 testing
+- Social site templates (#390) — 3 templates (logistics-hub, bar, smuggling-ring) with role slot definitions per D-025
+- Triangle YAML files (#391) — 5 v0.1 triangles (3 active fork, 2 passive) per D-024 workshop synthesis
+- Seed configuration schema design (#394) — design document defining game-start randomization: FRIEND selections, pool draws, template assignments, entanglement config, ChaCha20 RNG protocol
+- YAML to RON converter tool (#403) — build-time converter in tooling/content-converter/, runs via `make content-ron`
+- Line previewer CLI (#407) — 4 subcommands (dialogue, monologue, coverage, sequence) for content authors to test line selection without running the full game
+- Happiness added to WantKind enum — Harek remapped from Safety to Happiness
+
+### Fixed
+- Dialogue-pool schema corrected to use arrays for situation/topic/mood per D-035 (were incorrectly single strings)
+- NPC want.primary changed from narrative strings to WantKind enum keywords — fixes silent Want component drop at spawn time
+- Schema enum constraint added to npc-profile.schema.json for want.primary validation
+
+### Added
+- Sprint 4 "Feel" team briefings — copy (8 tickets), server (9), client (1 carry-over), CI (1), joint coordination
+- Interaction prompt system (#405) — server-driven "E - Talk" prompt decoding v4 nearby_interactions with nested VerbOption structs, fade animation, extensible get_interaction_target/get_selected_verb interface for future radial verb menu
+- Art direction & mood board workshop (3 rounds + closing) — 4-agent team establishes visual identity, 16 art direction principles, 9 mood board images, 10 candidate decisions (D-042–D-051)
+- 3D-to-2D sprite render pipeline (`client/tooling/sprite_renderer/`) — Godot @tool scene renders textured 3D models at "the angle" (-72.5deg ortho) from 4 cardinal directions at 1024/256/64 resolutions with outline applied at working resolution
+- `/render-sprite` skill — CLI wrapper for the render pipeline with headless import step
+- Pipeline POC: Era 1 institutional wall + bar green wall textures generated via Nano Banana and rendered through full pipeline
+- PerceptionQuery trait and ActivePerceptionMode resource — abstraction layer for D-017 perception mode swapping (NaturalVision default implementation)
+- VisibilityGeometry intermediate resource decoupling FOV computation from entity filtering
+- Client-side PROTOCOL_VERSION enforcement — snapshot decoder rejects version mismatches with error log
+- POI verb priority test in observer pipeline — asserts both verb kind and priority values end-to-end
+
+### Changed
+- Observer pipeline decomposed into two-stage system: compute_visibility_geometry (geometry) → compute_observer_snapshot (entity filtering + assembly)
+- POI verb priority adjustment moved from simulation phase (interaction.rs) to perception phase (observer) — fixes D-010 information boundary violation
+- compute_nearby_interactions no longer reads KnowledgeGraph — determines verb availability by proximity only, verb priority adjusted by observer
+- compute_nearby_interactions scheduling moved from SimulationPlugin to BridgePlugin for explicit ordering with geometry and observer systems
+- Client test snapshot updated to v4 format (Protocol.PROTOCOL_VERSION, tick_rate replaces paused)
+
+### Added
+- Content validation tooling — `make validate-content` validates campaign YAML files against JSON schemas, maps files by directory context
+- Entity::to_bits() roundtrip test — guards against bevy version changes silently breaking wire IDs
+- TickRate switch mid-accumulation test — verifies Half→Full→Paused→Half transitions preserve accumulator state
+- Tick rate scaling system (#406, D-052) — Full/Half/Paused rates with fractional accumulation, SetTickRate player action, replaces binary pause flag
+- Proximity detection and interaction verbs (#404, D-060) — compute_nearby_interactions system with Manhattan distance ranges (close ≤2, mid ≤5), context-sensitive verb computation (Talk, Observe, Examine), PersonOfInterest priority flip, NearbyInteraction in ObserverSnapshot v4
+- Content directory skeleton (#385, D-057) — district-as-atomic-pack layout with Sova Transit first district, 17 NPC stubs, 3 locations, 5 triangles, dialogue/monologue pools, factions, knowledge catalogs, enum definitions
+- Content schema definitions (#386) — 8 JSON Schema files (draft 2020-12) for district, location, npc-profile, dialogue-pool, monologue-pool, triangle, routine, fact-catalog validation
+- PROTOCOL_VERSION constant in bridge types — versioning strategy documented (subprocess IPC, serde defaults for field evolution)
+- Campaign, system, station JSON schemas for hierarchical content validation
+
+### Fixed
+- Test suite aligned with server v4 protocol enforcement — all hand-built snapshots include version field, verb priorities 1-indexed, ExamineNpc label corrected to "Observe"
+- E2E proof tests resilient to entity ordering — player found by kind instead of array position, wall-hides test checks specific NPC position instead of total count, supports 3-NPC proof room layout
+- Wire entity_id now uses StableId consistently across observer, observation, interpretation, and interaction systems (was Entity::to_bits() in some paths)
+- Restored system/station/district hierarchical fields in district metadata (incorrectly removed during canonical_id cleanup)
+- Unregistered entities in observer/interaction now log tracing::error instead of silently falling back to Entity::to_bits()
+
+### Changed
+- NearbyInteractionBuffer refactored from global Resource to per-entity Component on PlayerCharacter — multiplayer-ready (D-009)
+- Observer module split into mod.rs (244 lines) + tests.rs (480 lines) — reduces module complexity
+- Content directory restructured from flat districts/ to hierarchical campaigns/main/systems/krenn/stations/sova/districts/transit/ — path mirrors canonical IDs, glob-based discovery, multi-campaign/DLC ready
+- Content manifest (content.yaml) rewritten for glob-based district discovery
+- District identity fields (system, station, district) now derived from directory path — removed from district.yaml required fields
+- NPC canonical_id schema accepts district-scoped IDs (npc:transit.kael-davan) for cross-district uniqueness
+- ObserverSnapshot protocol bumped to v4 — adds nearby_interactions field, tick_rate replaces paused field in GameTime
+- NearbyInteractionBuffer.interactions is now private with take() accessor (no per-frame clone)
+- NearbyInteraction.distance changed from f32 to u32 (matches manhattan distance)
+- Missing PlayerCharacter in input processing now panics instead of silent no-op
+- Verb sort uses (priority, kind) tuple for deterministic ordering at equal priority
+- Unregistered entity in knowledge events triggers debug_assert + error (was warn)
+- District schema: canonical_id is now optional (derived from directory path at load time)
+- Skills trimmed for CLAUDE.md deduplication — search-docs (-48%), ticket (-17%), review-pr (-35%) now reference CLAUDE.md for basics instead of repeating them
+- Review-pr reviewer profiles extracted to `references/reviewer-profiles.md` for progressive disclosure
+
+### Removed
+- Dead generate_snapshot function in bridge/mod.rs — superseded by compute_observer_snapshot
+- content/global/regions/ directory — region data absorbed into system.yaml metadata
+
+### Added
+- Dual Lens Authoring Guide — 7-chapter reference for writing content that works for both smuggler and detective perspectives (D-027, D-028, D-032, D-034, D-035)
+- THE MIRROR pattern spec — transparency-as-contrast NPC design with Naia Tamm reference implementation and generator template
+- Smuggler voice card — register parameters, 5 voice anchors, 4 anti-patterns, paired comparison examples, display constraints, authoring checklist
+- Smuggler moral arc spec — 4-phase trajectory (Comfort, Doubt, Reckoning, Compromise), FactId gates, monologue trigger rules, Kael intersection mapping
+- PC-as-NPC unified spec — starting knowledge/relationship graphs, tell inversion, orientation monologue, 9-step conversion checklist, v0.1 smuggler + detective briefs
+- Triangle 1 Hub Power Volume Escalation fork — 3-path smuggler decision (escalate/stabilize/mediate), ~41 authored dialogue lines, NPC state change tables
+- Content directory structure design doc — runtime content/ layout, canonical ID format, 8 JSON Schema specs, 3-tier validation pipeline, migration path from wiki
+- Interaction verb spec — 7 v0.1 verbs (Move, Look, Monologue, Examine Object, Examine NPC, Talk, Overhear), priority resolution, server pipeline architecture
+- v0.1 wow moments checklist — maps all 6 D-039 moments to content deliverables, tickets, dependencies, completion status
+- Nils Davan off-stage NPC stub — ring coordinator, GHOST + HANDLER pattern, lattice message design, relationship map
+- NPC pattern/motivation mapping applied to all 18 NPC wiki pages with composition reads
+- Structured NPC data model (#86) — replaced stub string/f32 fields with typed enums and integer types for D-010 determinism (WantKind, SecretSeverity, Skill, PersonalityTrait, CombatStyle, RelationshipKind)
+- Global RelationshipGraph resource (#87) — BTreeMap with tuple key for efficient prefix queries and reverse lookups
+- A* pathfinding system (#237) — PathRequest/ComputedPath/PathBlocked components with cardinal-neighbor A* and manhattan heuristic
+- NPC path following system (#238) — MovementSpeed throttling, per-tick path advancement with MoveIntent creation
+- Daily routine system (#88) — NpcPlugin with PreviousDayPhase resource and check_phase_transition system issuing PathRequests at day-phase boundaries
+- Multiple NPC spawning (#84) — 3 distinct NPCs (dock worker, field tech, guard) with full component bundles and RelationshipGraph edges
+- Observation event generator (#239) — RoutineDeviation, Absence, and NewEntity triggers from comparing visible snapshot against NPC routines and knowledge state
+- Review-pr skill routes reviewers by branch type — server/client get Hoshe+Tyre, copy gets Hoshe+Paula+Miri, visual gets Hoshe+Araminta, audio gets Hoshe+Ozzie
+- Start-sprint skill spawns team agents from sprint briefings — parses the Agents line, creates a team with tasks from tickets, and launches all listed agents as background teammates
+
+### Fixed
+- IPC error handling (#341) — DeserializationWithDump/MutexPoisoned error variants, hex dump logging on deserialization failure, graceful error classification in bridge I/O systems
+- NpcPlugin system ordering — routine phase transitions now run before pathfinding so PathRequests are picked up same frame
+- Stale doc comment in observation event generator — system runs before knowledge updates, not after
+- Clippy warnings from Rust 1.93 — derive Default, is_multiple_of, collapsible if
+
+### Changed
+- Hael renamed to Naia Tamm across all wiki files (16 files updated)
+- Canonical full names applied to 11 single-name NPCs (Voss→Arvo Voss, Devra→Devra Talsen, etc.)
+- Location shortcodes standardized in monologue guide (hub_m_ → terminal_m_ per D-036)
+- Entity attributes updated to 16 canonical keys — 4 new role-perspective keys (risk_assessment, loyalty_assessment, position_integrity, moral_weight), secret_held→leverage_held rename
+- Drin Rosta expanded from Tier 3 to Tier 2 — full 10-axis profile, 6 voice lines, Triangle 2 + Triangle 5 roles
+- NPC index roster table expanded with Pattern and Motivation columns
+- Sprint 3 "Know" team briefings regenerated from database — all four files (server, client, joint, copy) now match actual sprint 3 ticket assignments
+- Ticketing database moved to shared worktree location (`../settledreach.db`) — eliminates binary merge conflicts across branches
+- All Python connectors use script-relative path resolution instead of `$REPO_ROOT` env var or git rev-parse
+- `$REPO_ROOT` environment variable removed — all scripts, skills, and docs use relative paths
+- Merged copy branch — 39 tickets, wiki review + content scoping workshops, game world glossary
+- Merged maintenance branch — worktree-update skill
+
+### Added
+- `make db-backup` / `make db-install` — database backup to `docs/backups/` (main-only) and restore for new clones
+- Worktree-update skill backs up the shared database after merges on main
+
+### Removed
+- `db/commonwealth.db` from git tracking (replaced by shared `../settledreach.db`)
+- `$REPO_ROOT` env var from all 9 worktree `settings.local.json` files
+
+### Added
+- Worktree-update skill — non-destructive branch sync with PR detection and conflict safety
+- Game world wiki — 45-file glossary covering Sova Transit District: 17 NPCs, 5 triangles, 3 social sites, 7 factions, knowledge vocabulary
+- Wiki Review workshop (4 rounds + lead interview) — 300-world generator model, cultural ingredients menu, three-system NPC architecture, Sacred/Profane/Middle Kingdom framework
+- v0.1 Content Scoping workshop (2 rounds + closing) — 16 EntityKnowledge keys, mechanical NPC mapping, YAML content format, 7-verb interaction model, server-authoritative pause, 20 decisions (D-042–D-061)
+- 39 implementation tickets (#371–#409) from content scoping workshop — copy 21, server 13, client 2, ci 1
+- Control & Interaction workshop brief (queued)
+- Large content push team pattern in CLAUDE.md
+- Inigo sound designer agent — soundscape design, ambient layers, diegetic cues, D-018 audio propagation
+- Team-agent mapping in sprint planning — each team has defined default agents for briefing assignment
+- Sprint skills recognize all team branches (server, client, copy, audio, visual, ci)
+- Sprint 3 "Know" team briefings — server (6 tickets), client (2 tickets), joint (2 split tickets), copy (1 carry-over)
+- Copy team sprint briefing for Sprint 2 (#368 knowledge vocabulary)
+- Sprint 2 proof: fog of perception E2E tests (#357) — 3 tests verifying all 7 acceptance criteria through real server pipeline (movement, tiles, fog, wall hiding, corner reveal)
+- Server proof room — wall at (16,14) between player at (16,16) and NPC at (16,13) for LOS testing
+- Dynamic test snapshot in SimBridge — tracks player position from queued inputs, Bresenham LOS, Manhattan-distance visibility for standalone demo mode
+- 4 Bresenham LOS unit tests — clear path, wall blocked, diagonal, same position (PR #13 review)
+
+### Fixed
+- Type safety in GameState visible_tiles loop — validates Dictionary with x/y keys before access (PR #11 review)
+- Consistent reset_test_state() usage across all test files (PR #13 review)
+- E2E connection loop now detects server process death early (PR #13 review)
+- Corner reveal test verifies NPC position at (16.5, 13.5) (PR #13 review)
+- Entity renderer skips redundant modulate.a writes when alpha unchanged (PR #11 review)
+
+### Added
+- Observer snapshot knowledge integration (#366) — VisibleEntity carries relationship state (D-033 color) and observation type (Visible/Remembered), remembered entities appear as fog ghosts at last known position
+- Knowledge graph system (#361, #362, #363, #365) — per-entity KnowledgeGraph component (D-041), StableEntityId + EntityRegistry, KnowledgeEventQueue, decay system, 4-level confidence hierarchy
+- Direct observation knowledge flow (#364) — perception emits DirectObservation/LeftLOS events to knowledge graph, entities entering/leaving LOS tracked
+- Protocol v2 decoder — extracts game_time, player_facing, visible_tiles, and per-entity visibility sectors from ObserverSnapshot v2
+- D-033 entity color palette (#130) — relationship-based colors (teal/green/amber/red), Phase 1 defaults by entity kind
+- Peripheral vision dimming — entities in peripheral vision rendered at 50% alpha (D-015)
+- Player facing direction indicator — Polygon2D triangle on player entity showing 8-directional facing
+- GameState v2 fields — game_time, player_facing, visibility_sectors stored from snapshot data
+- Test snapshot updated to v2 format with visibility sectors, game_time, and player_facing
+- Observer visibility query (#112) — replaces unfiltered generate_snapshot with LOS-filtered compute_observer_snapshot combining shadowcasting + vision cone
+- Vision cone system (#111) — forward/peripheral/blind sectors per D-015, Facing component updated on movement
+- Symmetric shadowcasting (#110, #359) — Albert Ford algorithm with rational fraction slopes, benchmarked 1.2-10.5x faster than recursive, symmetry guaranteed (D-035)
+- ObserverSnapshot v2 schema (#358, #25) — version field, GameTime, FacingDirection, VisibleTile, VisibilitySector types, visibility tag on entities
+- D-035 decision record — symmetric shadowcasting selected over recursive (resolves Q-018)
+- Tile rendering engine (#129) — programmatic TileSet with floor/wall/door/object placeholders, renders from snapshot tile data
+- Fog overlay rendering (#131) — three visibility states (visible/fog-edge/hidden) via TileMapLayer overlay
+- Camera lock to character (#116) — Camera2D smoothing at 2x zoom, locked to player position (D-015)
+- Test room environment — 8x8 room with corridor and Manhattan-distance visibility for development without server
+- `ticket team` command and `--team` filter — comma-separated team assignment for tickets (server, client, joint, content)
+
+### Changed
+- All instruction files (CLAUDE.md, skills, agent files) now use `$REPO_ROOT` env var instead of `git rev-parse --show-toplevel` — pre-set per worktree via `.claude/settings.local.json`
+- `start-sprint` skill now requires plan mode — agent must create and get approval for a concrete sprint plan before starting implementation
+
+### Fixed
+- Entity renderer protocol field mismatches — "id"→"entity_id", "type"→"kind.variant", "position"→x/y fields now match Protocol.decode_entity() output
+- Entity centering — entities (24x24) now centered within 32px tiles instead of top-left aligned
+- `start-sprint` skill uses `git rev-parse --show-toplevel` for worktree-safe absolute paths — fixes "No such file or directory" errors on team branches
+
+### Changed
+- Background clear color set to near-black for unexplored areas (was default Godot gray)
+- Scene render order: Tiles → FogOverlay → Entities (fog covers tiles, entities render on top)
+- FogOverlay node type changed from Node2D to TileMapLayer for tile-based fog rendering
+- GameState now stores visible_tiles and visible_positions from snapshots
+- Test snapshot includes player entity (kind "Player"), second NPC entity, tile data, and visibility data
+
+### Added
+- Sprint 2 "See" briefings (server, client, joint) — fog of perception through the bridge
+- `/plan-sprint` skill — automates sprint planning workflow and briefing file generation
+- `ticket show` multi-ID support and `--brief` flag for compact human-readable output
 - Q-018 through Q-023 — 6 open questions from architecture audit (shadowcasting, entity ID stability, collision resolution, tick overflow, pathfinding cache, debug visualization)
 - 5 architecture spike workshop briefs (knowledge graph, observer pipeline, NPC AI state machines, save/load, map authoring)
 - 17 tickets from architecture audit (#339-#355) — 7 Sprint 1 tasks, 5 Sprint 2+ tasks, 5 workshop epics
+- End-to-end connection test (#81) — GDScript test spawning Rust server, connecting via LocalBridge, sending MoveNorth input, verifying player movement in snapshot response (D-030 Layer 3)
+- Batch input encoding (Vec\<PlayerInput\> wire format) — Protocol.encode_player_inputs() batches all inputs per tick into one framed message matching server expectations
+- EntityKind::Player fixture — snapshot_player.msgpack for cross-language testing, multi-entity fixture updated to include all 4 entity kinds
+- 7 new tests (4 batch encoding, 1 framed batch roundtrip, 1 Player fixture decode, 1 E2E connection), 43 total client tests passing
 - LocalBridge GDScript TCP transport (#79) — 4-byte big-endian length-prefix framing matching Rust server, StreamPeerTCP wrapper with partial read handling
 - ServerProcess subprocess manager — spawns/stops Rust server via OS.create_process(), auto-cleanup on destruction
 - SimBridge live transport integration — _process() polling loop for TCP receive/send, connection state machine (DISCONNECTED → CONNECTING → CONNECTED → ERROR)
@@ -116,6 +997,9 @@ Format based on [Keep a Changelog](https://keepachangelog.com/).
 - Rejected alternatives R-004 through R-010 documented (pure Bevy, pure Godot, GDExtension, C++ GDExtension, Fyrox, custom framework, protobuf)

 ### Fixed
+- create-skill references to nonexistent init_skill.py and package_skill.py scripts
+- SimBridge wire format: inputs now batch-encoded as Vec\<PlayerInput\> array per server protocol (was sending individual inputs per frame)
+- SimBridge server args: positional address format ("127.0.0.1:9876") matching server CLI, port default corrected to 9876
 - Wire format mismatch: LocalBridge now uses rmp_serde::to_vec_named() (named maps) matching client Protocol.gd expectations
 - EOF on bridge read now returns BridgeError::Transport for disconnect detection instead of empty Vec
 - WalkabilityMap rewritten from flat Vec to chunk-based HashMap per D-012 architecture (Tyre review)
@@ -137,6 +1021,7 @@ Format based on [Keep a Changelog](https://keepachangelog.com/).
 - dotfiles/tmux.conf (no longer needed)

 ### Changed
+- Q-018 (shadowcasting algorithm selection) resolved via D-035
 - All 18 agent briefings updated for decisions/ directory split and DEVOPS.md references
 - Implementation agents (Dudley, Hoshe, Justine, Oscar, Si, Stig, Tyre) now include Development Workflow sections with Makefile targets
 - Q-009 (time system) resolved via D-031
@@ -1,134 +1,79 @@
 # The Settled Reach

-A top-down immersive sim — occlusion-based detective game with combat elements, set in an original science fiction universe. Single-character perspective, asymmetric information as core mechanic, Rimworld-style storyteller. Godot 4 client + Rust/bevy_ecs simulation server via subprocess/IPC (D-020).
+A top-down immersive sim — occlusion-based detective game with combat elements, set in an original science fiction universe. Single-character perspective, asymmetric information as core mechanic, Rimworld-style storyteller. Godot 4 client + Rust/bevy_ecs simulation server via subprocess/IPC.

-**Official Title:** The Settled Reach (D-021)
-**Repository name:** commonwealth (historical code name, retained for path stability)
+**Official Title:** The Settled Reach
+**Repository name:** settled-reach
+**Version source of truth:** `project.yaml` (root `version` field, scheme: `0.1.{sprint_number}`)

 ## Project Structure

 ```
-client/               # Godot 4 client (D-020)
-server/               # Rust/bevy_ecs simulation server (D-020)
+client/               # Godot 4 client
+server/               # Rust/bevy_ecs simulation server
 tooling/              # Build tools, scripts, asset pipelines
 tests/                # Integration and end-to-end tests
-.config/              # Configuration files (linters, formatters, CI)
-.cache/               # Local caches for testing/linting (gitignored)
-docs/
-  discussions/        # Discussion rounds (all rounds archived here per D-022)
-  briefings/          # Per-agent context briefings (maintained by Qatux)
-  architecture/       # Technical architecture documents
-  design/             # Game design documents
-  sprints/            # Sprint briefings per team (server.md, client.md, joint.md, content.md)
-  workshops/          # Workshop briefs and outputs (per-workshop subdirectories)
-db/
-  commonwealth.db     # SQLite ticketing database
-  schema.sql          # Database schema
-  connectors/         # Connector scripts for SQLite and Qdrant
-    config.json       # Endpoint configuration
-    ticket                # Ticket CLI (list, show, create, assign, sprint, etc.)
-    sqlite_connector.py   # SQLite mini MCP
-    qdrant_connector.py   # Qdrant + ollama mini MCP
-.claude/
-  agents/             # Agent personality files
-  skills/             # Skill definitions
-decisions/            # Decision domain files (source of truth)
-  README.md           # Domain index and query examples
-  architecture.md     # D-008, D-009, D-010, D-012, D-020, D-026, D-030, D-031
-  perception.md       # D-011, D-015, D-016, D-017, D-018, D-019
-  content.md          # D-023, D-024, D-025, D-028, D-029
-  scope.md            # D-001, D-003, D-005, D-006, D-007, D-013, D-014, D-027
-  process.md          # D-004, D-021, D-022
-  questions.md        # Q-001 through Q-011
-  rejected.md         # R-001 through R-010
-DECISIONS.md          # Redirect to decisions/ directory
-TEAM.md               # Team roster and roles
+docs/                 # Architecture, design, briefings, sprints, workshops
+db/                   # Schema + seed data (connectors moved to tooling/db/)
+.claude/              # Agents, skills, rules
+decisions/            # Decision domain files (D-NNN confirmed, Q-NNN open, R-NNN rejected)
 ```

+Full annotated tree: `.claude/rules/project-structure.md`
+
 ## DevOps

 See [docs/DEVOPS.md](docs/DEVOPS.md) for build, test, lint, and CI procedures. All development operations go through the top-level `Makefile` — run `make` for a summary of targets.

 ## Agent Instructions

+### Team boundaries
+
+**Your team identity is `$WORKTREE_TEAM`.** All work must stay within the current working directory.
+
+- All file paths are relative to the current working directory (e.g. `server/src/bridge/types.rs`).
+- **Do NOT navigate to parent or sibling directories** (`../`, `../client/`, etc.) unless explicitly instructed. Do NOT use absolute paths to reach other team directories.
+- **Do NOT write auto-memory files for other teams.** If `$WORKTREE_TEAM` is `server`, do not write to memory paths containing `client`, `main`, etc.
+- For context: each team has its own directory via git worktrees, sharing a parent directory (`settled-reach/`). The `.git` file points to a shared git directory — do not follow it to determine your working root.
+- **Exception — stale git lock files:** If a `git` command fails with `index.lock: File exists`, you may remove the lock file for **your own team only** (e.g. `main/.git/worktrees/$WORKTREE_TEAM/index.lock`). Never touch lock files belonging to other teams.
+- **Never chain git commands** in a single Bash call (e.g. `git add ... && git commit ...`). The shared `.git` directory means concurrent index access from the same terminal creates `index.lock` collisions. Always run `git add` and `git commit` as **separate sequential Bash calls**.
+
+### Database
+
+The ticketing database (`settledreach.db`) lives in the **parent directory** shared across all worktrees — it is not tracked in git. A backup is committed to `docs/backups/settledreach.db.backup` via main only.
+
 ### Before starting work
 1. Read your sprint briefing at `docs/sprints/sprint-N/{team}.md` for current tasks
-2. Use `db/connectors/ticket show <id>` for full ticket details
+2. Use `tooling/db/ticket show <id>` for full ticket details
 3. Read the relevant `decisions/*.md` domain file(s) referenced in the briefing
 4. Background context: `docs/briefings/{your-name}.md`, `docs/discussions/`

-### SQLite access
-**Never use the `sqlite3` CLI** - it crashes in Claude Code due to a known std::bad_alloc bug.
+### CLI tools

-Use the whitelistable wrapper scripts:
-```bash
-db/connectors/sqlite-query "SELECT * FROM tickets WHERE status='in_progress'"
-db/connectors/sqlite-exec "UPDATE tickets SET status='done' WHERE id=1"
-```
+**Prefer CLI wrappers over raw SQL.** Never use the `sqlite3` CLI — it crashes in Claude Code (std::bad_alloc). Use the wrapper scripts instead.

-### Qdrant / document search
-```bash
-db/connectors/qdrant-search "asymmetric information design"
-db/connectors/qdrant-index docs/briefings/tyre.md
-db/connectors/qdrant-health
-db/connectors/qdrant-count
-```
+| Tool | Command | Full reference |
+|------|---------|----------------|
+| Tickets | `tooling/db/ticket list`, `show`, `create`, `assign` | `/ticket` skill |
+| Sprints | `tooling/db/sprint status`, `start-work`, `prepare` | `/sprint-start` skill |
+| SQL queries | `tooling/db/sqlite-query "SELECT ..."` | — |
+| SQL writes | `tooling/db/sqlite-exec "UPDATE ..."` | — |
+| Decisions | `tooling/db/decision next`, `claim`, `check-dupes` | — |
+| Doc search | `tooling/db/qdrant-search "query"` | `/docs-search` skill |
+| Doc index | `tooling/db/qdrant-index path/to/file.md` | `/docs-search` skill |

-### Gitea access (tea CLI)
-**Never access the Gitea API directly** — use the `tea` CLI with all required flags to bypass interactive mode.
+### Testing preferences

-Always pass `--login schweitz --repo jpmschweitzer/settled-reach --output simple` to avoid TTY prompts.
-
-```bash
-# List open PRs
-tea pr list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
-
-# View a PR with comments
-tea pr --login schweitz --repo jpmschweitzer/settled-reach --comments -o simple <PR_NUMBER>
-
-# Post a comment on a PR (or issue)
-tea comment --login schweitz --repo jpmschweitzer/settled-reach <NUMBER> "comment body"
-
-# Approve a PR
-tea pr approve --login schweitz --repo jpmschweitzer/settled-reach <PR_NUMBER>
-
-# List issues
-tea issue list --login schweitz --repo jpmschweitzer/settled-reach --state open --output simple
-```
-
-Key rules:
- **All flags must be explicit** — omitting `--login` or `--repo` triggers interactive prompts that crash in Claude Code (no TTY)
- **Use `--output simple`** for machine-readable output (no table borders)
- **`tea pr reject` does not work on your own PRs** — use `tea comment` instead
- **Never delete protected branches:** `main`, `maintenance`, `server`, `client` are protected on Gitea. Do not use `tea pr clean`, `git push --delete`, or `git branch -D` on these branches.
+- **Prefer live Gauntlet testing over mocks.** For visual tests and rendering verification, use the full client/server pipeline (`--test-mode` + `SR_LIVE=1`) instead of TestHarness mocks. The Gauntlet test world produces production-identical data. Mocks can mask rendering bugs by taking different code paths.
+- **Gauntlet rooms are immutable.** Never modify existing rooms — new systems get new rooms. This ensures StableId determinism and fixture stability.
+- Three test tiers: (1) Live server — highest fidelity, (2) MessagePack replay via `Protocol.decode_snapshot()` — for unreachable rooms, (3) TestHarness mock — for UI-only tests where fog data doesn't matter.
+- `make fixtures-gauntlet` regenerates real server snapshot fixtures from the Gauntlet world.

 ### File conventions
 - Decisions: domain files in `decisions/` (see `decisions/README.md` for index)
 - Decision IDs: `D-NNN` (confirmed), `Q-NNN` (open questions), `R-NNN` (rejected)
+- **Claim IDs before writing:** `tooling/db/decision claim D <domain> "title"` — prevents ID collisions across worktrees
+- Diagrams: `.d2` source + `.png` renders in `docs/diagrams/{category}/`. Create or update diagrams via `/d2-diagram` when D-records are added or modified.
 - Discussion rounds: numbered sequentially, archived to `docs/discussions/` when complete
 - Briefings: one per agent, updated after decision-producing rounds
- Tickets: managed via `db/connectors/ticket` CLI or `/ticket` skill
-
-### Commit conventions
-Use conventional commits with project-specific scopes:
-`agents`, `skills`, `docs`, `briefings`, `discussions`, `schema`, `db`, `config`, `engine`, `simulation`, `client`, `ui`, `audio`, `assets`, `meta`
-
-### Pull requests
-**Use `tea` (Gitea CLI), not `gh` (GitHub CLI).** The remote is Gitea at `git.schweitz.internal`.
-
-Always provide all required flags to ensure non-interactive execution:
-```bash
-tea pr create \
-  --repo jpmschweitzer/settled-reach \
-  --login schweitz \
-  --title "feat(scope): short description" \
-  --description "PR body here" \
-  --base main \
-  --head branch-name
-```
-
-### Local services
- Gitea: `http://git.schweitz.internal` (login: `schweitz`)
- Qdrant: `http://tower-of-joy:6333/`
- Ollama: `http://tower-of-joy:11434/` (nomic-embed-text)
- Collection: `commonwealth` (768 dimensions, cosine distance)
+- Tickets: managed via `tooling/db/ticket` CLI or `/ticket` skill
@@ -1,7 +1,15 @@
 GODOT := $(shell command -v godot4 2>/dev/null || command -v godot 2>/dev/null)

-.PHONY: help setup build client server test lint ci ci-client ci-server clean \
-       decisions-sync decisions-coverage decisions-active decisions-orphan
+.PHONY: help setup build check-protocol client server game stop test lint ci ci-client ci-server clean \
+       decisions-sync decisions-coverage decisions-active decisions-orphan \
+       db-backup db-install validate-content content-ron check-fact-ids setup-hooks \
+       pre-pr pre-pr-lint pre-pr-build pre-pr-test pre-pr-validate pre-pr-fixtures \
+       pre-pr-server pre-pr-client pre-pr-content \
+       fixtures-client fixtures-gauntlet golden-diff golden-update \
+       checklist-validate checklist-generate \
+       perf-baseline debug-schedule \
+       test-ipc-fixtures test-ipc-protocol test-ipc-integration test-ipc-benchmark \
+       screenshot visual-movie test-visual visual-update

 # --- Configuration ---

@@ -13,25 +21,57 @@ help:
 	@echo ""
 	@echo "  make setup          Install dev dependencies (Rust, Godot, tooling)"
 	@echo "  make build          Build client and server"
-	@echo "  make client         Run the Godot client"
+	@echo "  make game           Build and run the full game (server + client)"
+	@echo "  make stop           Stop any running server instance"
+	@echo "  make client         Run the Godot client (test mode)"
 	@echo "  make server         Run the Rust simulation server"
-	@echo "  make test           Run all tests"
-	@echo "  make lint           Run all linters"
-	@echo "  make ci             Run full CI pipeline locally"
-	@echo "  make ci-client      Run client CI checks"
-	@echo "  make ci-server      Run server CI checks"
+	@echo "  make test               Run all tests"
+	@echo "  make test-ipc-fixtures  Layer 1: IPC serialization fixtures"
+	@echo "  make test-ipc-protocol  Layer 2: mock IPC protocol tests"
+	@echo "  make test-ipc-integration Layer 3: real subprocess round-trip"
+	@echo "  make test-ipc-benchmark IPC latency benchmark (blocked: #555/#556)"
+	@echo "  make lint               Run all linters"
+	@echo "  make ci                 Run full CI pipeline locally"
+	@echo "  make ci-client          Run client CI checks"
+	@echo "  make ci-server          Run server CI checks"
+	@echo "  make check-protocol Verify server/client protocol versions match"
 	@echo "  make clean          Remove build artifacts and caches"
 	@echo ""
+	@echo "  make db-backup          Backup shared database to git (main only)"
+	@echo "  make db-install         Restore shared database from backup"
+	@echo ""
 	@echo "  make decisions-sync     Sync decisions/*.md into SQLite"
 	@echo "  make decisions-coverage Decision-to-ticket coverage by domain"
 	@echo "  make decisions-active   List active decisions"
 	@echo "  make decisions-orphan   Decisions without implementing tickets"
+	@echo "  make validate-content   Validate content YAML against schemas"
+	@echo "  make check-fact-ids    Check fact_id references against knowledge catalogs"
+	@echo "  make content-ron       Convert content YAML to RON (build-time)"
+	@echo "  make fixtures-client    Generate GDScript->Rust cross-encoder fixtures (#475)"
+	@echo "  make golden-diff        Show diff if golden file output has changed"
+	@echo "  make golden-update      Regenerate golden file and stage for commit"
+	@echo "  make checklist-validate Validate checklist YAML against schema"
+	@echo "  make checklist-generate Validate checklists + print condition summary"
+	@echo "  make perf-baseline      Run performance benchmarks and save baseline"
+	@echo ""
+	@echo "  make screenshot          Ad-hoc visual capture (SCENARIO=name, default: fog_3state)"
+	@echo "  make visual-movie       Flow capture with contact sheet (FLOW=name)"
+	@echo "  make test-visual        Run visual golden regression tests"
+	@echo "  make visual-update      Regenerate visual goldens and stage for commit"
+	@echo ""
+	@echo "  make pre-pr             Run all pre-PR checks (lint, build, test, validate, fixtures)"
+	@echo "  make pre-pr-server      Server-scoped pre-PR (lint, build, test, fixtures)"
+	@echo "  make pre-pr-client      Client-scoped pre-PR (lint, build, test)"
+	@echo "  make pre-pr-content     Content-scoped pre-PR (schema + cross-ref validation)"
+	@echo ""
+	@echo "  make setup-hooks       Install pre-commit hooks (included in setup)"
+	@echo "  make debug-schedule    Print bevy_ecs schedule graph (diff for PR artifacts)"
 	@echo ""
 	@echo "  GODOT_VERSION=4.6 make setup   Override Godot version"

 # --- Setup ---

-setup: setup-rust setup-godot setup-tooling decisions-sync
+setup: setup-rust setup-godot setup-tooling setup-hooks decisions-sync
 	@echo "Dev environment ready."

 setup-rust:
@@ -45,40 +85,120 @@ setup-tooling:
 	@command -v python3 >/dev/null 2>&1 || { echo "Install Python 3"; exit 1; }
 	@command -v curl >/dev/null 2>&1 || { echo "Install curl (required for Godot download)"; exit 1; }
 	@command -v unzip >/dev/null 2>&1 || { echo "Install unzip (required for Godot download)"; exit 1; }
+	@python3 -c "import yaml" 2>/dev/null || { echo "Install PyYAML: pip install pyyaml"; exit 1; }
+	@python3 -c "import jsonschema" 2>/dev/null || { echo "Install jsonschema: pip install jsonschema"; exit 1; }
+
+setup-hooks:
+	@git config core.hooksPath .config/hooks
+	@echo "Git hooks path set to .config/hooks"

 # --- Build ---

-build: build-server build-client
+check-protocol:
+	@SERVER_V=$$(grep 'pub const PROTOCOL_VERSION' server/src/bridge/types.rs | sed 's/.*= *//;s/[^0-9]//g'); \
+	CLIENT_V=$$(grep 'const PROTOCOL_VERSION' client/scripts/protocol/protocol.gd | sed 's/.*= *//;s/[^0-9]//g'); \
+	if [ "$$SERVER_V" != "$$CLIENT_V" ]; then \
+		echo "ERROR: Protocol version mismatch — server=$$SERVER_V, client=$$CLIENT_V"; \
+		echo "  Fix: update client/scripts/protocol/protocol.gd to match server/src/bridge/types.rs"; \
+		exit 1; \
+	fi
+
+build: check-protocol build-server build-client

 build-server:
 	cd server && cargo build

 build-client:
 	@test -n "$(GODOT)" || { echo "Godot not found. Run 'make setup' first."; exit 1; }
-	$(GODOT) --headless --path client --quit
+	@# First import may error on theme/font loading before the import scan completes.
+	@# Run twice: first pass generates imports silently, second pass validates clean.
+	@$(GODOT) --headless --path client --import --quit 2>/dev/null || true
+	$(GODOT) --headless --path client --import --quit

 # --- Run ---

 server:
-	cd server && cargo run
+	cd server && cargo run --bin settled-reach-server

 client:
 	@test -n "$(GODOT)" || { echo "Godot not found. Run 'make setup' first."; exit 1; }
 	$(GODOT) --path client

+game: stop build
+	@test -n "$(GODOT)" || { echo "Godot not found. Run 'make setup' first."; exit 1; }
+	@echo "Starting server..."
+	@cd server && cargo run --bin settled-reach-server &
+	@sleep 2
+	@echo "Starting client..."
+	@SR_LIVE=1 $(GODOT) --path client
+	@$(MAKE) stop
+
+stop:
+	@lsof -ti :9876 | xargs -r kill 2>/dev/null || true
+	@echo "Stopped any running server on port 9876"
+
 # --- Test ---

 test: test-server test-client

 test-server:
-	cd server && cargo nextest run
+	tests/run-rust

 fixtures:
 	cd server && cargo test --test gen_fixtures -- --ignored

-test-client:
+fixtures-gauntlet:
+	cd server && cargo test --test gen_gauntlet_fixtures -- --ignored
+
+fixtures-client:
 	@test -n "$(GODOT)" || { echo "Godot not found. Run 'make setup' first."; exit 1; }
-	$(GODOT) --headless --path client -s res://addons/gdUnit4/bin/GdUnitCmdTool.gd --ignoreHeadlessMode -a res://tests/
+	@echo "Generating GDScript fixtures for Rust decoder..."
+	$(GODOT) --headless --path client -s res://tests/gen_client_fixtures.gd
+	@echo "Verifying Rust can decode GDScript fixtures..."
+	cd server && cargo test --test serialization gdscript_generated_fixtures
+	@echo "--- Fixtures-client: PASS ---"
+
+golden-diff:
+	@echo "Regenerating golden output for comparison..."
+	@mkdir -p .cache/golden
+	@cp server/tests/golden/proof_room_tick_10.json .cache/golden/before.json
+	@cd server && UPDATE_GOLDEN=1 cargo test --test golden_suite -- proof_room_tick_10_matches_golden; \
+		rc=$$?; \
+		cp ../server/tests/golden/proof_room_tick_10.json ../.cache/golden/after.json 2>/dev/null; \
+		cp ../.cache/golden/before.json ../server/tests/golden/proof_room_tick_10.json; \
+		if [ $$rc -ne 0 ]; then echo "Cargo test failed (golden file restored)."; exit $$rc; fi
+	@if diff -q .cache/golden/before.json .cache/golden/after.json >/dev/null 2>&1; then \
+		echo "--- Golden file: UP TO DATE ---"; \
+	else \
+		echo "--- Golden file has CHANGED ---"; \
+		echo ""; \
+		diff --color -u .cache/golden/before.json .cache/golden/after.json || true; \
+		echo ""; \
+		echo "Run 'make golden-update' to accept changes."; \
+		exit 1; \
+	fi
+
+golden-update:
+	@echo "Regenerating golden file..."
+	@cd server && UPDATE_GOLDEN=1 cargo test --test golden_suite -- proof_room_tick_10_matches_golden
+	@git add server/tests/golden/
+	@echo "--- Golden file updated and staged ---"
+	@echo "Review with: git diff --cached -- server/tests/golden/"
+
+test-client:
+	tests/run-godot
+
+test-ipc-fixtures:
+	tests/run-ipc-fixtures
+
+test-ipc-protocol:
+	tests/run-ipc-protocol
+
+test-ipc-integration:
+	tests/run-ipc-integration
+
+test-ipc-benchmark:
+	tests/run-ipc-benchmark

 # --- Lint ---

@@ -93,6 +213,70 @@ lint-client:
 	@echo "Checking GDScript for errors..."
 	@$(GODOT) --headless --path client --quit 2>&1 | grep -i "SCRIPT ERROR" && { echo "GDScript errors found"; exit 1; } || echo "No script errors found"

+# --- Pre-PR verification ---
+
+pre-pr: pre-pr-lint pre-pr-build pre-pr-test pre-pr-validate pre-pr-fixtures
+	@echo ""
+	@echo "=== PRE-PR: ALL CHECKS PASSED ==="
+	@echo "Safe to create PR."
+
+pre-pr-lint: lint-server lint-client
+	@echo "--- Lint: PASS ---"
+
+pre-pr-build: build-server build-client
+	@echo "--- Build: PASS ---"
+
+pre-pr-test: test-server test-client
+	@echo "--- Tests: PASS ---"
+
+pre-pr-validate: validate-content check-fact-ids
+	@echo "--- Content validation: PASS ---"
+
+pre-pr-fixtures:
+	@echo "Checking Rust->GDScript fixture staleness..."
+	@cd server && cargo test --test gen_fixtures -- --ignored
+	@if git diff --quiet client/tests/fixtures/; then \
+		echo "--- Rust fixtures: UP TO DATE ---"; \
+	else \
+		echo ""; \
+		echo "--- RUST FIXTURES STALE ---"; \
+		echo "  Protocol changed but fixtures not regenerated."; \
+		echo "  Stale fixtures make all client tests FALSE POSITIVES."; \
+		echo ""; \
+		echo "  Changed files:"; \
+		git diff --stat client/tests/fixtures/; \
+		echo ""; \
+		echo "  Fix: commit the updated fixtures with your protocol change."; \
+		exit 1; \
+	fi
+	@echo "Checking GDScript->Rust fixture staleness..."
+	@$(MAKE) fixtures-client
+	@if git diff --quiet server/tests/fixtures/gdscript/; then \
+		echo "--- GDScript fixtures: UP TO DATE ---"; \
+	else \
+		echo ""; \
+		echo "--- GDSCRIPT FIXTURES STALE ---"; \
+		echo "  Protocol changed but GDScript fixtures not regenerated."; \
+		echo "  Stale fixtures make cross-encoder tests FALSE POSITIVES."; \
+		echo ""; \
+		echo "  Changed files:"; \
+		git diff --stat server/tests/fixtures/gdscript/; \
+		echo ""; \
+		echo "  Fix: commit the updated fixtures with your protocol change."; \
+		exit 1; \
+	fi
+
+# Branch-specific variants (faster, scope-appropriate)
+
+pre-pr-server: lint-server build-server test-server pre-pr-fixtures
+	@echo "=== Server pre-PR: PASSED ==="
+
+pre-pr-client: lint-client build-client test-client
+	@echo "=== Client pre-PR: PASSED ==="
+
+pre-pr-content: validate-content check-fact-ids checklist-validate
+	@echo "=== Content pre-PR: PASSED ==="
+
 # --- CI (run locally) ---

 ci: ci-server ci-client
@@ -101,24 +285,73 @@ ci-server: lint-server build-server test-server

 ci-client: lint-client build-client test-client

+# --- Database ---
+
+db-backup:
+	@tooling/db-backup
+
+db-install:
+	@tooling/db-install
+
 # --- Decisions ---

 decisions-sync:
-	@db/connectors/decisions-sync
+	@tooling/db/decisions-sync

 decisions-coverage:
-	@db/connectors/sqlite-query "SELECT d.domain, COUNT(DISTINCT d.id) as decisions, COUNT(DISTINCT t.decision_ref) as with_tickets FROM decisions d LEFT JOIN tickets t ON d.id = t.decision_ref WHERE d.status='active' AND d.type='confirmed' GROUP BY d.domain"
+	@tooling/db/sqlite-query "SELECT d.domain, COUNT(DISTINCT d.id) as decisions, COUNT(DISTINCT t.decision_ref) as with_tickets FROM decisions d LEFT JOIN tickets t ON d.id = t.decision_ref WHERE d.status='active' AND d.type='confirmed' GROUP BY d.domain"

 decisions-active:
-	@db/connectors/sqlite-query "SELECT id, domain, title FROM decisions WHERE status='active' AND type='confirmed' ORDER BY domain, id"
+	@tooling/db/sqlite-query "SELECT id, domain, title FROM decisions WHERE status='active' AND type='confirmed' ORDER BY domain, id"

 decisions-orphan:
-	@db/connectors/sqlite-query "SELECT id, title FROM decisions WHERE type='confirmed' AND status='active' AND id NOT IN (SELECT DISTINCT decision_ref FROM tickets WHERE decision_ref IS NOT NULL)"
+	@tooling/db/sqlite-query "SELECT id, title FROM decisions WHERE type='confirmed' AND status='active' AND id NOT IN (SELECT DISTINCT decision_ref FROM tickets WHERE decision_ref IS NOT NULL)"
+
+# --- Content Validation ---
+
+validate-content:
+	@tooling/validate-content
+
+check-fact-ids:
+	@tooling/check-fact-ids
+
+checklist-validate:
+	@tooling/validate-checklist --check
+
+checklist-generate:
+	@tooling/validate-checklist
+
+perf-baseline:
+	@tooling/perf-baseline
+
+# --- Schedule debug (#346) ---
+
+debug-schedule:
+	@echo "Dumping bevy_ecs schedule graph..."
+	@cd server && cargo run --bin settled-reach-server -- --dump-schedule
+
+# --- Visual test harness ---
+
+screenshot:
+	@tests/run-visual --screenshot $(SCENARIO)
+
+visual-movie:
+	@tests/run-visual --movie $(FLOW)
+
+test-visual:
+	@tests/run-visual
+
+visual-update:
+	@tests/run-visual --update
+
+content-ron:
+	cd tooling/content-converter && cargo build --release
+	tooling/content-converter/target/release/content-converter --input content --output content-ron --verbose

 # --- Clean ---

 clean:
 	cd server && cargo clean || true
 	rm -rf .cache/*
-	rm -rf client/.godot client/reports
+	rm -rf client/reports
 	@echo "Clean complete."
@@ -41,7 +41,7 @@ Your character interprets what they sense in their own voice. Footsteps behind y
 Different characters access different sensors. Natural vision shows detail but is blocked by walls. Thermal imaging shows heat signatures with no identity. Camera feeds give remote vision but can be spoofed. Unisphere tracking pings known contacts but can be masked. Each mode reveals different information with different trust tradeoffs.

 ### Diegetic Interface
-The map is your character's neural lattice - Commonwealth technology, not a game UI. Points of interest appear when you learn them through gameplay. Tips can be traps. Navigation is pulled by player intent, not pushed by map design.
+The map is your character's neural lattice - Settled Reach technology, not a game UI. Points of interest appear when you learn them through gameplay. Tips can be traps. Navigation is pulled by player intent, not pushed by map design.

 ### Multiple Playable Characters
 Every character starts in a different position with different knowledge and different tools. A cop has case files and legal authority. An investigator has contacts and freedom to operate. A politician has institutional access and public constraints. Replayability comes from perspective, not randomness.
@@ -125,7 +125,7 @@ No fog-of-war as an afterthought. No tutorial popups. No omniscient map reveals.
 **Official Title:** The Settled Reach (D-021)
 **Repository:** commonwealth (historical code name)
 **Engine:** Godot 4 + Rust/bevy_ecs simulation server via subprocess/IPC
-**Setting:** Original science fiction IP, Commonwealth-inspired
+**Setting:** Original science fiction IP, inspired by space opera traditions
 **Status:** Pre-alpha development

 For development documentation, see the [decisions/](decisions/) directory and [TEAM.md](TEAM.md).
@@ -38,6 +38,7 @@
 | **DUDLEY** | Server Developer | Game server, ECS, simulation loop, world state management. | Server implementation phase |
 | **OSCAR** | Networking Developer | Multiplayer networking, client-server protocol, sync. | Networking implementation phase |
 | **JUSTINE** | Polish & Deploy | Build pipelines, packaging, performance optimization, release prep. | Pre-release phase |
+| **INIGO** | Sound Designer | Soundscape design, ambient layers, diegetic audio cues, audio propagation. | Audio implementation phase |
 | **MELLANIE** | Copywriter | In-game text, UI copy, tooltips, flavor text, lore entries. | Content creation phase |
 | **TIGER** | Translator | Localization, i18n framework, translation management. | Localization phase |

@@ -69,25 +69,26 @@ static func _encode_message(buffer: StreamPeerBuffer, value):
 		TYPE_INT:
 			if - (1 << 5) <= value and value <= (1 << 7) - 1:
 				buffer.put_8(value)
-			elif - (1 << 7) <= value and value <= (1 << 7):
+			elif - (1 << 7) <= value and value < (1 << 7):
 				buffer.put_u8(types["int_8"])
 				buffer.put_8(value)
 			elif 0 <= value and value <= (1 << 8) - 1:
 				buffer.put_u8(types["uint_8"])
 				buffer.put_u8(value)
-			elif - (1 << 15) <= value and value <= (1 << 15):
+			elif - (1 << 15) <= value and value < (1 << 15):
 				buffer.put_u8(types["int_16"])
 				buffer.put_16(value)
 			elif 0 <= value and value <= (1 << 16) - 1:
 				buffer.put_u8(types["uint_16"])
 				buffer.put_u16(value)
-			elif - (1 << 31) <= value and value <= (1 << 31):
+			elif - (1 << 31) <= value and value < (1 << 31):
 				buffer.put_u8(types["int_32"])
 				buffer.put_32(value)
 			elif 0 <= value and value <= (1 << 32) - 1:
 				buffer.put_u8(types["uint_32"])
 				buffer.put_u32(value)
-			elif - (1 << 63) <= value and value <= (1 << 63):
+			elif value < 0:
+				# Negative beyond int_32 range — encode as int_64 (0xd3)
 				buffer.put_u8(types["int_64"])
 				buffer.put_64(value)
 			else:
@@ -133,7 +134,9 @@ static func _encode_message(buffer: StreamPeerBuffer, value):
 				return ERR_INVALID_DATA
 			
 			for obj in value:
-				_encode_message(buffer, obj)
+				var inner_err = _encode_message(buffer, obj)
+				if inner_err:
+					return inner_err

 		TYPE_DICTIONARY:
 			var size = value.size()
@@ -150,8 +153,12 @@ static func _encode_message(buffer: StreamPeerBuffer, value):
 				return ERR_INVALID_DATA
 			
 			for key in value:
-				_encode_message(buffer, key)
-				_encode_message(buffer, value[key])
+				var key_err = _encode_message(buffer, key)
+				if key_err:
+					return key_err
+				var val_err = _encode_message(buffer, value[key])
+				if val_err:
+					return val_err
 		
 		TYPE_PACKED_BYTE_ARRAY:
 			var size = value.size()
@@ -225,11 +232,9 @@ static func _decode_message(buffer: StreamPeerBuffer, err: Dictionary):
 		return buffer.get_utf8_string(size)
 		
 	elif first_byte == types["nil"]: # nil
-		print("null size:%s"%buffer_size)
 		return null
-		
+
 	elif first_byte == types["false"]: # false
-		print("false size:%s"%buffer_size)		
 		return false
 		
 	elif first_byte == types["true"]: # true
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://dfy0ye3srawos"
+path="res://.godot/imported/amb_bar_layer.ogg-8e32a9c679a33f27226744a176d7d405.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/amb_bar_layer.ogg"
+dest_files=["res://.godot/imported/amb_bar_layer.ogg-8e32a9c679a33f27226744a176d7d405.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://cne005dbmwt6d"
+path="res://.godot/imported/amb_corridor_layer.ogg-f14ba54010b129b65b0d248444331998.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/amb_corridor_layer.ogg"
+dest_files=["res://.godot/imported/amb_corridor_layer.ogg-f14ba54010b129b65b0d248444331998.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://b6ycjdvxpphfa"
+path="res://.godot/imported/amb_station_base.ogg-8056e0ae231edecc9ec0e49bb90136b7.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/amb_station_base.ogg"
+dest_files=["res://.godot/imported/amb_station_base.ogg-8056e0ae231edecc9ec0e49bb90136b7.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://dw2pokvg5d7v2"
+path="res://.godot/imported/amb_workplace_layer.ogg-580ba32198a3f6c782381c66f9520e63.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/amb_workplace_layer.ogg"
+dest_files=["res://.godot/imported/amb_workplace_layer.ogg-580ba32198a3f6c782381c66f9520e63.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://uflbvtm1aquk"
+path="res://.godot/imported/cursor_hover.ogg-f20fa5adecb73cc9163569968f5867a3.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/cursor_hover.ogg"
+dest_files=["res://.godot/imported/cursor_hover.ogg-f20fa5adecb73cc9163569968f5867a3.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://bw0mfil2343po"
+path="res://.godot/imported/fog_recognition.ogg-fd0dc7f57c3509774a533bc71a7687e7.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/fog_recognition.ogg"
+dest_files=["res://.godot/imported/fog_recognition.ogg-fd0dc7f57c3509774a533bc71a7687e7.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://dei8ikwaqyn67"
+path="res://.godot/imported/implant_open.ogg-46eadc4ed252693e3a936e75ddfdf4bc.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/implant_open.ogg"
+dest_files=["res://.godot/imported/implant_open.ogg-46eadc4ed252693e3a936e75ddfdf4bc.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://da81bx5y6iw87"
+path="res://.godot/imported/sfx_footstep_metal_run.ogg-0d448f29204d35d4133f5314a179d054.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/sfx_footstep_metal_run.ogg"
+dest_files=["res://.godot/imported/sfx_footstep_metal_run.ogg-0d448f29204d35d4133f5314a179d054.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://d14dx3q0qd483"
+path="res://.godot/imported/sfx_footstep_metal_walk.ogg-af30f14f9f80059ea65ad6e78234cc05.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/sfx_footstep_metal_walk.ogg"
+dest_files=["res://.godot/imported/sfx_footstep_metal_walk.ogg-af30f14f9f80059ea65ad6e78234cc05.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://b7iopmg6ftp4k"
+path="res://.godot/imported/sfx_monologue_chime.ogg-5981f28716fbe14273c052560195d890.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/sfx_monologue_chime.ogg"
+dest_files=["res://.godot/imported/sfx_monologue_chime.ogg-5981f28716fbe14273c052560195d890.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://4m87qby6qdhc"
+path="res://.godot/imported/sfx_monologue_chime_urgent.ogg-696a4dbc297417724610e01fa44fa575.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/sfx_monologue_chime_urgent.ogg"
+dest_files=["res://.godot/imported/sfx_monologue_chime_urgent.ogg-696a4dbc297417724610e01fa44fa575.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://cow7symyvpmal"
+path="res://.godot/imported/sfx_npc_murmur.ogg-bfd7592cfea1b592d89f107b6cd33838.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/sfx_npc_murmur.ogg"
+dest_files=["res://.godot/imported/sfx_npc_murmur.ogg-bfd7592cfea1b592d89f107b6cd33838.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://dbu2lr4scswyn"
+path="res://.godot/imported/sfx_stance_change.ogg-042fce976b2bd1b0806c72aa5dd64755.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/sfx_stance_change.ogg"
+dest_files=["res://.godot/imported/sfx_stance_change.ogg-042fce976b2bd1b0806c72aa5dd64755.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
@@ -0,0 +1,19 @@
+[remap]
+
+importer="oggvorbisstr"
+type="AudioStreamOggVorbis"
+uid="uid://c5lduxqgx0vme"
+path="res://.godot/imported/sfx_weapon_aim_lock.ogg-649a54b41e9bf6dd8ab414c03bb48cfa.oggvorbisstr"
+
+[deps]
+
+source_file="res://assets/audio/sfx_weapon_aim_lock.ogg"
+dest_files=["res://.godot/imported/sfx_weapon_aim_lock.ogg-649a54b41e9bf6dd8ab414c03bb48cfa.oggvorbisstr"]
+
+[params]
+
+loop=false
+loop_offset=0
+bpm=0
+beat_count=0
+bar_beats=4
--- a/Show More
+++ b/Show More