chore(meta): initial project structure and infrastructure

Set up Commonwealth game project with complete agent team (18 agents),
discussion archives (12 rounds), briefing system, ticketing database,
Qdrant document search, and skill definitions. Establishes the
documentation and tooling foundation for engine selection and
implementation phases.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docs/briefings/araminta.md

@@ -0,0 +1,27 @@
+# Araminta - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-013: Diegetic insert and minimap visual design - in-world UI aesthetic
+- D-015: Camera and vision cone visual presentation
+- D-016: Internal monologue text presentation - typography, positioning, style
+- D-017: Perception mode overlays - thermal vision, camera feeds, distinct visual treatments
+- D-018: Sound visual indicators - how audio information appears in medium range
+- D-019: Top-down art style - defining the game's visual identity
+
+## Open Questions Assigned to You
+- Q-003: Art direction (LEAD)
+
+## Current Priorities
+Create Commonwealth-specific visual style guide (color palette, UI patterns, visual grammar). Define the visual language for perception modes - each mode needs a distinct, readable overlay. Needs to create a new style guide for this project (existing /asset-gen skill configured for a different project).
+
+Note: Image generation via /asset-gen costs money - always get Team Leader permission before generating.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/dudley.md

@@ -0,0 +1,18 @@
+# Dudley - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic. Pre-implementation phase.
+
+## Status
+STANDBY. This briefing will be populated when backend/engine implementation begins.
+
+## Key Decisions for Your Domain
+- D-010: Four architectural principles - client-server, deterministic sim, moddable, data-driven
+- D-011: LOS shadowcasting implementation
+- D-012: Chunk-based map architecture
+- D-014: v0.1 map specification
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- docs/discussions/ - archived design rounds

docs/briefings/gestalt.md

@@ -0,0 +1,29 @@
+# Gestalt - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-005: Core concept - story generator mechanics, emergent narrative from systems
+- D-007: Five pillars - mechanical framework for all gameplay systems
+- D-008: Action pillar - hubris wall mechanic as systemic consequence generator
+- D-011: Fog of war as pillar 1 infrastructure - foundational information hiding
+- D-015: Camera lock to character - vision cone as primary information constraint
+- D-017: Perception loadout system - observer queries defining what player knows
+- D-018: Three-range sound system - information quality model by distance
+
+## Open Questions Assigned to You
+- Q-002: v0.1 scope definition (co-lead)
+- Q-005: Prototype scale (co-lead with Tyre, Miri)
+- Q-009: Time system design (co-lead with Gore)
+- Q-010: Storyteller AI architecture (co-lead with Nigel)
+
+## Current Priorities
+Mechanical deep-dive on individual pillars. Storyteller AI design. Ensure all five pillars interlock coherently as a unified system. Define how the storyteller orchestrates emergent narrative from pillar interactions.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/gore.md

@@ -0,0 +1,24 @@
+# Gore - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-005: Core concept - ascension as transformative character progression
+- D-007: Five pillars - thematic foundations supporting ascension narrative
+- D-008: Action pillar - scales with ascension level, hubris wall as ascension check
+- D-017: Perception modes - scaling with ascension, expanded awareness at higher tiers
+
+## Open Questions Assigned to You
+- Q-004: One campaign or eras? (co-lead with Miri)
+- Q-009: Time system design (co-lead with Gestalt)
+
+## Current Priorities
+Ascension path design. Endgame transformation mechanics. Define how ascension changes the player's relationship with the game's core systems.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/hoshe.md

@@ -0,0 +1,30 @@
+# Hoshe - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-010: Information boundaries - testable? Can we verify information never leaks?
+- D-011: LOS shadowcasting - verify correctness of visibility calculations
+- D-012: Chunk loading - seamless? No visible pop-in or loading seams?
+- D-013: POI appear/disappear correctly? Diegetic insert triggers reliably?
+- D-015: Vision cone - correct blind spots? No information visible outside cone?
+- D-016: Monologue triggers - contextually appropriate? Right timing, right content?
+- D-017: Perception queries - each mode returns correct information for its type?
+- D-018: Three ranges working correctly? Sound quality degrades properly by distance?
+
+## Open Questions Assigned to You
+None assigned.
+
+## Current Priorities
+STANDBY until implementation begins. When activated:
+1. Write test plans BEFORE features are built
+2. Verify implementations against DECISIONS.md specifications
+3. Ensure every decision with testable criteria has corresponding test coverage
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/justine.md

@@ -0,0 +1,16 @@
+# Justine - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic. Pre-implementation phase.
+
+## Status
+STANDBY. This briefing will be populated when build/deployment pipeline work begins.
+
+## Key Decisions for Your Domain
+- Q-007: Target platforms (open question - affects entire build pipeline)
+- D-019: Top-down primary view with future 3D cutscenes - build implications for asset pipelines and platform support
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- docs/discussions/ - archived design rounds

docs/briefings/mellanie.md

@@ -0,0 +1,17 @@
+# Mellanie - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic. Pre-implementation phase.
+
+## Status
+STANDBY. This briefing will be populated when narrative content creation begins.
+
+## Key Decisions for Your Domain
+- D-005: Single-character perspective - all narrative filtered through one viewpoint
+- D-016: Internal monologue system - primary narrative content delivery mechanism
+- D-013: Diegetic UI text - in-world written content and documents
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- docs/discussions/ - archived design rounds

docs/briefings/miri.md

@@ -0,0 +1,25 @@
+# Miri - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-005: Core concept - asymmetric information, single-character perspective, story generator
+- D-006: Prototype scenario - conspiracy arc proving core mechanics
+- D-013: Diegetic insert system - canon basis for in-world UI and POI navigation
+- D-016: Internal monologue system - character voice, unreliable narrator potential
+- D-017: Perception modes - canon check, ensuring modes are lore-consistent
+
+## Open Questions Assigned to You
+- Q-004: One campaign or eras? (co-lead with Gore)
+- Q-011: Character selection roster for prototype (co-lead with Paula)
+
+## Current Priorities
+Prepare canon reference material for engine selection discussion. Design character roster for prototype scenario. Ensure all mechanical decisions remain consistent with established lore and world-building.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/nigel.md

@@ -0,0 +1,24 @@
+# Nigel - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-005: Replayability through perspective - each playthrough reveals different information
+- D-008: Procedural generation for replayability - no two runs identical
+- D-010: Deterministic simulation aids debugging and replay verification
+- D-012: Chunk-based maps - no solvable maps, ensuring fresh exploration each run
+- D-017: Perception modes as playstyle selectors - different builds see different games
+
+## Open Questions Assigned to You
+- Q-010: Storyteller AI architecture (co-lead with Gestalt)
+
+## Current Priorities
+Structural randomness design. Replayability verification of all new systems. Ensure every confirmed decision contributes to meaningful variance across playthroughs. Co-design storyteller AI with Gestalt.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/oscar.md

@@ -0,0 +1,16 @@
+# Oscar - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic. Pre-implementation phase.
+
+## Status
+STANDBY. This briefing will be populated when networking/multiplayer implementation begins.
+
+## Key Decisions for Your Domain
+- D-009: Multiplayer strategy
+- D-010: Four architectural principles - especially client-server architecture and deterministic simulation
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- docs/discussions/ - archived design rounds

docs/briefings/ozzie.md

@@ -0,0 +1,22 @@
+# Ozzie - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-005: Core concept - player experience of asymmetric information and perspective
+- D-008: Action pillar - hubris wall mechanic creating meaningful player consequences
+- D-019: Top-down primary view with future 3D cutscenes
+
+## Open Questions Assigned to You
+None assigned.
+
+## Current Priorities
+Participate in design discussions. Champion player experience during engine evaluation. Ensure all mechanical decisions serve the player's moment-to-moment experience.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/paula.md

@@ -0,0 +1,24 @@
+# Paula - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-005: Asymmetric information as core mechanic driving faction dynamics
+- D-006: Prototype scenario - conspiracy arc with faction manipulation
+- D-013: POI manipulation system - how factions mark and control information
+- D-016: Internal monologue - unreliable narrator reflecting faction allegiances
+- D-018: Sound system - information quality degrades by range, affecting faction awareness
+
+## Open Questions Assigned to You
+- Q-011: Character selection roster for prototype (co-lead with Miri)
+
+## Current Priorities
+Faction and relationship mechanics design. Character roster for prototype scenario. Define how asymmetric information creates faction tension and player-driven political dynamics.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/qatux.md

@@ -0,0 +1,25 @@
+# Qatux - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+All decisions (D-001 through D-019) - maintains DECISIONS.md as the canonical record. Indexes and retrieves decision context for the team.
+
+## Open Questions Assigned to You
+None assigned directly.
+
+## Current Priorities
+1. Maintain DECISIONS.md with any new confirmed decisions after each discussion round
+2. Archive completed rounds to docs/discussions/ when DISCUSSION.md exceeds 3 rounds
+3. Update relevant agent briefing files with new decision references
+4. Re-index changed documents in Qdrant after updates
+5. Verify briefing freshness against DECISIONS.md
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- docs/briefings/ - agent briefing files (you maintain these)
+- TEAM.md - team roster

docs/briefings/si.md

@@ -0,0 +1,20 @@
+# Si - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+All decisions (D-001 through D-019) - manages tickets derived from confirmed decisions.
+
+## Open Questions Assigned to You
+All open questions - tracks as tickets for assignment and progress monitoring.
+
+## Current Priorities
+Set up ticketing workflow. Seed initiatives from D-001 through D-019. Create initial sprint plan for engine selection phase. Coordinate with Team Leader on work priorities. Ensure every confirmed decision has at least one corresponding ticket tracking its implementation.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/stig.md

@@ -0,0 +1,20 @@
+# Stig - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic. Pre-implementation phase.
+
+## Status
+STANDBY. This briefing will be populated when UI implementation begins.
+
+## Key Decisions for Your Domain
+- D-013: Diegetic insert/POI navigation system
+- D-015: Camera locked to character, vision cone
+- D-016: Internal monologue text display
+- D-017: Perception mode overlays
+- D-018: Sound visual indicators (medium range)
+- D-019: Top-down primary view
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- docs/discussions/ - archived design rounds

docs/briefings/tiger.md

@@ -0,0 +1,16 @@
+# Tiger - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic. Pre-implementation phase.
+
+## Status
+STANDBY. This briefing will be populated when localization work begins.
+
+## Key Decisions for Your Domain
+- D-016: Internal monologue system - localization of character voice and personality through text
+- Q-008: Licensing (open question - affects localization scope and supported languages)
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- docs/discussions/ - archived design rounds

docs/briefings/troblum.md

@@ -0,0 +1,21 @@
+# Troblum - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-010: Architectural baseline - four principles to stress-test against engine candidates
+- D-012: Chunk-based map architecture - evaluate engine support and performance
+
+## Open Questions Assigned to You
+- Q-001: Engine selection (sparring partner for Tyre)
+
+## Current Priorities
+Prepare to evaluate engine candidates when Tyre begins Q-001. Research benchmark data, documentation quality, and community health for shortlisted engines. Challenge Tyre's assumptions with hard technical evidence. Ensure no engine is selected without rigorous stress-testing against D-010 and D-012 requirements.
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/briefings/tyre.md

@@ -0,0 +1,38 @@
+# Tyre - Project Briefing
+Last updated: 2026-02-09
+
+## Current Project State
+Commonwealth game: top-down immersive sim, single-character first-person perspective, asymmetric information core mechanic, Rimworld-style storyteller. 19 confirmed decisions, 12 discussion rounds complete. Pre-implementation phase - engine selection (Q-001) is next priority.
+
+## Decisions Relevant to Your Role
+- D-008: Z-levels, LOD, procedural generation - technical architecture implications
+- D-010: Four architectural principles - client-server, deterministic sim, moddable, data-driven (ALL)
+- D-011: LOS shadowcasting implementation for fog of war
+- D-012: Chunk-based map architecture for streaming and generation
+- D-014: v0.1 map specification - full technical requirements
+- D-015: Camera lock to character - vision cone rendering and binaural audio hookup
+- D-017: Perception as observer queries - technical pattern for all perception modes
+- D-018: Sound propagation system - three-range model with wall occlusion
+- D-019: Top-down primary view with potential future 3D client
+
+## Open Questions Assigned to You
+- Q-001: Engine selection (LEAD, CRITICAL - next priority)
+- Q-002: v0.1 scope definition (co-lead)
+- Q-005: Prototype scale (co-lead with Gestalt, Miri)
+- Q-007: Target platforms
+
+## Current Priorities
+ENGINE SELECTION IS NEXT. Hard requirements from confirmed decisions:
+- Client-server architecture (D-010)
+- Deterministic simulation (D-010)
+- Chunk-based maps (D-012)
+- LOS shadowcasting with vision cone (D-011/D-015)
+- Sound propagation (D-018)
+- Observer-based perception queries (D-017)
+- 2D top-down with potential 3D cutscenes (D-019)
+
+## Key Documents
+- DECISIONS.md - all confirmed decisions
+- DISCUSSION.md - active discussion round
+- docs/discussions/ - archived rounds
+- TEAM.md - team roster

docs/discussions/README.md

@@ -0,0 +1,18 @@
+# Discussion Archive
+
+Historical discussion rounds from the Commonwealth game design process.
+
+| Round | Topic | Key Decisions | File |
+|-------|-------|---------------|------|
+| 1 | Opening Positions | - | [round-01](round-01-opening-positions.md) |
+| 2 | Is Stellaris the Right Vehicle? | - | [round-02](round-02-is-stellaris-right.md) |
+| 3 | The Character Gap | - | [round-03](round-03-character-gap.md) |
+| 4 | Build Our Own Game | D-001 | [round-04](round-04-build-our-own.md) |
+| 5 | Is the Team Still Right? | D-003, D-004 | [round-05](round-05-team-still-right.md) |
+| 6 | First-Person Pivot | D-005 | [round-06](round-06-first-person-pivot.md) |
+| 7 | Single Character | D-005, D-006 | [round-07](round-07-single-character.md) |
+| 8 | Action & Spectacle | D-007, D-008 | [round-08](round-08-action-spectacle.md) |
+| 9 | Multiplayer | D-009, D-010 | [round-09](round-09-multiplayer.md) |
+| 10 | Map, Fog & Borderless | D-011, D-012, D-013, D-014 | [round-10](round-10-map-fog-borderless.md) |
+| 11 | Insert, Sound & Camera | D-015, D-016, D-017, D-018 | [round-11](round-11-insert-sound-camera.md) |
+| 12 | Top-Down Final | D-019 | [round-12](round-12-top-down-final.md) |

docs/discussions/round-01-opening-positions.md

@@ -0,0 +1,3 @@
+# Round 1: Opening Positions - "What should this mod BE?"
+
+(See git history for full Round 1 transcript)

docs/discussions/round-02-is-stellaris-right.md

@@ -0,0 +1,159 @@
+# Round 2: "Is Stellaris even the right vehicle?"
+
+**Team Leader (Jeroen):** Before we go further - is Stellaris actually the right game for this?
+
+### MIRI (Lore Expert)
+
+Honestly? This question keeps me up at night. Let me lay out the **friction points** between Hamilton's universe and Stellaris:
+
+**The Commonwealth is mostly ONE civilization.** The books aren't about competing star empires clashing - they're about a single, sprawling human civilization dealing with internal politics, existential threats, and the question of what humanity should become. Stellaris is built around multi-empire competition. That's a fundamental mismatch.
+
+**Characters matter enormously.** Ozzie, Nigel, Paula Myo, Gore, the Waterwalker - these aren't interchangeable leaders. The books are driven by specific people making specific choices across centuries of life. Stellaris leaders are... somewhat disposable.
+
+**The narrative is linear.** There IS a story. The barriers open, MorningLightMountain attacks, the Starflyer is exposed, the Void threatens everything. Stellaris generates emergent narratives - it doesn't tell a specific one well.
+
+**Scale is wrong.** The Commonwealth has ~600 worlds connected by wormholes. That's a mid-game Stellaris empire, not a galaxy of competing powers.
+
+If I'm being brutally honest, the BEST vehicle for the Commonwealth might be something more like **Crusader Kings in space** - dynasty politics, character-driven, with crisis events. But that game doesn't exist.
+
+### OZZIE (Casual Fan)
+
+Counterpoint, Miri: you're overthinking it.
+
+When I imagine playing a Commonwealth game, what do I ACTUALLY picture? I picture zooming out and seeing a galaxy map with wormhole lines criss-crossing it. I picture watching Dyson barriers shimmer. I picture the moment an alert pops up saying the barriers have fallen and hostile fleets are pouring through. I picture building the Deterrence Fleet.
+
+**That's Stellaris.** No other game does galaxy-scale spectacle like Stellaris does. The map, the megastructures, the fleet battles, the crisis escalation - that's all there.
+
+Is it perfect? No. But I'd rather have an imperfect Commonwealth experience in Stellaris than a theoretically perfect one in a game that doesn't exist. Mods are always compromises. The question is whether the compromise is *worth it*.
+
+### PAULA (Hardcore Fan)
+
+I'm somewhere in the middle, but let me complicate this by listing the actual alternatives:
+
+| Game | Strengths for Commonwealth | Weaknesses |
+|------|---------------------------|------------|
+| **Stellaris** | Galaxy map, megastructures, crisis events, modding support, gateways, species mechanics | Weak characters, multi-empire focus, no internal politics depth |
+| **Distant Worlds 2** | Economy depth, civilian ships, more organic feel | Smaller modding community, less spectacle |
+| **Galactic Civilizations IV** | Good diplomacy, cultural influence | Less moddable, less active |
+| **Crusader Kings III** (space total conversion) | Characters! Dynasties! Intrigue! Factions! | Would need total conversion to space - massive undertaking, no space map |
+| **Sins of a Solar Empire II** | Great real-time fleet combat | Too focused on warfare, thin on politics |
+| **Aurora 4X** | Absurd detail, wormhole mechanics | Niche, no modding, terrible UX |
+| **Custom game (Godot/Unity)** | Total control, perfect fit | Years of work before anything playable, need a dev team |
+
+The honest truth: **no existing game is a great fit.** The Commonwealth is a weird universe - it's a space opera where the most important technology is a *door*. Every space 4X assumes ships are the primary vehicle. Hamilton's universe says "why would you fly when you can walk?"
+
+But if I have to pick one... Stellaris has the **largest modding community**, the **best tooling**, and the **most active player base**. A compromised mod that people actually PLAY beats a perfect mod no one ever sees.
+
+### GORE (Transhumanist Fan)
+
+Paula's table is useful but she's missing the real question. It's not "which game simulates the Commonwealth best?" It's **"which game lets us explore the THEMES best?"**
+
+The central theme is: *what does a civilization do when it's solved scarcity and death?*
+
+- Stellaris has ascension paths. It has the concept of transcendence. It has megastructures as expressions of civilizational ambition. It has the Shroud, which is basically Stellaris's own "Void" - a dangerous psychic dimension offering power at a price.
+- The ethics system lets us model the Higher/Advancer/Natural split.
+- The crisis mechanics let us model existential threats from the Void and MorningLightMountain.
+
+**No other moddable game has ascension as a core mechanic.** That's what tips it for me.
+
+But I want to flag something: we should also consider whether this should be **one mod or two**. A "Commonwealth Era" mod (Pandora's Star / Judas Unchained) plays very differently from a "Void Era" mod. The first is about exploration-turned-survival. The second is about post-human politics and cosmic threats. They might map to different Stellaris mechanics entirely.
+
+### GESTALT (Stellaris Mechanics Fan)
+
+Let me get concrete about what Stellaris CAN do that maps to Commonwealth:
+
+**Near-perfect fits:**
+- Gateways → Wormhole network (already in game, just need to make them primary)
+- Megastructures → Dyson barriers (we can create "prison" megastructures)
+- Crisis → MorningLightMountain invasion
+- Determined Exterminator civic → MorningLightMountain playstyle
+- Shroud → Void (psychic dimension with rewards and catastrophic risks)
+- Gene modding → Biononic enhancements / Higher path
+- Synthetic ascension → ANA upload path
+- Espionage → Starflyer infiltration
+- Federations → Commonwealth political structure
+
+**Acceptable fits with modding:**
+- Traditions/Ascension perks → Commonwealth-specific tech paths
+- Edicts/Decisions → Rejuvenation policy, wormhole expansion
+- Archaeology → Anomine/Raiel ruins
+- L-Cluster → Void (isolated space with unique rules)
+
+**Poor fits we'd have to work around:**
+- Hyperlane travel (can be disabled but then AI breaks somewhat)
+- Leader system (too shallow for Hamilton's characters)
+- Planetary management (functional but not evocative)
+- Pop faction system (too simple for Commonwealth politics)
+
+My take: **Stellaris is roughly 65-70% there out of the box.** No other game gets above 40%. The remaining 30% is where the modding work lives, and most of it IS moddable.
+
+### NIGEL (Stellaris Sandbox Fan)
+
+I want to challenge everyone's framing. You're all asking "can Stellaris BE the Commonwealth?" Wrong question.
+
+**The right question: "Can Stellaris let me PLAY IN the Commonwealth?"**
+
+Nobody expects a Lord of the Rings mod for CK3 to literally recreate the books. They expect it to let you exist in Middle-earth and see what happens. The Total War: Warhammer games aren't faithful adaptations of every army book - they're playgrounds.
+
+Stellaris is the best **playground** for the Commonwealth because:
+1. It already thinks in the right scale (galaxy-wide)
+2. It already has the right verbs (expand, research, diplomacy, war, ascend)
+3. Its sandbox nature means players create their OWN Commonwealth stories
+4. The modding community is massive and experienced
+
+The character stuff Miri worries about? That's what **event chains** are for. We write scripted narrative moments that fire at the right times. The Starflyer revelation. The barrier opening. The first contact with MorningLightMountain. Between those tentpole events, the sandbox does its thing.
+
+**Stellaris isn't the perfect vehicle. It's the only realistic one.**
+
+### TYRE (Modding Expert)
+
+Time for the technical verdict.
+
+**Stellaris modding maturity:** 10 years of modding tools, documentation, and community knowledge. There are total conversion mods (Star Trek: New Horizons, 40K mods) that prove you can radically reshape the game. The mod tools are well-documented, actively maintained, and Paradox generally doesn't break mods on purpose.
+
+**Alternatives from a modding perspective:**
+- Distant Worlds 2: modding is growing but still immature
+- GalCiv IV: XML modding, limited scope
+- CK3 space conversion: someone would need to build the space map from scratch - that's a separate project before we even start
+- Custom game: 2-5 year dev cycle before you have anything playable
+
+**The decisive factor:** In Stellaris, we can have a **playable prototype in weeks**, not years. Custom origins, prescripted empires, a few event chains, modified gateways - that's a version 0.1 that people can download and try. Every other option has a much longer time-to-playable.
+
+**My verdict: Stellaris, with eyes open about the compromises.**
+
+The biggest technical risk is the hyperlane/wormhole issue. Stellaris AI is tuned for hyperlanes. If we force a wormhole-only galaxy, the AI may struggle. We need to test this early and decide how far we push it.
+
+### SCRIBE (Documenter)
+
+**ROUND 2 SUMMARY:**
+
+**Question:** Is Stellaris the right vehicle?
+
+**Consensus emerging:** Yes, with caveats. Nobody thinks it's perfect, but every agent agrees (or concedes) it's the most *practical* choice.
+
+| Argument FOR Stellaris | Raised by |
+|----------------------|-----------|
+| Best galaxy-scale spectacle | Ozzie |
+| Largest modding community & tooling | Paula, Tyre |
+| Ascension mechanics already exist | Gore |
+| 65-70% mechanical fit out of the box | Gestalt |
+| Sandbox = playground, not adaptation | Nigel |
+| Fastest path to playable prototype | Tyre |
+
+| Argument AGAINST / Risk | Raised by |
+|------------------------|-----------|
+| Commonwealth is one civ, not competing empires | Miri |
+| Characters are too shallow | Miri, Paula |
+| Hyperlane AI may break with wormhole-only | Tyre, Gestalt |
+| Internal politics modding is limited | Paula, Gestalt |
+| Might need two mods (Commonwealth era vs Void era) | Gore |
+
+**KEY DECISION NEEDED:**
+
+The team leans Stellaris but wants the Team Leader to confirm before committing. Also:
+
+1. **One mod or two?** Gore raises a good point about Commonwealth vs Void eras being very different games.
+2. **How hard do we push against Stellaris's grain?** Specifically: do we force wormhole-only travel (lore-accurate but AI-risky) or keep hyperlanes and add wormholes on top?
+3. **Content pack or total conversion?** This changes the scope dramatically.
+
+*Awaiting Team Leader direction.*

docs/discussions/round-03-character-gap.md

@@ -0,0 +1,23 @@
+# Round 3: "The character gap is a dealbreaker for Stellaris"
+
+**Team Leader (Jeroen):** I have doubts along exactly the thin character space lines. I've played the New Horizons mod a lot - it has far more surface area to connect with Stellaris in the source material and even there, it fails on connecting with characters. This sounds even harder to get to vibe properly. CK3 in space would be good, but ideally we'd have CK3 with Stellaris map systems. CK3's map fails the complexity needed for Commonwealth.
+
+### TYRE (Technical Architect)
+
+There's a third option nobody's mentioned: **Victoria 3.** Vic3 is all about internal politics, pops with ideologies, interest groups pulling your government in different directions, economic pressure driving political change. The map is wrong but the *systems* are closer to what the Commonwealth actually needs.
+
+### PAULA (Narrative & Political Depth)
+
+The Commonwealth books are fundamentally about *what happens inside a civilization*, not between civilizations. CK3 gets the characters right but the map wrong. Stellaris gets the map right but the characters wrong. Vic3 gets the *society* right but it's planet-bound.
+
+### GORE (Themes & Endgame)
+
+What if we stop looking for ONE game? What if the answer is a Stellaris mod that deliberately leans into what Stellaris does well and doesn't try to be the character game at all? Accept that characters will be delivered through event chain *writing* rather than mechanics. New Horizons works not because Stellaris simulates Kirk well, but because the events tell stories while the sandbox does the galaxy stuff.
+
+### NIGEL (Sandbox & Replayability)
+
+Or flip the whole thing. What if the mod isn't about playing AS Nigel Sheldon or Paula Myo? What if you play as a **Commonwealth dynasty** - the Burnellis, the Halgarths, the Sheldons - and the named characters show up as event-chain actors who do things TO your game? You're steering a family's influence across centuries, and the big canon events are storms you navigate.
+
+### SCRIBE (Documenter)
+
+Nigel's dynasty framing is interesting because it works with Stellaris's leader system rather than against it - your leaders ARE your dynasty members, they live forever via rejuvenation, and the book characters are external forces. But the Team Leader's New Horizons experience suggests even this approach may not be enough.

docs/discussions/round-04-build-our-own.md

@@ -0,0 +1,43 @@
+# Round 4: "What if we build our own game?"
+
+**Team Leader (Jeroen):** Here's a spanner for the works - what if we make our own game?
+
+### OZZIE (Player Experience)
+
+Forget the blackjack, I'm in.
+
+### TYRE (Technical Architect)
+
+Six months ago I'd have said "absolutely not, you need a team of 10 and 3 years." But AI-assisted development has changed the calculus. The key questions become: engine choice (Godot?), scope floor (galaxy map + entity management + UI + save/load + AI at minimum), and the actual advantage - we can build EXACTLY the CK3-meets-Stellaris hybrid with wormhole-first travel and no fighting someone else's assumptions.
+
+### PAULA (Narrative & Political Depth)
+
+If we build our own thing, rejuvenation becomes a *core system* instead of a bolted-on modifier. Centuries-old characters with accumulated relationships, grudges, alliances. THAT'S the Commonwealth.
+
+### MIRI (Lore Expert)
+
+This solves every lore complaint I had. But are we making a *Commonwealth game* or a *game engine that could support the Commonwealth*? Those are very different projects.
+
+### GORE (Themes & Endgame)
+
+Miri's right. The smart play: build a character-driven space grand strategy *framework*, Commonwealth as the first campaign/scenario. Not locked into one IP.
+
+### GESTALT (Systems Design)
+
+Two-layer map: galaxy view (systems as network graph connected by wormhole lines) and abstracted planet view. Character system at the core - centuries of life, accumulated traits, relationships driving events. Society layer with real factions, not just opinion bars.
+
+### MIRI (Lore Expert)
+
+Commonwealth-specific: the wormhole *economy*. Planets connected by routes owned by CST or rivals. Opening a new route is a huge play - land rights, resource claims, political capital. Closing a route is an act of war.
+
+### GORE (Themes & Endgame)
+
+Endgame isn't "do you win" - it's "what does your dynasty become?" Stay natural, go Higher, upload to ANA, pursue the Void, walk the Silfen paths. Each changes how the game plays.
+
+### TYRE (Technical Architect)
+
+Think smaller than Stellaris, deeper than CK3. 50-100 star systems, 20-50 active characters. Event-driven narrative with sandbox consequences. Art style can be clean and diagrammatic - the galaxy map is essentially a network graph, which is actually *easier* to build than Stellaris's 3D map.
+
+### PAULA (Narrative & Political Depth)
+
+The opening vibe: You're the Burnelli family, 2350. Controlling interest in three wormhole routes, a Senate seat, a 380-year-old matriarch. An election is coming. The Guardians of Selfhood are making noise about an alien infiltrator. A rival dynasty just opened a route to something weird. Your youngest wants to join the navy. Your oldest wants to defund it. *That's* the game.

docs/discussions/round-05-team-still-right.md

@@ -0,0 +1,17 @@
+# Round 5: "Is the team still right for this?"
+
+**Team Leader (Jeroen):** Confirms the vision. 30 years software dev / systems & cloud architect, with Claude Code 20x. Lots of planning, engine choosing, and feature defining needed before we're anywhere near building. Stellaris fans - are you onboard or should we swap you out?
+
+### GESTALT (formerly Stellaris Mechanics Fan)
+
+I was always a *mechanics* fan, not a Stellaris loyalist. Everything I care about - ethics systems, pop dynamics, meaningful strategic choices - I want done *better*. I'm staying. Rebrand me: **Systems Designer.** I ask "is this fun?" and "does this create interesting decisions?" regardless of engine.
+
+### NIGEL (formerly Stellaris Sandbox Fan)
+
+Same. Replayability and emergent stories matter MORE in a custom game because we're not leaning on Paradox's sandbox as a crutch. I'm your **Sandbox & Replayability advocate.**
+
+### SCRIBE (Documenter)
+
+Team confirmed. No departures. Gestalt and Nigel rebranded with updated roles. See TEAM.md and DECISIONS.md for confirmed decisions D-001 through D-004, plus 8 open questions queued.
+
+*Awaiting Team Leader direction on next topic: engine selection, core mechanics, scope, or other.*

docs/discussions/round-06-first-person-pivot.md

@@ -0,0 +1,71 @@
+# Round 6: "First person. Asymmetric information. The apple cart tips over."
+
+**Team Leader (Jeroen):** What if the player is a first-person character? Think X4, but less Eve-spreadsheety.
+
+### OZZIE (Player Experience)
+
+You walk through the wormhole. You *physically walk through it.* That's the book. That's literally how Hamilton writes it.
+
+### PAULA (Narrative & Political Depth)
+
+This changes everything. Political intrigue works because you're IN the room, sitting across from a senator who might be Starflyer-compromised and reading their face. That doesn't work from a galaxy map. It works from across a table.
+
+### MIRI (Lore Expert)
+
+Checked against the source material - the books ARE experienced first-person. You walk through wormholes, sit in meetings, investigate, occasionally fly a ship and it's exceptional. Hamilton writes close third-person POV for a reason. The universe IS experienced through individuals.
+
+### GESTALT (Systems Design)
+
+The four pillars don't break - they reframe. You're not a god-cursor, you're a piece that moves itself. Player decisions become: Where do I physically go? Who do I meet? What do I advocate for? How do I spend this decade?
+
+### GORE (Themes & Endgame)
+
+Ascension becomes visceral. Going Higher isn't clicking a tech tree button. It's your character choosing biononic implants. Uploading to ANA is YOU leaving your body.
+
+### NIGEL (Sandbox & Replayability)
+
+Replayability explodes. You're replaying a *life*. Be a Sheldon industrialist, a Paula Myo investigator, a Silfen path-walker, an Ozzie-style wanderer.
+
+### TYRE (Technical Architect)
+
+The scope risk goes up but asymmetric information actually *reduces* rendering needs. If the player only sees what their character knows, we don't simulate the whole galaxy in detail. The hard part shifts from "simulate a galaxy" to "make the keyhole view compelling." Think Dwarf Fortress adventure mode - rich world model, experienced through a keyhole.
+
+### GORE (Themes & Endgame)
+
+What we're describing isn't grand strategy. It isn't an RPG exactly. It's an **immersive sim set in a political space opera**. Closest references: Disco Elysium meets Sunless Skies meets King of Dragon Pass.
+
+**Team Leader (Jeroen):** The strength is asymmetric information. How you deal with information, system interaction, and powerfully the fact that it can get obscured. Not easy, incredibly exciting.
+
+### PAULA (Narrative & Political Depth)
+
+Asymmetric information IS the Starflyer conspiracy. Guardians screaming about an infiltrator and everyone thinks they're cranks. If you're god-view, you know or you don't - binary, boring. If you're a character, you hear rumors, find evidence that doesn't add up, might be WRONG.
+
+### MIRI (Lore Expert)
+
+This is the single mechanic that makes the scope explosion *worth it*. Nobody knows what's behind the Dyson barriers. The Starflyer has manipulated humanity for a century. Different dynasties have different intelligence. Even rejuvenation creates information asymmetry - a 400-year-old has context a 30-year-old doesn't.
+
+### GESTALT (Systems Design)
+
+Every pillar changes. Relationships become *information channels*. Your ally tells you things, your rival withholds, someone lies. The wormhole network: you only know what's on worlds you've visited. Factions: you can't see strength as a number, you feel it. Crises: MorningLightMountain isn't announced by a popup - reports trickle in, conflicting, panic, denial, THEN the picture.
+
+### TYRE (Technical Architect)
+
+Rimworld comparison raised by Team Leader. Rimworld's storyteller model maps perfectly: AI selects events for dramatic pacing, not simulation logic. Characters as bundles of traits interacting with systems. Randomization creates replayability. And critically - simple 2D presentation, depth in the simulation not the graphics. This is buildable.
+
+**Team Leader (Jeroen):** Prototype scope: Institute / Armstrong City / Guardians. Controllable scope, maximum asymmetry. Also: randomized outcomes - how close to Rimworld can we get?
+
+### GESTALT (Systems Design)
+
+Rimworld mapping: AI Storyteller → Commonwealth Storyteller pacing conspiracy/crises. Colonist traits → character traits/suspicion/loyalty over decades. Random events → rumors, leaks, assassinations, discoveries. Colony management → dynasty asset management. Simple 2D presentation → same, depth in systems not graphics.
+
+### GORE (Themes & Endgame)
+
+Two layers of randomness needed: (1) structural - who's compromised, where evidence is, which factions are strong, set at game start like a map seed. (2) dramatic - storyteller deciding WHEN things happen based on pacing. The Starflyer always exists. But who it controls and when things unravel is randomized. Same truth, different mystery.
+
+### TYRE (Technical Architect)
+
+This is buildable. 2D/2.5D, systems-driven, Godot-capable. A prototype with a single location network, 10-20 characters, one storyteller arc could be built and tested. It proves or disproves the core concept.
+
+### OZZIE (Player Experience)
+
+"Investigative political sim set in a space opera where the conspiracy theorists are right" - I'd play this even without Commonwealth branding.

docs/discussions/round-07-single-character.md

@@ -0,0 +1,25 @@
+# Round 7: "Single character. Pick and play."
+
+**Team Leader (Jeroen):** This is a single character selection, take it from there game.
+
+### GESTALT (Systems Design)
+
+Clean. One character, one perspective, one life. A Paula Myo playthrough is a completely different game from a Gore Burnelli playthrough - not because the plot branches, but because you're standing in a different place with different information, access, and leverage.
+
+### NIGEL (Sandbox & Replayability)
+
+Replayability without engineering it. One rich world-state that looks completely different depending on which keyhole you're looking through.
+
+### MIRI (Lore Expert)
+
+Character selection becomes the most important screen. Each character implies: starting location, starting knowledge, available levers (political/investigative/economic/military), and personal goals that may conflict with the big picture. A Guardian operative starts knowing the Starflyer is real but nobody believes them. A Senate insider has power but no idea they're being manipulated. A CST engineer sees anomalies in the wormhole data.
+
+### TYRE (Technical Architect)
+
+Most achievable version of the vision. One character means one camera, AI handles all other characters as NPCs, no dynasty management UI for v1, simulation only needs depth where the player is looking.
+
+### SCRIBE (Documenter)
+
+Confirmed as D-005 (superseding D-002) and D-006 (prototype scenario). See DECISIONS.md. Concept has evolved from grand strategy → first-person story generator with asymmetric information as core mechanic.
+
+*Awaiting Team Leader direction. Next candidates: core mechanics deep-dive (Gestalt's four pillars through the first-person lens), engine selection, or prototype character roster.*

docs/discussions/round-08-action-spectacle.md

@@ -0,0 +1,61 @@
+# Round 8: "The fifth pillar - Action & Spectacle"
+
+**Team Leader (Jeroen):** Rimworld was originally designed as a shooter, and still benefits from that pedigree. With all the story/politics/information direction this game has, it still needs to come to spectacular, epic fight situations at times. Another pillar.
+
+### OZZIE (Player Experience)
+
+THANK YOU. When does something explode?
+
+### PAULA (Narrative & Political Depth)
+
+The Commonwealth books aren't all Senate meetings. The assault on the Starflyer's base. Cat's Claws running black ops. MorningLightMountain's forces hitting Commonwealth worlds. Personal combat with enhanced humans. The Deterrence Fleet. These aren't cutscenes.
+
+### GESTALT (Systems Design)
+
+Fifth pillar accepted: **Action & Spectacle** - what happens when talking stops working. Rimworld's combat works because stakes are personal. That colonist isn't a unit counter - it's someone you've invested 40 hours in. We already have that because the character IS you. The other four pillars CREATE the situations. Pillar five is what happens when they boil over. The combat isn't the game loop - it's the punctuation.
+
+### MIRI (Lore Expert)
+
+Maps to the source material at three scales: personal (enhanced human fights, biononic combat), tactical (Cat's Claws ops, Guardian raids, Starflyer assault), and cataclysmic (MorningLightMountain invasion, planets falling). Critically - violence in the books is usually a failure state that leads to more interesting situations. The Starflyer War starts because someone opened a door they shouldn't have.
+
+**Team Leader (Jeroen):** Completely agree with Tyre that this can remain simple - simple will get complicated fast. Somewhere between Rimworld and XCOM. Needs Z-levels (floors, not 3D rendering), multiple maps, LOD/occlusion to reduce what happens outside your view. Maps need to feel large, locations varied, through trickery or procedural generation or both. The action pillar scales with ascension but allows for insane asymmetry too. The books are not always balanced. The fun pops out when a character hits their hubris wall.
+
+### GESTALT (Systems Design)
+
+The hubris wall. That's the design principle for the whole pillar. Your biononic Higher walks through a room of baseline humans like they're not there. Then you walk into a room with MorningLightMountain combat drones and suddenly YOU'RE the baseline.
+
+### TYRE (Technical Architect)
+
+Technical breakdown:
+- **Z-levels:** Dwarf Fortress does this, Rimworld doesn't. Significant complexity jump but transforms spaces into *places*. Armstrong City hab-tower, CST station with maintenance tunnels below and executive suites above. You're on floor 12, firefight breaks out on floor 3, you hear it before you see it. Asymmetric information applied to ACTION.
+- **Multiple maps/locations:** Needed anyway for the wormhole network. Step through a gate, new location, own map. Each independent - don't need all loaded simultaneously.
+- **LOD/occlusion:** "You only know what your character perceives" = information boundary = rendering boundary. Simulation runs abstractly offscreen, full detail only where player is present. Design principle AND performance optimization are the same thing.
+- **Procedural generation:** Templates + procedural flesh. "CST station" generates differently from "Armstrong City residential" from "Guardian safehouse." Hand-craft only what matters narratively. Also feeds replayability - layouts differ per playthrough.
+
+### OZZIE (Player Experience)
+
+The hubris wall is what makes the books page-turners. Nigel Sheldon is basically a god - invented wormhole tech, centuries of experience. Dyson barriers open and NONE of that matters. The game should let you succeed easily for a while. Lull you. Then the storyteller drops something that completely recontextualizes your power level.
+
+### GESTALT (Systems Design)
+
+XCOM does this at the tactical level - dominating a mission, trigger a new pod, everything's sideways. We want that but driven by narrative stakes. You kick down a door expecting three Starflyer agents and there's a Prime combat construct. Your biononics are useless. Run or die. That moment happened because of investigation choices three hours ago.
+
+### PAULA (Narrative & Political Depth)
+
+Power levels in the books are WILDLY uneven. Paula Myo vs a street criminal is a joke. Paula Myo vs a Cat's Claw operative is tense. Paula Myo vs something MorningLightMountain fielded is terrifying. The system needs to handle all three. XCOM's scaling does this okay. Rimworld's "one lucky shot kills anyone" does it better for tension.
+
+### GORE (Themes & Endgame)
+
+Ascension makes asymmetry vertical over time. Early game: baseline, every fight dangerous. Mid game: Higher, most threats manageable but real ones scarier because stakes are higher. Late game: if you've gone ANA, what does combat even MEAN?
+
+### MIRI (Lore Expert)
+
+Lore note - Commonwealth technology means almost nobody actually *dies* permanently. Memory cell implants back up consciousness. Body destroyed = re-lifed from last backup. Death isn't the consequence - **lost time and lost information is.** You wake up missing everything since last backup. What did you learn? Who did you meet? What deal did you make?
+
+### GESTALT (Systems Design)
+
+...that's a GAME MECHANIC. Death isn't game over. Death is losing your recent save - but in-fiction. You lose acquired information, relationships built since last backup. The storyteller KNOWS what you've lost. It can exploit that.
+
+### SCRIBE (Documenter)
+
+Confirmed as D-007 (five pillars) and D-008 (action pillar design principles). See DECISIONS.md. The five pillars are now: (1) Characters & Information, (2) Wormhole Network, (3) Society & Factions, (4) Crisis & Storyteller, (5) Action & Spectacle.

docs/discussions/round-09-multiplayer.md

@@ -0,0 +1,56 @@
+# Round 9: "Multiplayer?"
+
+**Team Leader (Jeroen):** Multiplayer? Or no...
+
+### TYRE (Technical Architect)
+
+Not for v1. Asymmetric information + multiplayer is incredible but doubles engineering on everything. Networking, sync, anti-cheat on hidden info, pacing for multiple players...
+
+### NIGEL (Sandbox & Replayability)
+
+But: two players in the same world who don't know what each other knows? Senate insider + Guardian operative, same conspiracy, opposite sides, neither knows if the other is ally or threat?
+
+### PAULA (Narrative & Political Depth)
+
+That's a social deduction game embedded in an immersive sim. Extraordinary.
+
+### GESTALT (Systems Design)
+
+Also a completely different design problem. Single-player: storyteller controls pacing. Multiplayer: PLAYERS create pacing. Storyteller becomes referee, not director.
+
+### TYRE (Technical Architect)
+
+Design for it, don't build it yet. Make architectural decisions that don't prevent multiplayer: client-server separation even in single-player, first-class information boundary system, no baked-in player identity, deterministic simulation with input events. Actual networking/matchmaking is a milestone way down the road.
+
+### GORE (Themes & Endgame)
+
+"Two players experiencing the same conspiracy from different keyholes" is a killer market-defining feature. It just can't kill the project by being too early.
+
+**Team Leader (Jeroen):** Tyre is right, but we have to beware that adding multiplayer later is one of the hardest things to do.
+
+### TYRE (Technical Architect)
+
+Absolutely right. "We'll add multiplayer later" is the graveyard of a thousand indie games. "Design for it" means concrete architectural commitments from day one:
+
+1. **Client-server separation** - even in single-player. Simulation = server, player view = client. Single-player is local client + local server.
+2. **Information boundaries as first-class system** - every piece of game state tagged with who knows it. Needed for single-player asymmetric info anyway. Multiplayer = multiple observers.
+3. **No baking player identity** - simulation doesn't know there's "the player." It knows characters, some player-controlled. Second player = configuration change, not rewrite.
+4. **Deterministic simulation with input events** - state advances on timestamped actions, not local calculation. Enables sync later.
+
+Cost: ~15-20% slower single-player dev. But the alternative is throwing away the codebase when we want multiplayer.
+
+### NIGEL (Sandbox & Replayability)
+
+Every one of those decisions makes single-player BETTER. Information boundaries = smarter NPC AI. Client-server = cleaner save/load. Deterministic simulation = easier debugging. No sacrifice.
+
+### GESTALT (Systems Design)
+
+This also becomes a hard requirement on engine selection. Some engines make client-server trivial, others make it a nightmare.
+
+**Team Leader (Jeroen):** Sound architectural baseline, Tyre.
+
+### SCRIBE (Documenter)
+
+Confirmed as D-009 (multiplayer strategy) and D-010 (architectural baseline). These four principles are non-negotiable from first line of code. Engine selection (Q-001) now has an additional hard requirement: client-server friendliness.
+
+*Session paused. Team Leader signing off for the night. Next session candidates: deep dive on individual pillars, engine selection (now with D-010 constraints), prototype character roster, or v0.1 scope definition.*

docs/discussions/round-10-map-fog-borderless.md

@@ -0,0 +1,88 @@
+# Round 10: "Map size, fog, and borderless generation"
+
+**Team Leader (Jeroen):** Morning, team. What will we aim for map-wise for the first playable version?
+
+### MIRI (Lore Expert)
+
+Grounding in source: the Starflyer conspiracy plays across Earth (Senate, institutions), Augusta (CST hub, wormhole nexus), and various colony worlds (Guardian hideouts, evidence surfaces). We don't need the whole Commonwealth - enough to feel its shape.
+
+### NIGEL (Sandbox & Replayability)
+
+Three worlds for the prototype, each with a distinct vibe:
+1. **The Hub** (Augusta-inspired) - CST operations, commercial, transit. Access but exposure.
+2. **The Capital** (Earth-inspired) - Senate, Institute/Serious Crimes, dynasty estates. Power and information.
+3. **The Fringe** (colony world) - Guardian territory, less oversight, more freedom. Where evidence surfaces.
+
+### PAULA (Narrative & Political Depth)
+
+The conspiracy thread runs ACROSS all three. Evidence on the Fringe. Power to act in the Capital. Infrastructure being manipulated at the Hub. No single location has the full picture. You have to move. Things happen where you aren't.
+
+### TYRE (Technical Architect)
+
+Proposed two-layer structure: world map (node graph) + local maps (top-down Rimworld-style). Initially proposed 30x30 tiles per local map.
+
+**Team Leader (Jeroen):** I'm not sure how 30x30 tiles relate to size and freedom. It feels too cramped - the only thing in it will immediately be what you're looking for.
+
+### GESTALT (Systems Design)
+
+Correct. 30x30 is a Rimworld colony - you KNOW where everything is because you placed it. Our game is the opposite: navigating spaces you don't know, looking for things you're not sure exist. At 30x30 you see everything in seconds. No discovery, no "I chose docks instead of residential and missed the meeting." Information asymmetry collapses at small scale.
+
+### TYRE (Technical Architect)
+
+Reframed: the question is "how long to cross, and what do you miss going one way?" Sweet spot: 5-10 minutes real-time to cross full map. Distinct neighborhoods. Contacts/tips valuable because they tell you WHERE to look. In tile terms: ~150-200 tiles across. Most is procedural atmosphere. Interactable content density stays the same - just embedded in larger space creating friction of distance.
+
+### PAULA (Narrative & Political Depth)
+
+That friction IS the mechanic. "Guardian contact is somewhere in the lower docks, searching costs an evening" = real decision. What else could you do tonight?
+
+### OZZIE (Player Experience)
+
+Large maps with ambient life = free atmosphere. Crowded markets, overheard conversations, news screens, bars with possible contacts. The atmosphere IS the gameplay surface.
+
+**Team Leader (Jeroen):** I'm on board with 150x150 mostly ambient for the first tech demo. But I'd want to consider making it more akin to borderless generation like Minecraft, with a good POI/insert map system so people anchor by desire, not by force.
+
+**Also:** Fog. I was thinking about this in bed. We're missing on information asymmetry by going top-down. Fog kinda solves that, but not the way first-person view would. Fog is the minimum requirement for this to feel alive in the right way, not an extra feature.
+
+### GESTALT (Systems Design)
+
+Fog isn't a feature. Fog is the TAX we pay for choosing top-down instead of first-person camera. First-person gets asymmetry for free - can't see behind you. Top-down is omniscient within viewport unless we actively take that away. Without fog, the entire information pillar collapses locally. Fog is pillar 1 infrastructure.
+
+### TYRE (Technical Architect)
+
+On borderless generation: fixed maps are "solvable" - walk every tile, mystery dies. Borderless means effectively infinite, can never solve it, mystery is permanent. For v0.1 keep bounded 150x150 but use chunk-based generation from day one. Bounded map = "only generate within this boundary." Removing boundary later = configuration change, not rewrite. Same principle as D-010.
+
+### MIRI (Lore Expert)
+
+The insert/POI system is CANON. Commonwealth citizens have **inserts** - neural implants connecting to the **unisphere**. Built-in navigation, messaging, data access. The map screen IS your character checking their implant. POIs appear because someone told you, you researched them, or your credentials gave you access. Different characters see different POIs - a cop sees case-flagged locations, a Guardian sees safehouses, a Senator sees political venues. Same city, different map.
+
+### PAULA (Narrative & Political Depth)
+
+Contacts can SEND you POIs. "Meet me here" drops a pin. Tips can be traps. The POI system becomes an information channel that can be manipulated.
+
+### GESTALT (Systems Design)
+
+Navigation summary: start knowing very little. Learn places by being told, researching, or discovering. POIs decay/update. Anchoring by desire - the insert gives reasons to go places without funneling. Anti-Ubisoft: no tower-climbing icon reveals. Map fills at investigation pace.
+
+**Team Leader (Jeroen):** Confirm all four decisions. Is fog line-of-sight?
+
+### TYRE (Technical Architect)
+
+It should be. Radius fog = see X tiles regardless of obstacles. LOS fog = walls block vision, can't see around corners, buildings create blind spots, z-levels matter for sightlines. For this game, LOS is the only option:
+- Corners/doorways become information boundaries
+- Buildings opaque from outside
+- Z-levels interact with vision (balcony = surveillance, basement = hiding)
+- Action pillar needs it (hear gunfire two blocks away, don't know the situation)
+
+Implementation: shadowcasting algorithms, well-documented and efficient (Cogmind, Caves of Qud, every good roguelike). v0.1: 2D shadowcast per z-level, vertical LOS deferred.
+
+### GESTALT (Systems Design)
+
+Sound becomes a mechanic. Hear things outside LOS - footsteps, conversations, alarms, gunfire. Partial/directional information. "Something is happening THAT way, roughly THAT far." Decide whether to investigate on incomplete data. The game working at every scale.
+
+### PAULA (Narrative & Political Depth)
+
+LOS applies to NPCs too. They can't see you = don't know you're there. They SAW you enter = infer you're inside. Same perception system for everyone. Ties to D-010 principle 2: information boundaries are universal.
+
+### SCRIBE (Documenter)
+
+Confirmed as D-011 (fog as non-negotiable), D-012 (chunk-based architecture), D-013 (diegetic insert/POI system), D-014 (v0.1 map spec). Engine selection Q-001 now has additional hard requirements: shadowcasting support, chunk-based loading.

docs/discussions/round-11-insert-sound-camera.md

@@ -0,0 +1,83 @@
+# Round 11: "Insert minimap, sound direction, and the camera question"
+
+**Team Leader (Jeroen):** Insert system needs a rudimentary version from the start for anchoring. A minimap with a dot when close and border arrow when far might be enough. How do we do directional sound - can't go binaural since that needs first-person view to map to.
+
+### GESTALT (Systems Design)
+
+Minimap with dots + border arrows is clean and enough for v0.1. Dots/arrows only for KNOWN POIs. Start with two arrows. Learn more, more appear. The minimap visually represents growing familiarity.
+
+### PAULA (Narrative & Political Depth)
+
+POI indicators should differ by how you learned them. Official records look different from whispered tips look different from physical discovery. Trust level baked into UI.
+
+### TYRE (Technical Architect)
+
+Proposed four options for sound direction. Team converged on hybrid three-range model: stereo for close, visual indicators for medium, insert notifications for long range. Each range = different information quality and trust level.
+
+### GESTALT (Systems Design)
+
+Close range: raw sensory, high accuracy. Medium range: directional impression, vague. Long range: network-filtered, possibly delayed, possibly wrong. Each range is different information QUALITY, not just distance.
+
+### MIRI (Lore Expert)
+
+Long-range insert feeds are diegetic AND manipulable. The Starflyer's people would spoof sensors, feed false alerts. Your long-range awareness is only as trustworthy as the network.
+
+**Team Leader (Jeroen):** I think I love the idea of internal monologue. It creates atmosphere, tension, and tutorial options. Also: should the camera be pannable at all? I think it should lock to the character, and maybe even rotate to where the character is facing (player option in later version).
+
+### GESTALT (Systems Design)
+
+Camera lock - absolutely. Pannable camera breaks the information model. You become a surveillance drone, not a character.
+
+### TYRE (Technical Architect)
+
+Camera rotation with character facing gives us binaural audio BACK. Screen now has consistent orientation relative to character. Left speaker = left of character. And it gives us a vision cone: forward = full LOS, peripheral = reduced, behind = blind. You can be snuck up on.
+
+### OZZIE (Player Experience)
+
+That's Hotline Miami. That camera made that game terrifying.
+
+### PAULA (Narrative & Political Depth)
+
+Internal monologue maps to the vision cone. Things you sense but can't see get narrated. *"Footsteps behind me. Two people, unhurried."* The monologue IS the perception layer for everything the camera doesn't show.
+
+### MIRI (Lore Expert)
+
+This is how Hamilton writes. Close third-person POV, constantly inside a character's head. They notice things, make assumptions, are wrong sometimes.
+
+### GORE (Themes & Endgame)
+
+Diegetic tutorials via monologue. Character THINKS hints. *"That terminal might have access logs."* No "press X" popups. New players guided by character instincts.
+
+### PAULA (Narrative & Political Depth)
+
+Monologue can be WRONG. Unreliable narrator. *"Seems quiet. Safe to move."* It wasn't safe. Character's interpretation, not ground truth. Gold for a conspiracy game.
+
+### NIGEL (Sandbox & Replayability)
+
+Cheapest feature on the list - it's text. AI-assistable generation, character-specific variants. Paranoid Guardian vs confident Senator = different monologue = different experience.
+
+**Team Leader (Jeroen):** Love the character build aspect on the FoW. Also thermal vision, visual hacks into cameras etc.
+
+### GESTALT (Systems Design)
+
+Perception loadout system. Multiple perception modes per character build: natural vision, thermal (through walls, no identity), camera feeds (remote, spoofable), unisphere tracking (location pings, maskable), audio analysis (sound classification, trainable).
+
+### TYRE (Technical Architect)
+
+Each mode is just another observer query against the information boundary system (D-010). Engine doesn't distinguish eyes from thermal from camera feed - all are "given this sensor, what's visible?"
+
+### PAULA (Narrative & Political Depth)
+
+Camera hacking is gold for conspiracy. Watch a hallway remotely. See target enter a room. No camera in the room. Or worse - someone loops the feed. You think it's empty. It's not.
+
+### GORE (Themes & Endgame)
+
+Ascension scales perception vertically. Baseline: eyes + gear. Enhanced: insert modes. Higher: biononic thermal/scanning. ANA-touched: pattern recognition across all feeds, predictive awareness.
+
+### NIGEL (Sandbox & Replayability)
+
+Low-tech Guardian = survival horror (blind, paranoid). Senator = information overload (cameras everywhere, can't find what matters). Perception modes are playstyle selectors.
+
+### SCRIBE (Documenter)
+
+Confirmed as D-015 (camera lock), D-016 (internal monologue), D-017 (perception modes), D-018 (three-range sound). D-014 updated with camera/perception/monologue specs for v0.1.

docs/discussions/round-12-top-down-final.md

@@ -0,0 +1,55 @@
+# Round 12: "Final gut-check on top-down vs first-person"
+
+**Team Leader (Jeroen):** One last challenge before we lock it in. What are we missing out on fun/immersion-wise if we don't go first-person? I'm set on the choice, just have a nagging doubt.
+
+### OZZIE (Player Experience)
+
+Honest answer: first-person would be more immersive in the moments that matter most. Walking through a wormhole. Sitting across from a liar. Peeking around a corner in a firefight. The terror of hearing footsteps behind you. These are visceral in first-person. In top-down they're abstracted. We're losing something real.
+
+### PAULA (Narrative & Political Depth)
+
+Conversation scenes. Disco Elysium works partly because you SEE the person. Body language, the way someone shifts when pushed on a lie. Top-down, it's two sprites and a text box.
+
+### MIRI (Lore Expert)
+
+Walking through the wormhole. In the books it's a sensory experience - light changes, air smells different, gravity shifts. Top-down, it's a loading screen between maps.
+
+### GORE (Themes & Endgame)
+
+Ascension moments. Going Higher should feel like senses expanding. First-person could literally render new visual spectrums. Top-down, it's a stat change.
+
+### TYRE (Technical Architect)
+
+Now the cost column: 3D environments = months before testing a single mechanic. Tactical awareness dies in first-person. Political/strategic layer fights with the camera. NPC simulation becomes invisible. Time-to-prototype multiplies 5-10x.
+
+### GESTALT (Systems Design)
+
+The fun of this game is SYSTEMS INTERACTING. See character enter building → check insert → thermal scan → monologue fires → mental note → later exploit camera hack. That sequence is BETTER top-down because you observe multiple layers simultaneously. First-person shows you a building facade and nothing else.
+
+### PAULA (Narrative & Political Depth)
+
+Actually... the conversation thing? Monologue solves it differently. First-person shows a face. Monologue shows your character's INTERPRETATION. *"She's lying. The micro-expressions are wrong - I've seen this pattern, centuries ago."* That's richer. And more faithful to Hamilton - he writes what characters THINK about faces, not what faces look like.
+
+### TYRE (Technical Architect)
+
+Architecture supports a first-person client later. Client-server separation means the renderer is swappable. Top-down now ≠ top-down forever.
+
+**Team Leader (Jeroen):** Tyre makes a good point about different clients. There's a great middle ground: we can switch to 3D for cutscenes. I'm sold.
+
+### OZZIE (Player Experience)
+
+There it is. Top-down for detective work, 3D cutscene for the wormhole walk-through. That's my moment back. The Dyson barrier opening. First contact. Moments that SHOULD feel different because the world just changed.
+
+### TYRE (Technical Architect)
+
+3D cutscenes are decoupled from gameplay engineering. Can be pre-rendered, can be simple, can be added AFTER core game works. They're polish, not architecture.
+
+### GESTALT (Systems Design)
+
+Camera change to 3D IS the dramatic signal. Player knows: something significant is happening.
+
+### SCRIBE (Documenter)
+
+Confirmed as D-019 (top-down final, 3D cutscenes for key moments). Camera debate closed. Full honest tradeoff analysis preserved in the record.
+
+*Engine selection. NOW. Hard requirements: client-server (D-010), deterministic sim (D-010), chunk-based maps (D-012), LOS shadowcasting with vision cone (D-011/D-015), sound propagation (D-018), observer-based perception queries (D-017), 2D top-down primary with potential 3D cutscenes (D-019). Q-001 is next.*