Files

T

jpmschweitzerandClaude Opus 4.6 7158ae9cf5 feat(meta): add whatsinagame multi-agent team starter kit

Claude-native starter kit that bootstraps multi-agent team
infrastructure for any project. Clone once, install as a global
skill, run /kit-install in any project directory.

Includes:
- 3-tier profile system (minimal/standard/full: 3-12 agents)
- 16 agent archetype templates with personality spectrum
- 18 skill templates using domain-action naming convention
- Stakeholder persona panel for workshops and PR reviews
- SQLite ticketing DB with CLI tools (config-based DB paths)
- Decision tracking, sprint lifecycle, workshop orchestration
- Multi-git-host support (GitHub, Gitea, GitLab)
- /kit-update skill for syncing with source repo evolution
- Naming theme support for agent identity/flavor
- Smoke tests for all three profile tiers

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

2026-02-18 02:22:30 +01:00

3.1 KiB

Raw Blame History

DevOps

Build, test, lint, and CI procedures for {Project Name}.

Quick Start

make setup          # Initialize dev environment
make                # Show all available targets

Database

The project uses SQLite for ticketing and decision tracking.

Initialize

db/connectors/sqlite-init

Query

db/connectors/sqlite-query "SELECT * FROM tickets WHERE status='in_progress'"
db/connectors/sqlite-exec "UPDATE tickets SET status='done' WHERE id=1"

Never use the sqlite3 CLI — it crashes in Claude Code (std::bad_alloc). Use the wrapper scripts.

Ticket CLI

db/connectors/ticket list [--status S] [--sprint N] [--team T]
db/connectors/ticket show <id>
db/connectors/ticket create --title "Title" --team T --priority P
db/connectors/ticket assign <id> --agent name

Sprint CLI

db/connectors/sprint status                    # Current sprint progress
db/connectors/sprint status --team T           # Team-scoped view
db/connectors/sprint start-work [--team T]     # Full context dump for starting work
db/connectors/sprint prepare                   # Prepare next sprint
db/connectors/sprint start                     # Activate a planned sprint
db/connectors/sprint stop                      # Complete an active sprint

Decision Tracking

Decisions live in decisions/*.md domain files and sync to SQLite:

make decisions-sync       # Parse decisions/*.md into SQLite
make decisions-coverage   # Decision-to-ticket coverage report
make decisions-active     # List all active confirmed decisions
make decisions-orphan     # Decisions without associated tickets

Document Search (optional)

If Qdrant + Ollama are configured for semantic search:

db/connectors/qdrant-health                    # Check service status
db/connectors/qdrant-search "query text"       # Semantic search
db/connectors/qdrant-index path/to/doc.md      # Index a document
db/connectors/qdrant-count                     # Collection stats

Git Hooks

Install hooks:

make setup-hooks

Hook directory: .config/hooks/

The pre-commit hook runs project-specific validation checks. Add new checks by editing .config/hooks/pre-commit and adding run_check calls.

Pre-PR Checklist

make pre-pr

This runs:

Decision sync (ensures SQLite index is current)
{Add project-specific checks as needed}

Worktree Workflow (if configured)

If the project uses git worktrees for team branches:

{parent}/
  main/         # Integration branch (worktree)
  server/       # Server team branch (worktree)
  client/       # Client team branch (worktree)
  {team}/       # Additional team branches
  {db_name}     # Shared ticketing database

Each worktree is a full checkout. The shared database lives in the parent directory. Agents should stay within their worktree root unless accessing the shared database.

Branch management

# Update worktree branch from main
git merge main

# Check worktree status
git worktree list

Protected branches (never delete): main, and all team branches.

3.1 KiB Raw Blame History