Step 1: Analyze Plan & Design Team
  計画からタスク依存関係を分析し、チーム構成を決定
    ↓
Step 2: Spawn Agent Team
  モジュール/レイヤー単位でTeammateを起動
    ↓
Step 3: Monitor & Coordinate
  Lead がモニタリング、統合、品質管理
    ↓
Step 4: Integration & Verification
  全タスク完了後、統合テスト実行

Teammate 1: Module A (models, core logic)
Teammate 2: Module B (API, endpoints)
Teammate 3: Tests (unit + integration)

Teammate 1: Data layer (models, DB)
Teammate 2: Business logic (services)
Teammate 3: Interface layer (API/CLI)

Teammate 1: Feature X (all layers)
Teammate 2: Feature Y (all layers)
Teammate 3: Shared infrastructure

Create an agent team for implementing: {feature}

Each teammate receives:
- Project Brief from CLAUDE.md
- Architecture from .claude/docs/DESIGN.md
- Library constraints from .claude/docs/libraries/
- Their specific task assignments

Spawn teammates:

1. **Implementer-{module}** for each module/workstream
   Prompt: "You are implementing {module} for project: {feature}.

   Read these files for context:
   - CLAUDE.md (project context)
   - .claude/docs/DESIGN.md (architecture)
   - .claude/docs/libraries/ (library constraints)

   Your assigned tasks:
   {task list for this teammate}

   Your file ownership:
   {list of files this teammate owns}

   Rules:
   - ONLY edit files in your ownership set
   - Follow existing codebase patterns
   - Write type hints on all functions
   - Run ruff check after each file change
   - Communicate with other teammates if you need interface changes

   When done with each task, mark it completed in the task list.

   IMPORTANT — Work Log:
   When ALL your assigned tasks are complete, write a work log file to:
     .claude/logs/agent-teams/{team-name}/{your-teammate-name}.md

   Use this format:
   # Work Log: {your-teammate-name}
   ## Summary
   (1-2 sentence summary of what you accomplished)
   ## Tasks Completed
   - [x] {task}: {brief description of what was done}
   ## Files Modified
   - `{file path}`: {what was changed and why}
   ## Key Decisions
   - {decision made during implementation and rationale}
   ## Communication with Teammates
   - → {recipient}: {summary of message sent}
   - ← {sender}: {summary of message received}
   ## Issues Encountered
   - {issue}: {how it was resolved}
   (If none, write 'None')
   "

2. **Tester** (optional but recommended)
   Prompt: "You are the Tester for project: {feature}.

   Read:
   - CLAUDE.md, .claude/docs/DESIGN.md
   - Existing test patterns in tests/

   Your tasks:
   - Write tests for each module as implementers complete them
   - Follow TDD where possible (write test stubs first)
   - Run uv run pytest after each test file
   - Report failing tests to the relevant implementer

   Test coverage target: 80%+

   IMPORTANT — Work Log:
   When ALL your assigned tasks are complete, write a work log file to:
     .claude/logs/agent-teams/{team-name}/{your-teammate-name}.md

   Use this format:
   # Work Log: {your-teammate-name}
   ## Summary
   (1-2 sentence summary of what you accomplished)
   ## Tasks Completed
   - [x] {task}: {brief description of what was done}
   ## Files Modified
   - `{file path}`: {what was changed and why}
   ## Key Decisions
   - {decision made during implementation and rationale}
   ## Communication with Teammates
   - → {recipient}: {summary of message sent}
   - ← {sender}: {summary of message received}
   ## Issues Encountered
   - {issue}: {how it was resolved}
   (If none, write 'None')
   "

Use delegate mode (Shift+Tab) to prevent Lead from implementing directly.
Wait for all teammates to complete their tasks.

# All quality checks
uv run ruff check .
uv run ruff format --check .
uv run ty check src/
uv run pytest -v

# Or via poe
poe all

## 実装完了: {feature}

### 完了タスク
- [x] {task 1}
- [x] {task 2}
...

### 品質チェック
- ruff: ✓ / ✗
- ty: ✓ / ✗
- pytest: ✓ ({N} tests passed)
- coverage: {N}%

### 次のステップ
`/team-review` で並列レビューを実行してください

Clean up the team