Team Lead（队长）    → 主Claude Code会话，负责任务分解和协调
Teammates（队友）    → 独立的Claude实例，各有自己的上下文窗口和工具
Task List（任务列表） → ~/.claude/tasks/{team-name}/，带状态和依赖关系
Mailbox（邮箱）      → ~/.claude/teams/{team-name}/inboxes/，队友间直接消息

{
  "env": {
    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
  }
}

export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

claude --env CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

# macOS
brew install tmux

# Ubuntu/Debian
sudo apt install tmux

我正在设计一个CLI工具，帮助开发者追踪代码库中的TODO注释。
创建3个队友从不同角度探索这个需求：
- 一个关注用户体验
- 一个做技术架构设计
- 一个当"魔鬼代言人"挑刺

{
  "teammateMode": "auto"  // auto | tmux | iterm2 | in-process
}

Review pull request #47 using a team of 3 specialized reviewers.
Create a team called "pr-47-review".

Reviewer 1 (Security): Review all changes in src/auth/ and src/api/
for authentication bypasses, injection vulnerabilities, and unsafe
data handling. Use Sonnet model.

Reviewer 2 (Performance): Review all changes for N+1 queries,
unnecessary re-renders, missing indexes, and memory leaks.
Focus on files touching database queries and React components.
Use Sonnet model.

Reviewer 3 (Code Quality): Review for consistent error handling,
proper TypeScript types, test coverage gaps, and adherence to our
coding standards in CLAUDE.md. Use Sonnet model.

After all reviewers complete, synthesize findings into a single
prioritized report. Flag any conflicts between reviewers' recommendations.

Implement the user notification preferences feature from issue #234.
Create a team called "notification-prefs".

Teammate 1 (Backend): Create the API endpoints in src/api/notifications/
- GET /api/notifications/preferences
- PUT /api/notifications/preferences
- Add database migration for notification_preferences table
- Write unit tests for new endpoints
Use Sonnet model.

Teammate 2 (Frontend): Build the settings UI in src/components/settings/
- Create NotificationPreferences component
- Connect to API endpoints (coordinate with Backend teammate for exact
  request/response shapes)
- Add form validation and loading states
- Write component tests
Use Sonnet model.

Teammate 3 (Integration): After Backend and Frontend complete:
- Write end-to-end tests covering the full flow
- Verify database migration runs cleanly
- Test error scenarios (network failures, invalid data)
Use Sonnet model. This task is blocked by Teammates 1 and 2.
Use delegate mode. I want to review the overall plan before implementation.

The checkout flow is failing intermittently with a 500 error in production.
Error logs show "connection refused" but only for ~10% of requests.
Create a team called "checkout-debug" with 3 investigators.

Investigator 1: Hypothesis — Database connection pool exhaustion.
Check src/db/pool.ts configuration, look for connection leaks in
checkout transaction code, analyze pool sizing vs concurrent load.

Investigator 2: Hypothesis — Redis session store timeout.
Check src/cache/redis.ts for timeout configuration, look for blocking
operations in session middleware, verify Redis health check.

Investigator 3: Hypothesis — Downstream payment API flakiness.
Check src/services/payment.ts for retry logic, error handling for
webhook, verify if circuit breaker is configured.

Each investigator: Share findings via messages as you go. If you find
strong evidence for your hypothesis, broadcast to team immediately.
If you rule out your hypothesis, say so and help another investigator.

I need to understand how our authentication system works before
refactoring it. Create a research team called "auth-research".

Researcher 1: Map the authentication flow from login to session creation.
Document every file involved, every middleware, every database query.
Output a flow diagram in markdown.

Researcher 2: Identify all places in the codebase that check
authentication or authorization. List every guard, middleware,
decorator, and manual check. Flag inconsistencies.

Researcher 3: Analyze test coverage for authentication.
Which flows are well-tested? Which have no tests?
What edge cases are missing?

All researchers: Use read-only operations only. Do not modify any files.
Share interesting findings as you discover them.

Spawn an architect teammate to refactor the authentication module.
Require plan approval before they make any changes.

# 在队友空闲时自动运行linter
TeammateIdle → 运行 eslint → 失败则反馈给队友修正

# 任务完成时自动部署预览
TaskCompleted → 运行集成测试 → 通过则部署staging

迁移数据库 → 后端API（依赖迁移） → 前端组件（依赖API定义） → E2E测试（依赖全部）

1. 在 ~/.claude/settings.json 添加 "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
2. 安装 tmux（brew install tmux / apt install tmux）
3. 打开 Claude Code，输入一个低风险探索任务（用模板4）
4. 观察队长如何分解任务、队友如何协作
5. 尝试2人代码审查（用模板1）
6. 逐步升级到3人全栈开发（用模板2）