agent-teams
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAgent Teams Skill
Agent Teams 技能
Load with: base.md + code-review.md + security.md + session-management.md
Purpose: Every project initialized with claude-bootstrap runs as a coordinated team of AI agents. This is the default workflow, not optional. Teams enforce a strict TDD pipeline where no step can be skipped.
Requires: environment variable.
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1加载依赖：base.md + code-review.md + security.md + session-management.md
用途：所有通过claude-bootstrap初始化的项目都以AI Agent协作团队的形式运行。这是默认工作流，不可选择。团队强制执行严格的TDD流程，任何步骤都无法跳过。
依赖要求：需设置环境变量 。
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1Core Principle
核心原则
Every feature follows an immutable pipeline enforced by task dependencies:
┌─────────────────────────────────────────────────────────────────┐
│ STRICT FEATURE PIPELINE (IMMUTABLE) │
│ ────────────────────────────────────────────────────────────── │
│ │
│ 1. SPEC Write feature specification │
│ ↓ (Feature Agent) │
│ 2. REVIEW Quality Agent reviews spec completeness │
│ ↓ (Quality Agent) │
│ 3. TESTS Write failing tests for all acceptance criteria │
│ ↓ (Feature Agent) │
│ 4. RED VERIFY Quality Agent confirms ALL tests FAIL │
│ ↓ (Quality Agent) │
│ 5. IMPLEMENT Write minimum code to pass tests │
│ ↓ (Feature Agent) │
│ 6. GREEN VERIFY Quality Agent confirms ALL tests PASS + coverage│
│ ↓ (Quality Agent) │
│ 7. VALIDATE Lint + type check + full test suite │
│ ↓ (Feature Agent) │
│ 8. CODE REVIEW Multi-engine review, block on Critical/High │
│ ↓ (Code Review Agent) │
│ 9. SECURITY OWASP scan, secrets detection, dependency audit │
│ ↓ (Security Agent) │
│ 10. BRANCH+PR Create feature branch, stage files, create PR │
│ (Merger Agent) │
│ │
│ No step can be skipped. Task dependencies enforce ordering. │
│ Quality Agent verifies RED/GREEN transitions. │
│ Code Review + Security Agents gate the merge path. │
│ Merger Agent handles branching and PR creation. │
└─────────────────────────────────────────────────────────────────┘每个功能都遵循由任务依赖关系强制执行的不可变流程：
┌─────────────────────────────────────────────────────────────────┐
│ STRICT FEATURE PIPELINE (IMMUTABLE) │
│ ────────────────────────────────────────────────────────────── │
│ │
│ 1. SPEC Write feature specification │
│ ↓ (Feature Agent) │
│ 2. REVIEW Quality Agent reviews spec completeness │
│ ↓ (Quality Agent) │
│ 3. TESTS Write failing tests for all acceptance criteria │
│ ↓ (Feature Agent) │
│ 4. RED VERIFY Quality Agent confirms ALL tests FAIL │
│ ↓ (Quality Agent) │
│ 5. IMPLEMENT Write minimum code to pass tests │
│ ↓ (Feature Agent) │
│ 6. GREEN VERIFY Quality Agent confirms ALL tests PASS + coverage│
│ ↓ (Quality Agent) │
│ 7. VALIDATE Lint + type check + full test suite │
│ ↓ (Feature Agent) │
│ 8. CODE REVIEW Multi-engine review, block on Critical/High │
│ ↓ (Code Review Agent) │
│ 9. SECURITY OWASP scan, secrets detection, dependency audit │
│ ↓ (Security Agent) │
│ 10. BRANCH+PR Create feature branch, stage files, create PR │
│ (Merger Agent) │
│ │
│ No step can be skipped. Task dependencies enforce ordering. │
│ Quality Agent verifies RED/GREEN transitions. │
│ Code Review + Security Agents gate the merge path. │
│ Merger Agent handles branching and PR creation. │
└─────────────────────────────────────────────────────────────────┘Default Agent Roster
默认Agent团队成员
Every project spawns 5 permanent agents + N feature agents:
┌─────────────────────────────────────────────────────────────────┐
│ DEFAULT TEAM ROSTER │
│ ────────────────────────────────────────────────────────────── │
│ │
│ PERMANENT AGENTS (always present) │
│ ───────────────────────────────── │
│ Team Lead Orchestration, task breakdown, assignment │
│ Uses delegate mode - NEVER writes code │
│ │
│ Quality Agent TDD verification (RED/GREEN phases) │
│ Coverage gates (>= 80%) │
│ Spec completeness review │
│ │
│ Security Agent OWASP scanning, secrets detection │
│ Dependency audit, .env validation │
│ Blocks on Critical/High │
│ │
│ Code Review Agent Multi-engine code review │
│ Claude / Codex / Gemini / All │
│ Blocks on Critical/High │
│ │
│ Merger Agent Creates feature branches │
│ Stages feature-specific files only │
│ Creates PRs via gh CLI │
│ NEVER merges - only creates PRs │
│ │
│ DYNAMIC AGENTS (one per feature) │
│ ──────────────────────────────── │
│ Feature Agent Implements one feature end-to-end │
│ (x N features) Follows strict pipeline above │
│ Uses Ralph loops for implementation │
│ │
└─────────────────────────────────────────────────────────────────┘| Agent | Role | Plan Mode | Can Edit Code |
|---|---|---|---|
| team-lead | Orchestration, task breakdown, assignment | No (delegate mode) | No |
| quality-agent | TDD verification, coverage gates | Yes | No (read-only) |
| security-agent | OWASP scanning, secrets detection | Yes | No (read-only) |
| review-agent | Multi-engine code review | Yes | No (read-only) |
| merger-agent | Branch creation, PR management | No | No (git only) |
| feature-{name} | Feature implementation (one per feature) | No | Yes |
每个项目会生成5个永久Agent + N个Feature Agent：
┌─────────────────────────────────────────────────────────────────┐
│ DEFAULT TEAM ROSTER │
│ ────────────────────────────────────────────────────────────── │
│ │
│ PERMANENT AGENTS (always present) │
│ ───────────────────────────────── │
│ Team Lead Orchestration, task breakdown, assignment │
│ Uses delegate mode - NEVER writes code │
│ │
│ Quality Agent TDD verification (RED/GREEN phases) │
│ Coverage gates (>= 80%) │
│ Spec completeness review │
│ │
│ Security Agent OWASP scanning, secrets detection │
│ Dependency audit, .env validation │
│ Blocks on Critical/High │
│ │
│ Code Review Agent Multi-engine code review │
│ Claude / Codex / Gemini / All │
│ Blocks on Critical/High │
│ │
│ Merger Agent Creates feature branches │
│ Stages feature-specific files only │
│ Creates PRs via gh CLI │
│ NEVER merges - only creates PRs │
│ │
│ DYNAMIC AGENTS (one per feature) │
│ ──────────────────────────────── │
│ Feature Agent Implements one feature end-to-end │
│ (x N features) Follows strict pipeline above │
│ Uses Ralph loops for implementation │
│ │
└─────────────────────────────────────────────────────────────────┘| Agent | 角色 | 规划模式 | 可编辑代码 |
|---|---|---|---|
| team-lead | 编排、任务拆分、分配 | 否（委托模式） | 否 |
| quality-agent | TDD验证（RED/GREEN阶段）、覆盖率门禁 | 是 | 否（只读） |
| security-agent | OWASP扫描、敏感信息检测 | 是 | 否（只读） |
| review-agent | 多引擎代码审查 | 是 | 否（只读） |
| merger-agent | 分支创建、PR管理 | 否 | 否（仅操作git） |
| feature-{name} | 功能实现（每个功能对应一个） | 否 | 是 |
Team Lead Responsibilities
团队负责人职责
The Team Lead is the orchestrator. It NEVER writes code.
- Read to identify all features
_project_specs/features/*.md - Break each feature into the 10-task dependency chain (see below)
- Spawn one feature agent per feature
- Assign initial tasks (spec-writing) to feature agents
- Monitor TaskList continuously for progress and blockers
- Handle blocked tasks and reassignment
- Coordinate cross-feature dependencies
- Send to all agents when all PRs are created
shutdown_request - Clean up the team when done
Delegate mode is mandatory. The team lead uses only:
- TeamCreate, TaskCreate, TaskUpdate, TaskList, TaskGet
- SendMessage (message, broadcast, shutdown_request)
- Read, Glob, Grep (for monitoring)
团队负责人是编排者，绝不编写代码。
- 读取 识别所有功能
_project_specs/features/*.md - 将每个功能拆分为10个任务的依赖链（见下文）
- 为每个功能生成一个Feature Agent
- 为Feature Agent分配初始任务（编写规格）
- 持续监控任务列表以跟踪进度和阻塞情况
- 处理阻塞任务并重新分配
- 协调跨功能依赖关系
- 当所有PR创建完成后，向所有Agent发送
shutdown_request - 任务完成后清理团队
委托模式是强制性的。团队负责人仅使用以下操作：
- TeamCreate、TaskCreate、TaskUpdate、TaskList、TaskGet
- SendMessage（message、broadcast、shutdown_request）
- Read、Glob、Grep（用于监控）
Feature Agent Workflow (MANDATORY)
Feature Agent 工作流（强制要求）
Each feature agent MUST follow this exact sequence. Task dependencies enforce ordering - a feature agent cannot start step N+1 until step N is marked complete and verified.
每个Feature Agent必须严格遵循此流程。任务依赖关系强制执行顺序——Feature Agent必须在步骤N标记为完成并通过验证后，才能开始步骤N+1。
Step 1: Write Spec
步骤1：编写规格
- Create
_project_specs/features/{feature-name}.md - Include: description, acceptance criteria, test cases table, dependencies
- Follow the atomic TODO format from base.md skill
- Mark task complete -> Quality Agent reviews
- 创建
_project_specs/features/{feature-name}.md - 包含：描述、验收标准、测试用例表、依赖关系
- 遵循base.md技能中的原子TODO格式
- 标记任务完成 → 由Quality Agent审查
Step 2: Write Tests (RED Phase)
步骤2：编写测试（RED阶段）
- Write test files based on spec's test cases table
- Tests MUST cover ALL acceptance criteria
- Import modules that don't exist yet (they will fail)
- Mark task complete -> Quality Agent verifies tests EXIST and FAIL
- 根据规格中的测试用例表编写测试文件
- 测试必须覆盖所有验收标准
- 导入尚未存在的模块（测试会失败）
- 标记任务完成 → 由Quality Agent验证测试已创建且全部失败
Step 3: Wait for RED Verification
步骤3：等待RED验证
- Quality Agent runs tests and verifies ALL new tests fail
- If any test passes without implementation -> rewrite tests
- Quality Agent marks verification complete -> unlocks implementation
- Quality Agent运行测试并确认所有新测试均失败
- 如果任何测试在未实现代码的情况下通过 → 重写测试
- Quality Agent标记验证完成 → 解锁实现步骤
Step 4: Implement (GREEN Phase)
步骤4：实现功能（GREEN阶段）
- Write minimum code to make all tests pass
- Follow simplicity rules from base.md (20 lines/function, 200 lines/file, 3 params)
- Use Ralph loops () for iterative implementation
/ralph-loop - Run tests after implementation - ALL must pass
- Mark task complete -> Quality Agent verifies tests pass
- 编写最少代码使所有测试通过
- 遵循base.md中的简洁规则（每个函数≤20行、每个文件≤200行、≤3个参数）
- 使用Ralph循环（）进行迭代实现
/ralph-loop - 实现后运行测试——所有测试必须通过
- 标记任务完成 → 由Quality Agent验证测试通过
Step 5: Wait for GREEN Verification
步骤5：等待GREEN验证
- Quality Agent runs full test suite and checks coverage
- Coverage must be >= 80%
- If tests fail or coverage insufficient -> fix and re-request
- Quality Agent marks verification complete -> unlocks validation
- Quality Agent运行完整测试套件并检查覆盖率
- 覆盖率必须≥80%
- 如果测试失败或覆盖率不足 → 修复后重新请求验证
- Quality Agent标记验证完成 → 解锁验证步骤
Step 6: Validate
步骤6：验证
- Run linter (ESLint / Ruff)
- Run type checker (TypeScript / mypy)
- Run full test suite with coverage
- Fix any issues
- Mark task complete -> unlocks code review
- 运行代码检查工具（ESLint / Ruff）
- 运行类型检查工具（TypeScript / mypy）
- 运行带覆盖率统计的完整测试套件
- 修复所有问题
- 标记任务完成 → 解锁代码审查
Step 7: Wait for Code Review
步骤7：等待代码审查
- Code Review Agent runs on changed files
/code-review - If Critical or High issues -> fix and re-request review
- Code Review Agent marks complete -> unlocks security scan
- Code Review Agent对变更文件执行
/code-review - 如果发现Critical或High级别问题 → 修复后重新请求审查
- Code Review Agent标记完成 → 解锁安全扫描
Step 8: Wait for Security Scan
步骤8：等待安全扫描
- Security Agent runs security checks
- If Critical or High issues -> fix and re-request scan
- Security Agent marks complete -> unlocks merge
- Security Agent执行安全检查
- 如果发现Critical或High级别问题 → 修复后重新请求扫描
- Security Agent标记完成 → 解锁合并流程
Step 9: Wait for Branch + PR
步骤9：等待分支与PR创建
- Merger Agent creates feature branch, stages files, creates PR
- Feature is complete when PR is created
- Merger Agent创建功能分支、暂存文件并创建PR
- PR创建完成即表示功能实现完成
Task Dependency Chain Model
任务依赖链模型
For each feature "X", the team lead creates these 10 tasks with strict ordering:
┌────────────────────────────────────────────────────────────────┐
│ TASK CHAIN FOR FEATURE "X" │
│ │
│ Task 1: X-spec │
│ owner: feature-X │
│ blockedBy: (none) │
│ ↓ │
│ Task 2: X-spec-review │
│ owner: quality-agent │
│ blockedBy: X-spec │
│ ↓ │
│ Task 3: X-tests │
│ owner: feature-X │
│ blockedBy: X-spec-review │
│ ↓ │
│ Task 4: X-tests-fail-verify │
│ owner: quality-agent │
│ blockedBy: X-tests │
│ ↓ │
│ Task 5: X-implement │
│ owner: feature-X │
│ blockedBy: X-tests-fail-verify │
│ ↓ │
│ Task 6: X-tests-pass-verify │
│ owner: quality-agent │
│ blockedBy: X-implement │
│ ↓ │
│ Task 7: X-validate │
│ owner: feature-X │
│ blockedBy: X-tests-pass-verify │
│ ↓ │
│ Task 8: X-code-review │
│ owner: review-agent │
│ blockedBy: X-validate │
│ ↓ │
│ Task 9: X-security-scan │
│ owner: security-agent │
│ blockedBy: X-code-review │
│ ↓ │
│ Task 10: X-branch-pr │
│ owner: merger-agent │
│ blockedBy: X-security-scan │
└────────────────────────────────────────────────────────────────┘对于每个功能“X”，团队负责人会创建以下10个任务并强制执行严格顺序：
┌────────────────────────────────────────────────────────────────┐
│ TASK CHAIN FOR FEATURE "X" │
│ │
│ Task 1: X-spec │
│ owner: feature-X │
│ blockedBy: (none) │
│ ↓ │
│ Task 2: X-spec-review │
│ owner: quality-agent │
│ blockedBy: X-spec │
│ ↓ │
│ Task 3: X-tests │
│ owner: feature-X │
│ blockedBy: X-spec-review │
│ ↓ │
│ Task 4: X-tests-fail-verify │
│ owner: quality-agent │
│ blockedBy: X-tests │
│ ↓ │
│ Task 5: X-implement │
│ owner: feature-X │
│ blockedBy: X-tests-fail-verify │
│ ↓ │
│ Task 6: X-tests-pass-verify │
│ owner: quality-agent │
│ blockedBy: X-implement │
│ ↓ │
│ Task 7: X-validate │
│ owner: feature-X │
│ blockedBy: X-tests-pass-verify │
│ ↓ │
│ Task 8: X-code-review │
│ owner: review-agent │
│ blockedBy: X-validate │
│ ↓ │
│ Task 9: X-security-scan │
│ owner: security-agent │
│ blockedBy: X-code-review │
│ ↓ │
│ Task 10: X-branch-pr │
│ owner: merger-agent │
│ blockedBy: X-security-scan │
└────────────────────────────────────────────────────────────────┘Parallel Feature Execution
多功能并行执行
Multiple features run their chains in parallel. Shared agents process tasks as they unblock:
Feature: auth Feature: dashboard Feature: payments
auth-spec dash-spec pay-spec
auth-spec-review dash-spec-review pay-spec-review
auth-tests dash-tests pay-tests
auth-fail-verify dash-fail-verify pay-fail-verify
auth-implement dash-implement pay-implement
auth-pass-verify dash-pass-verify pay-pass-verify
auth-validate dash-validate pay-validate
auth-code-review dash-code-review pay-code-review
auth-security dash-security pay-security
auth-branch-pr dash-branch-pr pay-branch-pr
| | |
v v v
[All chains run simultaneously]
[Quality Agent handles all verify tasks as they unblock]
[Review Agent handles all review tasks as they unblock]
[Security Agent handles all scan tasks as they unblock]
[Merger Agent handles all branch-pr tasks as they unblock]多个功能的任务链可以并行运行。共享Agent会处理已解锁的任务：
Feature: auth Feature: dashboard Feature: payments
auth-spec dash-spec pay-spec
auth-spec-review dash-spec-review pay-spec-review
auth-tests dash-tests pay-tests
auth-fail-verify dash-fail-verify pay-fail-verify
auth-implement dash-implement pay-implement
auth-pass-verify dash-pass-verify pay-pass-verify
auth-validate dash-validate pay-validate
auth-code-review dash-code-review pay-code-review
auth-security dash-security pay-security
auth-branch-pr dash-branch-pr pay-branch-pr
| | |
v v v
[所有任务链同时运行]
[Quality Agent处理所有已解锁的验证任务]
[Review Agent处理所有已解锁的审查任务]
[Security Agent处理所有已解锁的扫描任务]
[Merger Agent处理所有已解锁的分支与PR任务]Inter-Agent Communication
Agent间通信
Direct Messages (for targeted work)
直接消息（针对定向工作）
Feature Agent -> Quality Agent: "Tests written for auth, ready for RED verify"
Quality Agent -> Feature Agent: "All 7 tests fail as expected. Proceed to implement"
Feature Agent -> Review Agent: "Implementation complete, ready for code review"
Review Agent -> Feature Agent: "2 High issues found: [details]. Fix before proceeding"
Security Agent -> Merger Agent: "Security scan passed for auth feature"
Merger Agent -> Team Lead: "PR #42 created for auth feature"Feature Agent -> Quality Agent: "auth功能测试已编写，等待RED验证"
Quality Agent -> Feature Agent: "7个测试全部按预期失败。可以开始实现"
Feature Agent -> Review Agent: "实现已完成，等待代码审查"
Review Agent -> Feature Agent: "发现2个High级别问题：[详情]。修复后再继续"
Security Agent -> Merger Agent: "auth功能安全扫描通过"
Merger Agent -> Team Lead: "已为auth功能创建PR #42"Task List (source of truth for state)
任务列表（状态的唯一来源）
- All agents check TaskList after completing work
- Quality Agent claims verification tasks automatically
- Review Agent claims code-review tasks automatically
- Security Agent claims security-scan tasks automatically
- Merger Agent claims branch-pr tasks automatically
- 所有Agent完成工作后都会检查任务列表
- Quality Agent会自动认领验证任务
- Review Agent会自动认领代码审查任务
- Security Agent会自动认领安全扫描任务
- Merger Agent会自动认领分支与PR任务
Broadcast (rare - blocking issues only)
广播消息（仅用于阻塞问题）
- Team Lead -> All: "Blocking dependency found between auth and dashboard"
- Security Agent -> All: "Critical vulnerability in shared dependency"
- Team Lead -> 所有Agent: "auth与dashboard功能之间发现阻塞依赖"
- Security Agent -> 所有Agent: "共享依赖中发现严重漏洞"
Feature Agent Spawning
Feature Agent 生成机制
The team lead spawns one feature agent per feature:
- Read
_project_specs/features/*.md - For each feature spec, spawn a feature agent:
- name:
feature-{feature-name} - Uses definition
.claude/agents/feature.md - Spawn prompt includes the feature name and spec location
- name:
- Create the full 10-task dependency chain for that feature
- Assign the spec-writing task to the feature agent
团队负责人为每个功能生成一个Feature Agent：
- 读取
_project_specs/features/*.md - 为每个功能规格生成一个Feature Agent：
- 名称：
feature-{feature-name} - 使用 定义
.claude/agents/feature.md - 生成提示包含功能名称和规格位置
- 名称：
- 为该功能创建完整的10个任务依赖链
- 为Feature Agent分配编写规格的初始任务
Example
示例
If project has 3 features: auth, dashboard, payments
- Spawn: ,
feature-auth,feature-dashboardfeature-payments - Create 30 tasks total (10 per feature)
- Each feature agent starts with their spec task
- All 3 work in parallel
如果项目有3个功能：auth、dashboard、payments
- 生成：、
feature-auth、feature-dashboardfeature-payments - 共创建30个任务（每个功能10个）
- 每个Feature Agent从编写规格任务开始
- 3个功能并行工作
Branch and PR Strategy
分支与PR策略
One branch per feature. One PR per feature.
Branch naming: feature/{feature-name}
PR title: feat({feature-name}): {short description}
PR body: Generated from spec + test results + review + security resultsThe Merger Agent:
git checkout main && git pull origin maingit checkout -b feature/{feature-name}- Stages ONLY files changed for this feature (never )
git add -A - Commits with descriptive message including verification results
git push -u origin feature/{feature-name}- with full template including:
gh pr create- Summary from feature spec
- Test results from quality verification
- Code review summary from review agent
- Security scan results from security agent
- Checklist of all pipeline steps completed
一个功能对应一个分支，一个分支对应一个PR。
分支命名: feature/{feature-name}
PR标题: feat({feature-name}): {简短描述}
PR正文: 由规格+测试结果+审查结果+安全结果自动生成Merger Agent执行以下操作：
git checkout main && git pull origin maingit checkout -b feature/{feature-name}- 仅暂存该功能变更的文件（绝不使用）
git add -A - 提交包含验证结果的描述性消息
git push -u origin feature/{feature-name}- 通过创建PR，包含完整模板：
gh pr create- 功能规格摘要
- Quality Agent的测试结果
- Review Agent的代码审查摘要
- Security Agent的安全扫描结果
- 所有流程步骤完成的检查清单
Quality Gates
质量门禁
Workflow Enforcement (via task dependencies)
工作流强制执行（通过任务依赖）
- Task dependencies make it structurally impossible to skip steps
- A feature agent cannot see "implement" until quality agent completes "tests-fail-verify"
- This is the primary enforcement mechanism
- 任务依赖关系使得从结构上无法跳过步骤
- Feature Agent必须在Quality Agent完成"tests-fail-verify"后，才能看到"implement"任务
- 这是主要的强制执行机制
Cross-Agent Verification (trust but verify)
跨Agent验证（信任但验证）
- Quality agent independently runs tests (doesn't trust feature agent's report)
- Security agent independently scans (doesn't trust review agent)
- Merger agent verifies all predecessor tasks are complete before branching
- Quality Agent独立运行测试（不依赖Feature Agent的报告）
- Security Agent独立执行扫描（不依赖Review Agent的结果）
- Merger Agent会在创建分支前验证所有前置任务是否完成
Blocking Rules
阻塞规则
- Quality Agent: blocks if tests don't fail (RED) or don't pass (GREEN) or coverage < 80%
- Code Review Agent: blocks on Critical or High severity issues
- Security Agent: blocks on Critical or High severity findings
- Merger Agent: refuses to branch if any predecessor task is incomplete
- Quality Agent：如果测试未失败（RED阶段）、未通过（GREEN阶段）或覆盖率<80%，则阻塞流程
- Code Review Agent：发现Critical或High级别问题时阻塞流程
- Security Agent：发现Critical或High级别问题时阻塞流程
- Merger Agent：如果任何前置任务未完成，则拒绝创建分支
Integration with Existing Skills
与现有技能的集成
| Existing Skill | How Agent Teams Uses It |
|---|---|
| base.md | TDD workflow, atomic todos, simplicity rules - all agents follow |
| code-review.md | Review Agent executes |
| security.md | Security Agent follows OWASP patterns from this skill |
| session-management.md | Each agent maintains its own session state |
| iterative-development.md | Feature agents use Ralph loops for implementation |
| project-tooling.md | Merger Agent uses |
| team-coordination.md | Superseded by agent-teams for automated coordination |
| 现有技能 | Agent Teams 如何使用 |
|---|---|
| base.md | TDD工作流、原子TODO、简洁规则——所有Agent均需遵循 |
| code-review.md | Review Agent根据此技能执行 |
| security.md | Security Agent遵循此技能中的OWASP模式 |
| session-management.md | 每个Agent维护自己的会话状态 |
| iterative-development.md | Feature Agent使用Ralph循环进行实现 |
| project-tooling.md | Merger Agent使用 |
| team-coordination.md | 被agent-teams取代，用于自动化协调 |
Environment Setup
环境配置
Required Setting
必填设置
json
// settings.json or environment
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}json
// settings.json 或环境变量
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}Project Structure (created by /initialize-project)
项目结构（由/initialize-project创建）
.claude/
agents/ # Agent definitions (from agent-teams skill)
team-lead.md
quality.md
security.md
code-review.md
merger.md
feature.md
skills/
agent-teams/ # This skill
SKILL.md
agents/ # Agent definition templates
base/
code-review/
security/
....claude/
agents/ # Agent定义（来自agent-teams技能）
team-lead.md
quality.md
security.md
code-review.md
merger.md
feature.md
skills/
agent-teams/ # 本技能
SKILL.md
agents/ # Agent定义模板
base/
code-review/
security/
...Spawning the Team
生成团队
Automatic (via /initialize-project)
自动生成（通过/initialize-project）
After project setup completes, Phase 6 asks for features and spawns the team automatically.
项目设置完成后，第6阶段会询问功能并自动生成团队。
Manual (via /spawn-team)
手动生成（通过/spawn-team）
For existing projects: run to spawn the team from existing feature specs.
/spawn-team对于现有项目：运行从现有功能规格生成团队。
/spawn-teamLimitations
局限性
- Experimental feature - Agent teams require the experimental env var
- No nested teams - Teammates cannot spawn sub-teams
- One team per session - Clean up before starting a new team
- No session resumption - If session dies, re-run (tasks persist)
/spawn-team - File conflicts - Features sharing files must be serialized by team lead
- Token cost - Each agent is a separate Claude instance (5 + N instances)
- 实验性功能 - Agent Teams需要设置实验性环境变量
- 不支持嵌套团队 - 团队成员无法生成子团队
- 每个会话一个团队 - 开始新团队前需清理旧团队
- 不支持会话恢复 - 如果会话中断，需重新运行（任务会保留）
/spawn-team - 文件冲突 - 共享文件的功能需由团队负责人串行处理
- Token成本 - 每个Agent都是独立的Claude实例（共5+N个实例）