跳到正文
cccskills
免费在 GitHub 公开

agent-teams

Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.

中文简介正在准备中。当前显示原文说明。

集成工具Redis
查看安装方法

包含的文件(1)

  • SKILL.md5.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Agent Teams

Coordinate multiple Claude Code sessions working on the same codebase simultaneously.

Enable

export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
claude  # starts as team lead

The first session becomes the team lead. Subsequent sessions in the same repo join as teammates.

Architecture

Team Lead (coordinates, delegates, reviews)
  ├── Teammate 1 (owns task A, messages lead + peers)
  ├── Teammate 2 (owns task B, messages lead + peers)
  └── Teammate 3 (owns task C, messages lead + peers)
      │
      └── Shared: task list + mailbox + file locks

Key difference from subagents: Teammates are full Claude Code sessions. They have their own context window, can use all tools, and message each other directly — not just report back to a parent.

Team Sizing

Team SizeBest For
2One builds, one reviews
3-5Parallel features across layers (API, UI, tests)
> 5Coordination overhead outweighs parallelism

3-5 teammates is the productive range. Beyond that, the lead spends more time coordinating than the team saves.

Task granularity: Aim for 5-6 tasks per teammate. Fewer means underutilization; more means excessive context switching.

Display Modes

In-process navigation:

  • Shift+Down — cycle through teammates (wraps around)
  • See each teammate's current task and output

Split-pane (recommended for >2 teammates):

  • tmux: tmux split-window -h per teammate
  • iTerm2: Cmd+D for vertical split
  • Each pane runs its own claude session

Task Management

Tasks flow through states:

pending → in-progress → completed
              │
              └── blocked (waiting on dependency)

Task Decomposition

Break work into units that:

  • Touch non-overlapping files
  • Can be verified independently
  • Have clear done criteria

Good decomposition:

Task 1: Add rate limiting middleware (src/middleware/rate-limit.ts)
Task 2: Add rate limit tests (tests/rate-limit.test.ts)
Task 3: Update API docs for rate limit headers (docs/api.md)
Task 4: Add Redis config for rate limit store (src/config/redis.ts)

Bad decomposition:

Task 1: Implement rate limiting
Task 2: Fix rate limiting bugs
Task 3: Improve rate limiting

Dependencies

Tasks can declare dependencies:

Task 3 (API docs) → depends on Task 1 (middleware)
Task 2 (tests) → depends on Task 1 (middleware)
Task 4 (Redis config) → no dependencies

Teammates pick up unblocked tasks automatically.

File-Lock Claiming

Teammates claim files before editing to prevent conflicts:

  1. Teammate checks if file is locked
  2. If free, claims it (file-lock-based)
  3. Edits the file
  4. Releases lock on task completion

If two teammates need the same file, one waits or the lead reassigns.

Plan Approval

Teammates plan before implementing:

  1. Teammate receives task
  2. Writes a brief plan (files to change, approach)
  3. Lead reviews plan
  4. Lead approves or redirects
  5. Teammate implements

This prevents wasted work from misunderstood requirements.

Delegate Mode

Shift+Tab toggles delegate mode for the lead:

  • Lead coordinates only — no direct code edits
  • All implementation delegated to teammates
  • Lead reviews, approves plans, manages task flow

Hook Events

HookFires When
TeammateIdleA teammate finishes its task and has no pending work
TaskCreatedNew task added to the shared list
TaskCompletedA teammate marks a task done

Use these to trigger notifications, auto-assign next tasks, or run integration tests when all tasks complete.

When to Use Teams vs Alternatives

ScenarioUse
Parallel work on non-overlapping filesAgent teams
Quick background explorationSubagent
Isolated feature branch workWorktree (claude -w)
Competing approaches to same problemWorktrees (compare results)
Cross-layer changes (API + UI + tests)Agent teams
One-off delegationSubagent with isolation: worktree
Large-scale migration (20+ files)/batch command

Anti-Patterns

  • More than 5 teammates — coordination overhead dominates
  • Tasks that share mutable state or the same files
  • Skipping plan approval — leads to rework
  • Lead doing implementation instead of coordinating (use delegate mode)
  • Not setting dependencies — teammates race on coupled tasks

Example Session

Lead: "We need rate limiting. Breaking into 4 tasks."

  Task 1: middleware implementation → Teammate 1
  Task 2: Redis config → Teammate 2 (no deps)
  Task 3: tests → Teammate 1 (after Task 1)
  Task 4: API docs → Teammate 2 (after Task 1)

Teammate 1 plans → Lead approves → implements Task 1
Teammate 2 plans → Lead approves → implements Task 2
Task 1 completes → unblocks Tasks 3 and 4
Teammate 1 picks up Task 3, Teammate 2 picks up Task 4
All complete → Lead runs integration tests → commits

Docs

https://code.claude.com/docs/agent-teams

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.

中文简介正在准备中。当前显示原文说明。

rohitg00/pro-workflow29212026年9月29日 更新

Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.

中文简介正在准备中。当前显示原文说明。

rohitg00/pro-workflow29212026年9月29日 更新

Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".

中文简介正在准备中。当前显示原文说明。

rohitg00/pro-workflow29212026年9月29日 更新

Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.

中文简介正在准备中。当前显示原文说明。

rohitg00/pro-workflow29212026年9月29日 更新

Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.

中文简介正在准备中。当前显示原文说明。

rohitg00/pro-workflow29212026年9月29日 更新

Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.

中文简介正在准备中。当前显示原文说明。

rohitg00/pro-workflow29212026年9月29日 更新

查看 rohitg00 的全部技能

报告此技能的问题