Token导航 LogoToken导航TokenDH.com
开发执行命令clawhub未标认证来源可访问clear审计提醒

claude-swarmClaude swarm 开发

Agent Skill

claude-swarm 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,072

周安装

128

GitHub Stars

公开资料未说明

下载量

1,024
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:claude-swarm(Claude swarm 开发)
来源仓库:https://github.com/linkbag/claude-swarm
安装命令:
openclaw skills install claude-swarm
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install claude-swarm

简介

实现多个 Claude Code 代理的并行协作开发。

  • 适用于大型项目拆分、多人协同编码或任务分片执行场景。
  • 基于 Git 项目自动分配子任务,提升开发效率。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。
  • 使用前请确保本地具备多实例运行条件及足够的计算资源。
  • claude-swarm 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
claude-swarm
description
Claude-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Claude Code agents to work in parallel on a project with git worktrees, tmux tracking, endorsement gates, auto-review chains, integration merging, and webhook notifications. All agents are Claude (opus for architect/integrator, sonnet for builders/reviewers). Triggers on parallel coding, multi-agent work, swarm orchestration, batch spawning, or when 2+ coding tasks need coordinated execution.

Claude Swarm — Multi-Agent Orchestration

Parallel Claude Code agents: plan → endorse → spawn → monitor → review → integrate → ship.

Quick Start

# 1. Write task prompts
cat > /tmp/prompt-task1.md << 'EOF'
Implement feature X...
EOF

# 2. Create tasks JSON
cat > /tmp/tasks.json << 'EOF'
[
  {"id": "feat-x", "description": "/tmp/prompt-task1.md", "role": "builder"},
  {"id": "feat-y", "description": "/tmp/prompt-task2.md", "role": "builder"}
]
EOF

# 3. Spawn batch (auto-endorses + auto-integration)
bash scripts/spawn-batch.sh "/path/to/project" "batch-1" "Description" /tmp/tasks.json

Roles & Models

RoleModelEffortUse
architectopushighDesign, planning, complex decisions
buildersonnethighFeature implementation (parallel)
reviewersonnetmediumAuto-review on completion
integratoropushighCross-branch merge + conflict resolution

Configure in config/duty-table.json.

Scripts

ScriptPurpose
spawn-batch.shSpawn N parallel agents + integration watcher
spawn-agent.shSpawn single agent in worktree + tmux
endorse-task.shEndorse task (required before spawn)
check-agents.shShow status of all running agents
cleanup.shRemove worktrees, branches, tmux sessions
notify.shSend webhook/Telegram notification
notify-on-complete.shAuto-watcher: notify + review on completion
integration-watcher.shAuto: merge all branches when batch completes

Workflow Detail

1. Planning (human + architect)

Break work into parallel tasks. Each task needs: ID, prompt, role.

2. Endorsement Gate

Every task requires endorsement before spawning — safety gate to prevent runaway agents.

  • spawn-batch.sh auto-endorses all tasks in batch
  • Manual: bash scripts/endorse-task.sh <task-id>
  • 30-second cooldown between endorsement and spawn

3. Spawning

Each agent runs in:

  • Isolated git worktree (<project>-worktrees/<task-id>/)
  • tmux session (claude-<task-id>)
  • Non-interactive mode (claude --print --permission-mode bypassPermissions)
  • Auto-retry with model fallback (opus → sonnet → haiku) on rate limits

4. Auto-Review

When an agent completes, notify-on-complete.sh:

  1. Detects completion (polls tmux every 60s)
  2. Sends notification
  3. Spawns a reviewer (sonnet) that checks the diff
  4. If issues found: fixes and commits (up to 3 rounds)
  5. Pushes final state

5. Integration

When all agents in a batch complete, integration-watcher.sh:

  1. Collects all branches
  2. Merges sequentially into main
  3. Uses opus to resolve any conflicts
  4. Runs integration review (opus, up to 3 rounds)
  5. Pushes to main (if auto-merge enabled)

Setup

  1. Copy this skill's scripts/ and config/ to your workspace
  2. Copy config/swarm.conf.exampleconfig/swarm.conf and configure
  3. Ensure installed: bash 4+, tmux, git, gh, jq, claude (Claude Code CLI)

Notifications

Set SWARM_NOTIFY in swarm.conf:

  • webhook — POST to SWARM_WEBHOOK_URL (Slack/Discord/custom)
  • telegram — Send via SWARM_TELEGRAM_BOT_TOKEN + SWARM_TELEGRAM_CHAT_ID
  • none — Log only (default)

Hard Rules

  1. Always endorse before spawning — no exceptions
  2. Use spawn-batch.sh for 2+ tasks — starts integration watcher
  3. Never run bare claude --print in background — use spawn-agent.sh
  4. Let the watcher handle reviews — don't add review logic to prompts

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

78.41%
按下载量换算803

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 openclaw skills install claude-swarm 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills