← 返回 Skills 市场
78
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install codex-swarm
功能描述
OpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to work in parallel with git worktrees,...
使用说明 (SKILL.md)
Codex Swarm — Multi-Agent Orchestration
Parallel Codex agents: plan → endorse → spawn → monitor → review → integrate → ship.
Quick Start
# 1. Write task prompts
cat > /tmp/prompt-task1.md \x3C\x3C 'EOF'
Implement feature X...
EOF
# 2. Create tasks JSON
cat > /tmp/tasks.json \x3C\x3C '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
bash scripts/spawn-batch.sh "/path/to/project" "batch-1" "Description" /tmp/tasks.json
Roles & Models
| Role | Model | Reasoning | Use |
|---|---|---|---|
| architect | o3 | high | Design, planning, complex decisions |
| builder | codex-mini | medium | Feature implementation (parallel) |
| reviewer | o3 | medium | Auto-review via codex exec review |
| integrator | o3 | high | Cross-branch merge + conflict resolution |
Key Codex Features Used
codex exec --full-auto— non-interactive sandboxed executioncodex exec review— native code review (replaces custom reviewer)-c model=o3— deep reasoning model for complex tasks-c model_reasoning_effort=high— maximum reasoning depth
Scripts
| Script | Purpose |
|---|---|
spawn-batch.sh |
Spawn N parallel agents + integration watcher |
spawn-agent.sh |
Spawn single agent (manual worktree + tmux + codex exec) |
endorse-task.sh |
Endorse task before spawn |
check-agents.sh |
Show running agent status |
cleanup.sh |
Remove worktrees, branches, sessions |
notify.sh |
Webhook/Telegram notification |
notify-on-complete.sh |
Auto-watcher with native codex exec review |
integration-watcher.sh |
Auto-merge when batch completes |
Setup
- Copy
scripts/andconfig/to your workspace - Configure
config/swarm.conf(copy from.example) - Required:
bash 4+,tmux,git,gh,jq,codex(Codex CLI)
安全使用建议
This skill appears to implement the advertised swarm orchestration, but it underdeclares its requirements and includes powerful actions (auto-commit, conflict auto-resolution via codex exec, force-push, branch deletion, and optional webhook/Telegram notifications). Before installing or running it:
- Treat it as code that will run with your user credentials: test it in a disposable/forked repository (not your production repo or main branch).
- Inspect or create config/swarm.conf yourself; do not set SWARM_WEBHOOK_URL or Telegram tokens until you trust the workflow. Webhooks will transmit the message text off-host.
- Disable automatic merges by setting SWARM_AUTO_MERGE=false and review the integration-watcher logic.
- Prevent automatic endorsement if you want manual gating: modify spawn-batch so it doesn't auto-run endorse-task, or require a different endorsement workflow.
- Ensure your git/GH credentials are limited (use a machine/service account with minimal permissions) or remove push rights when testing.
- Check logs and prompt files (SWARM_DIR/logs and /tmp worklogs) for sensitive content and delete them if necessary.
If you want to proceed, update the skill metadata to list required binaries and the environment variables it uses, and consider hardening the scripts (explicit manual approval steps, remove force-push/delete actions, and avoid sending prompt contents to external endpoints).
功能分析
Type: OpenClaw Skill
Name: codex-swarm
Version: 1.0.0
The skill bundle implements a multi-agent orchestration framework that executes AI-generated code with high privileges using 'codex exec --full-auto' and performs automated 'git push' operations to remote repositories (found in scripts/integration-watcher.sh and scripts/notify-on-complete.sh). While the tool includes a manual 'endorsement' safety gate (scripts/endorse-task.sh) and is aligned with its stated purpose of parallel coding, the combination of arbitrary code execution, automated repository modification, and external data exfiltration via webhooks or Telegram (scripts/notify.sh) constitutes a high-risk environment that could be exploited if the underlying AI models are manipulated.
能力评估
Purpose & Capability
The name/description (Codex multi-agent orchestration) matches the included scripts: spawning tmux sessions, worktrees, codex exec runs, reviews, merges and notifications. However the registry metadata claims no required binaries/env vars while SKILL.md and the scripts explicitly require bash 4+, tmux, git, gh, jq, and the codex CLI — an incoherence between declared requirements and actual needs.
Instruction Scope
Runtime instructions and scripts read/write local files (prompts, logs, /tmp worklogs), create and remove git worktrees/branches, run codex exec (which executes model-driven changes), and can auto-commit, auto-resolve conflicts, and push to origin/main. They also support sending messages to arbitrary webhook URLs or Telegram tokens if configured. spawn-batch auto-calls endorse-task (so the endorsement gate is effectively automatic), and notify-on-complete does force pushes. These actions go beyond passive orchestration and can modify remote repositories and transmit messages externally.
Install Mechanism
No install spec is provided (instruction-only with bundled scripts). That lowers the risk of arbitrary remote code downloads. The presence of multiple executable scripts means code will run on the host, but nothing is being fetched from unknown URLs during install.
Credentials
The manifest declares no required environment variables, but scripts read many configuration variables (SWARM_NOTIFY, SWARM_WEBHOOK_URL, SWARM_TELEGRAM_BOT_TOKEN, SWARM_TELEGRAM_CHAT_ID, SWARM_AUTO_MERGE, SWARM_ENDORSEMENT_COOLDOWN, SWARM_MAX_REVIEW_ROUNDS) via config/swarm.conf or env. The scripts implicitly rely on git/GH credentials already present on the machine to push/delete branches. Requiring or using webhook/telegram tokens and having the ability to push/force-push/delete remote branches is a high-privilege operation that is not called out in the metadata.
Persistence & Privilege
always:false (good), but autonomous invocation is allowed (normal). Combined with default behavior in scripts (automatic endorsement via spawn-batch, SWARM_AUTO_MERGE default=true, force-with-lease/force pushes, branch deletion in cleanup.sh when called with --all), the skill can autonomously modify remote repositories and remove branches. It also writes persistent logs and prompt files containing prompt contents, which may include sensitive data.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install codex-swarm - 安装完成后，直接呼叫该 Skill 的名称或使用
/codex-swarm触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of codex-swarm.
- Enables multi-agent orchestration for parallel coding using OpenAI Codex models.
- Supports spawning and coordinating multiple Codex CLI agents (architect, builder, reviewer, integrator) via batch scripts.
- Integrates with git worktrees, tmux sessions, endorsement gates, native code review, and automated merging.
- Includes scripts for agent management, status checking, notifications, and automated review/integration.
- Simple setup with modular scripts and configuration files.
元数据
常见问题
Codex Swarm 是什么？
OpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to work in parallel with git worktrees,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 78 次。
如何安装 Codex Swarm？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install codex-swarm」即可一键安装，无需额外配置。
Codex Swarm 是免费的吗？
是的，Codex Swarm 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Codex Swarm 支持哪些平台？
Codex Swarm 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Codex Swarm？
由 linkbag（@linkbag）开发并维护，当前版本 v1.0.0。
推荐 Skills