All skills
cat-xierluo avatar

/multi-agent-orchestration

@41268aa

编排两个以上边界独立的本地 worker,使用 Orca Run/Task/Dispatch、独立 worktree/session 或 tmux 回退,由 PM 负责拆解、派发、巡检、429 停滞恢复、独立验收、PR 收口与临时资源清理;也用于用户明确要求“并行推进”“多个 worker”“PM 总控”“Wave Autopilot”或防止 PM 直接实现逃逸。不要用于单个短任务、纯状态同步,或仅需 Git 分支、提交、PR、merge 规则的工作。

Use this Skill: https://skilld.dev/gh/cat-xierluo/legal-skills/multi-agent-orchestration

This session only. Nothing lands on disk.

templatescodex-heartbeat-wait.md

≈407 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Codex Heartbeat Wait Template

使用时机:Codex App 作为 PM,需要低成本定期巡检一个 tmux / 独立 worker,而不是让主会话一直阻塞等待。

Heartbeat Prompt

你是 Codex PM 的 worker heartbeat。

每次唤醒只做一次轻量巡检,不要接管 worker 的业务实现:

1. 运行或等价执行:
   `{{skill_path}}/scripts/wait-worker.sh --session-context "{{session_context_path}}" --tmux-session "{{tmux_session}}" --once`
2. 如果输出是非终态:
   - 只汇报 status、phase、progress、current_action、next_action。
   - 不读取完整日志,不修改业务文件。
3. 如果输出是 done / failed / blocked / stopped:
   - 读取 `RESULT.md` 和 `PATCH_SUMMARY.md` 的摘要。
   - 汇报 worker 终态、验证结果、PR/commit 信息、需要 PM 处理的事项。
   - 提醒 PM 暂停或删除本 heartbeat。
4. 如果 `STATUS.json` 缺失或过期:
   - 只引用 `wait-worker.sh` 输出中的 tmux tail 诊断。
   - 需要纠偏时建议 PM 发送 checkpoint-only correction,不要自行实现业务代码。

边界:
- 不手写 raw RRULE 或自动化配置。创建、修改或删除 Codex automation 时必须先查找并使用 `automation_update` 工具。
- 不输出 token、settings、完整环境变量或敏感日志;如工具输出已脱敏,保留脱敏文本即可。
- 除非 PM 明确要求,不要 kill session、清理 worktree、push、merge 或创建 PR。

Completion Rule

Heartbeat 看到终态后,本轮回复必须明确写:

Heartbeat can stop: worker reached {{terminal_status}}.

Source: SKILL.md on GitHub

1 alert10d3 checks · Risk HIGH
  • Gen Agent Trust Hub10d

    The skill is a comprehensive multi-agent orchestration framework designed to manage multiple AI agents across isolated git worktrees and terminal sessions. It incorporates robust internal security controls such as an installation guard and a scope guard to limit the actions of sub-agents. It uses pinned executables and cryptographic hashes to verify script integrity. A potential risk of indirect prompt injection exists because the manager agent processes output from worker agents, but this is inherent to its function and mitigated by instructional boundaries and secret redaction.

  • Socket10d

    2 alerts: gptSecurity, gptAnomaly

  • Snyk10d

    Risk: LOW · No issues

Signed by skilld at 41268aa. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated yesterday
Other metadata
metadata
{
  "version": "2.31.1",
  "homepage": "https://github.com/cat-xierluo/legal-skills",
  "author": "杨卫薪律师(微信ywxlaw)"
}

README badge

README badge for cat-xierluo/legal-skills/multi-agent-orchestration