본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

subagent-overseer

globalcaos 제작

Web & Frontend Development
396clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Monitor sub-agent health and progress via a pull-based bash daemon.

설명

이 스킬이 하는 일

A bash daemon that monitors sub-agent health without consuming AI tokens. It reads /proc filesystem data and calls openclaw sessions list on a configurable interval, writing results atomically to a JSON status file. The main agent reads that file on each heartbeat instead of making live tool calls.

Replaces in-agent polling loops with a zero-token OS-level daemon, so heartbeat cost stays flat regardless of how many sub-agents are running.

사용 시점

  • Detecting a stuck sub-agent in a parallel coding pipeline
  • Monitoring filesystem activity across multiple concurrent agents
  • Getting local voice alerts when an agent stops making progress
  • Checking gateway process health without spending context tokens
  • Auto-stopping the monitor once all sub-agents have finished

예시 워크플로

입력

User asks: watch my 4 sub-agents and alert me if any get stuck

에이전트
  1. 1

    Start overseer.sh in the background with --workdir, --interval 180, and --max-stale 4

  2. 2

    Overseer polls /proc for gateway health, runs openclaw sessions list, and checks find -newer each cycle

  3. 3

    Overseer writes completed JSON atomically to /tmp/overseer/status.json

  4. 4

    On each heartbeat trigger, agent reads status.json with a single cat call

  5. 5

    If any agent shows stale count >= 4, report that label as stuck and offer to kill it

출력

status.json shows subagent 'worker-2' as stuck after 12 minutes of no filesystem changes

요구 사항

  • jarvis command (local TTS via sherpa-onnx) for --voice alerts

설치

clawhub install globalcaos/subagent-overseer

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크