loop-nanny

Monitor, triage, and clean up after agent loops. The agent-loop skill starts loops. This skill keeps them healthy.

Poll every 2–3 minutes. A story typically takes 3–8 minutes (test-write → implement → review → judge). If a story shows no progress for 10+ minutes, something is stuck.

| ✅ PASS | Story completed | None | | ⏭ SKIP | Exhausted retries | Check if code landed anyway (common — see Skip Triage) | | ▶ STORY.DISPATCHED | Implementor running | Wait | | ▶ TESTS.WRITTEN | Reviewer running | Wait | | ▶ CHECKS.COMPLETED | Judge evaluating | Wait | | ▶ STORY.RETRIED | Failed, retrying | Check attempt output for patterns |

監視正在運行的代理循環、對故障進行分類、完成後進行清理並決定何時進行幹預。當循環正在運行並且需要臨時看護時、當循環剛完成並且需要合併後驗證時、當故事跳過/失敗並且需要診斷時或當過時的測試工件需要清理時使用。觸發：「檢查循環」、「循環發生了什麼」、「循環完成」、「循環後清理」、「為什麼跳過那個故事」、「監視循環」、「保姆循環」或任何啟動後循環管理任務。與代理循環技能（處理啟動循環）不同。 來源：joelhooks/joelclaw。