Agent skill · operations · aiskillstore
low-frequency-thread-monitor
低频巡检 Skill for ordinary non-Goal Codex controller windows that need active, ETA-aware monitoring of background worker/review/planning threads. Use to keep the monitor alive until a terminal state, reduce context pollution and token spend, avoid over-polling, minimize expected wasted waiting time, and decide the next allowed action only after a final report, failure, or blocker appears.
Why this skill is useful
Provides a specialized monitoring workflow for background threads that minimizes wasted waiting time and context pollution, which the AI wouldn't reliably generate on its own.
What it needs
About 5k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
低频巡检 Skill Purpose Monitor a background Codex thread with minimal reads, no interruption, and low wasted waiting time. This skill is monitoring only. It does not authorize writes, approvals, closure, gate unblocks, active promotion, or PROJECTB consume/display changes. Use it for ordinary non-Goal controller windows that still need to keep background work moving. It complements Goal mode; it does not replace durable Goal workflows. State Model Keep these states separate: Foreground monitor state: the controller is active, waiting, checking, absorbing, blocked, or done. Background worker state: the worker is running, finalizing, completed, failed, blocked, or asking Owner. Governance state: self-report, review, absorption, approval, and routing are separate steps. Pending next check means the monitor is still active, even if no foreground text is being generated. Hard Rules 1. If the target thread is still running and a next check is scheduled, the monitor is still active. Do not send a final answer that closes, archives, marks complete, abandons, or replaces the monitoring window. 2. Use a wakeup, automation, timer, or thread-continuation mechanism for the next check when available. If unavailable, say that limitation and the exact next check time, but do not claim monitoring is complete. 3. Do not nudge or steer a running thread with messages like "continue", "hurry", "are you done", or "report progress". 4. Read only recent status while monitoring. Use turnLimit: 2 or 3 and includeOutputs: false by default. 5. Use includeOutputs: true only for failure diagnosis, a small cited final output, or an explicit Owner request. 6. Stop polling only when a final report, failure, blocker, handoff, or Owner-input request is visible. 7. After completion, read the final report seriously, then check named artifacts and governing fact files only as needed before recommending the next allowed action. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/low-frequency-thread-monitor