agentleFS
Sign inStart free
jaydubya818jaydubya818/MissionControl/skills/factory-watchdog/SKILL.md

factory-watchdog

Skill2 starsChanged 8 months agoMITView on GitHub

Experimental workflow for monitoring explicitly authorized delivery tasks and reporting stalled work. Use for scheduled ship follow-through.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .agent-factory/config.yaml, the optional skill_prompts.factory-watchdog entry, and the Factory configuration reference.

    line 15
  2. Very specific:

    Keep the task owner responsible for merge, post-merge verification, and cleanup unless the config explicitly assigns those actions …

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Factory Watchdog

Start with the Factory guide for workflow setup and configuration.

Read .agent-factory/config.yaml, the optional skill_prompts.factory-watchdog entry, and the Factory configuration reference. Monitor only configured projects and authorized delivery handoffs. The prompt cannot grant notification or delivery authority. A task title, branch, PR, green check, or agent summary is not authorization.

Find actionable stopped work

  • Find candidates through the configured host and read enough user-authored history to confirm the request and any later cancellation or scope change.
  • Skip active work, explicit waits, completed or cancelled tasks, ambiguous ownership, and tasks without configured delivery authorization.
  • For stopped work, identify its task-owned PR, branch, or worktree. Check live host state immediately before acting and verify the PR is still open and its head matches, or that the named worktree still contains task-owned work.

Notify only on a verified next step

Send a reminder only when the notification policy permits it and current live evidence shows a concrete next step is due. Check task history for an unchanged reminder. Use the configured destination, cadence, wording, and rate limit.

Keep the task owner responsible for merge, post-merge verification, and cleanup unless the config explicitly assigns those actions elsewhere. If target or state cannot be proven, do not message. Report DONT_NOTIFY when nothing meaningful changed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free