agentleFS
Sign inStart free
bazaarjapanbazaarjapan/codex-autoloop-template/.agents/skills/autoloop-status/SKILL.md

autoloop-status

Skill0 starsChanged 3 months agoMITView on GitHub

Inspect and explain the current Codex AutoLoop phase, counters, specification lock, GitHub evidence, configured gates, and next safe action without modifying repository or external state. Use when the user invokes $autoloop-status or asks how an autonomous run is progressing.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read .autoloop/state.json, .autoloop/config.json, the active feature's traceability file, and relevant local Git status.

    line 10
  2. Very specific:

    Run python scripts/autoloop/autoloop.py status and python scripts/autoloop/autoloop.py validate.

    line 11
  3. Distinctive:

    If GitHub evidence is present and credentials are already configured, inspect the referenced Issue, pull requests, current head checks, …

    line 12
  4. Very specific:

    Never transition state, retry a job, comment, push, merge, or edit files under this skill.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

AutoLoop Status

Provide a read-only, evidence-backed status report.

  1. Read .autoloop/state.json, .autoloop/config.json, the active feature's traceability file, and relevant local Git status.
  2. Run python scripts/autoloop/autoloop.py status and python scripts/autoloop/autoloop.py validate. These commands are read-only.
  3. If GitHub evidence is present and credentials are already configured, inspect the referenced Issue, pull requests, current head checks, Codex reviews, and merge state without changing them.
  4. Report:
    • current phase and active feature;
    • specification lock validity;
    • iterations used versus limits;
    • evidence that has passed for the current head;
    • failing, missing, stale, or blocked evidence;
    • the next state transition and concrete action;
    • whether automatic continuation is safe.
  5. Never transition state, retry a job, comment, push, merge, or edit files under this skill. If asked to continue, hand the work to $autoloop.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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