agentleFS
Sign inStart free
rossinsilicorossinsilico/loop-anything/.agents/skills/loop-anything/SKILL.md

loop-anything

Skill0 starsChanged 5 months agoMITView on GitHub

Front-door skill for Loop Anything. Use when the operator invokes dog-food, create, run, prompt, or asks to turn a spec, plan, orchestration pattern, repo surface, branch, or issue into a bounded visible loop.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this as the branded entrypoint for the loop pack.

    line 8
  2. Very specific:

    Read loop-state.md, loop-contract.md, loop-decisions.md, and loop-prompts.md.

    line 31
  3. Distinctive:

    Treat the named object as the current goal surface.

    line 33
  4. Distinctive:

    Keep state visible and permission boundaries explicit.

    line 34
  5. Distinctive:

    Stop on missing proof, failed proof, destructive action, hidden credentials, or expanded permissions.

    line 36

≈ “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

Loop Anything

Use this as the branded entrypoint for the loop pack.

Command Shape

Supported invocations:

  • $loop-anything dog-food <object> --turn single|multi|infinite
  • $loop-anything create <object> --from <path> --turn single|multi|infinite
  • $loop-anything run <object> --turn single|multi|infinite
  • $loop-anything prompt --stage triage|review|prove|record|resume

Claude can use the same command text with /loop-anything.

Routing

  • dog-food or run: follow loop-dog-food.
  • create: create or update visible loop state from the named source, then follow loop-dog-food.
  • prompt: print or use the matching stage prompt from loop-prompts.md.
  • Unknown method: treat the remaining text as the work object and dogfood it.

Rules

  1. Read loop-state.md, loop-contract.md, loop-decisions.md, and loop-prompts.md.
  2. Treat the named object as the current goal surface.
  3. Keep state visible and permission boundaries explicit.
  4. Name the proof command before implementation starts.
  5. Stop on missing proof, failed proof, destructive action, hidden credentials, or expanded permissions.
  6. Record the result before ending the turn.

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