Loop anything

Skill rossinsilico/loop-anything/.agents/skills/loop-anything

Make Codex and Claude loop orchestration easier and more powerful.

Install

npx -y skills add rossinsilico/loop-anything --skill loop-anything

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

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.

SKILL.md

1.4 KB, 293 tokens by cl100k_base, as published. Nobody here has run it

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

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

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.