agentsclimarketplace

Loop record

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

Make Codex and Claude loop orchestration easier and more powerful.

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

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

Update durable loop state after a loop iteration with completed work, proof history, decisions, blockers, and next action.

SKILL.md

0.7 KB, 144 tokens by cl100k_base, as published. Nobody here has run it

Loop Record

Use this skill at the end of a loop iteration.

Inputs

  • Active task
  • Diff summary
  • Review result
  • Proof command and output
  • Any new decisions or blockers

Process

  1. Update Proof History in loop-state.md.
  2. Clear or update Active Task.
  3. Move completed queue items to a finished state.
  4. Add durable decisions to loop-decisions.md.
  5. Write exactly one Next Action.
  6. Stop if the next action requires human input.

Output

The loop can stop only after state names:

  • what changed
  • what proved it
  • what risk remains
  • what happens next

What ships with it

Read from the repository

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

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.