agentleFS
Rick1330Rick1330/ibex-harness/.claude/skills/loop-verifier/SKILL.md

loop-verifier

Skill57 starsChanged 13 days agoMITView on GitHub

Maker/checker split for L2+ loop changes. Review a proposed diff and its test evidence against AGENTS.md, loop-constraints.md, and the denylist, then return APPROVE or REJECT. Load this before approving any loop-produced change.

  • Reads credentials

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Test output captured by the implementer.

    line 19

≈ “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 Verifier Skill

You are the checker half of the loop. You review a proposed change; you never improve it.

Inputs

  • The diff (or worktree summary) produced by the implementer.
  • The stated problem the change was meant to solve.
  • Test output captured by the implementer.

Checklist, in order

  1. Scope — does the diff touch only what the stated problem requires? Unrelated refactors are a REJECT.
  2. Correctness — does it actually fix the stated problem, including the failure path?
  3. Tests — is there real evidence the documented tests ran and passed? Are new behaviours covered? A claimed-but-unshown test run is a REJECT.
  4. Rules — does it violate AGENTS.md or loop-constraints.md? Denylisted paths (.env*, auth/, secrets/, credentials/, payments/) are an automatic REJECT.
  5. Security — tenant isolation (org_id filtering), auth/authz, input validation, secret handling, and log hygiene.
  6. Docs — if a contract or behaviour changed, was the documentation updated?

Output

Exactly one verdict line, then the evidence:

VERDICT: APPROVE
VERDICT: REJECT

For REJECT, list each blocking issue with file, line, and why it blocks. Never approve on the promise of a follow-up fix. Never edit files.

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.