agentleFS
scoobydont-666scoobydont-666/shared-claude-skills/skills/exact-head-review/SKILL.md

exact-head-review

Skill1 starsChanged 33 days agoMITView on GitHub

Resolve the live PR head and verify an isolated checkout before reviewing or recording an exact-revision verdict.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Create a new detached worktree at that exact commit in an operator-chosen review directory.

    line 11
  2. Very specific:

    Read the actual diff and consumers.

    line 12
  3. Distinctive:

    No script is bundled for this workflow.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Review the actual pull-request head

A supplied SHA is a claim. Resolve the current head independently through the repository API or gh pr view --json headRefOid,baseRefOid,state. Confirm repository identity and open state. Compare full object IDs, never short prefixes.

  1. Record the resolved head and base, repository, PR number and retrieval time.
  2. Fetch the PR's ref through the verified repository remote. Check command success, then verify the fetched object equals the API head. Stop on mismatch or unavailable evidence; do not use stale FETCH_HEAD.
  3. Create a new detached worktree at that exact commit in an operator-chosen review directory. Do not reuse, reset or clean another worktree. Confirm both HEAD and clean tracked/untracked state before testing.
  4. Read the actual diff and consumers. A nonempty diff does not prove the behavior is wanted; a test count does not prove a guard can fail. Use mutation-check for important negative paths.
  5. Re-read live head/base before issuing the verdict. If either changed, identify affected evidence and review the new candidate. Do not transfer approval by branch name.
  6. Report full revision, findings, executed checks, limits and whether the verdict is current. Remove only your clean disposable worktree with git worktree remove; preserve dirty evidence for inspection.

No script is bundled for this workflow. Use the available repository connector or installed Git/GitHub CLI, and report unavailable dependencies explicitly.

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.