agentleFS
woodbearywoodbeary/later-dog/skills/laterdog/independent-review/SKILL.md

independent-review

Skill2 starsChanged 29 days agoApache-2.0View on GitHub

Have a separate cloud session review a published PR at its exact current commit, and treat its verdict as valid for that commit only.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use security-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SentrySkill

    security-review

    Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 1

    Distinctive

    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 once a job's PR is published, before anyone calls it ready.

    line 8
  2. Very specific:

    Let it run: Follow the review job with inspect_cloud_job until it settles.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “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

Independent review

Use once a job's PR is published, before anyone calls it ready. The run that wrote a change does not approve it. {{TOOLS}}

Procedure

  1. Pin the commit. inspect_cloud_job on the job: note the PR and its headSha.
  2. Start the review with review_cloud_job and a new requestKey. Pass a profileId on another backend when one is connected; a second account on the same model is the same reviewer twice, so say which you used. The supervisor briefs a separate cloud run to read the requirements, the diff, the code around it and the tests, and to write only .laterdog-review.json: the headSha, a verdict of pass or changes_requested, and a summary of its findings and what it actually checked. That file is kept as evidence and never reaches the product branch.
  3. Let it run. Follow the review job with inspect_cloud_job until it settles. Do not resume or resubmit it to see whether it is alive.
  4. Read the summary, not only the verdict. A pass that does not say what was checked, or that admits something important could not be run or inspected, counts as a finding.
  5. Watch the head. A new commit on the PR (a repair run, a push) voids the review; review the new head. No verdict comes from green CI or from a worker's confidence in its own work.

Report

The PR, the commit reviewed, the reviewer's profile, the verdict, the findings, and what the reviewer could not check.

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.