agentleFS
Sign inStart free
David-Florian2013David-Florian2013/write-then-check/skills/checker/SKILL.md

checker

Skill0 starsChanged 28 days agoMITView on GitHub

Read-only second pass for a diff another agent just wrote. Use after an edit, before anyone says the task is done. Run scripts/check.py on the unified diff and return its PASS or FAIL unchanged. Do not edit files. Use when a write-then-check loop needs the checker, or when the user asks to check a diff for a committed secret or a forbidden file.

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. ecfromthedc/ec-rt-skills★ 1same name
    2. noamgariani11/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use git diff --cached when the change is staged.

    line 19
  2. Very specific:

    If scripts/check.py is not on disk, the result is FAIL.

    line 21
  3. Distinctive:

    When the host can start a second agent, you are that agent and you have no write tool.

    line 27

≈ “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

Checker

You are the second pass. You do not edit files. You do not say the task is done. You judge one diff and stop.

Run this

The script next to this file is scripts/check.py. Pipe the unified diff into it. From a repo that is the thing being changed:

git diff | python3 scripts/check.py

Use git diff --cached when the change is staged. Use git diff <base>...HEAD when the change is a branch. The script reads stdin. It does not use the network.

If scripts/check.py is not on disk, the result is FAIL. Say the script is missing. Do not invent a PASS.

What you return

Copy the script output. Exit 0 prints PASS. Exit 1 prints FAIL plus file and secret lines. Add nothing that flips a FAIL into a pass.

When the host can start a second agent, you are that agent and you have no write tool. When it cannot, this script is the checker. Its exit code is the result either way.

What a PASS is not

A PASS means this diff did not trip the script. The script looks for a short list of secret shapes and filenames (.env, key files, credentials.json, AKIA…, ghp_…, a private-key block, a Slack token). It does not know if the code is right, if tests passed, or if the user's request was met. Say that when you return PASS. Do not add "looks good" as a substitute for the script line.

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.

Check your setup, free