agentleFS
cyb3rcricketcyb3rcricket/cricket-mode/.agents/skills/scrub/SKILL.md

scrub

Skill0 starsChanged 51 days agoMITView on GitHub

Use when cleaning up AI-generated residue left in recent work, such as narrating comments, speculative helpers, redundant wrappers, defensive over-engineering, leftover scaffolding, and docs that restate the code.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. ZimoLiao/scholaraio★ 585same name
    2. dracocephalum/dc-agentics★ 0same name
    3. tweakyourpc/prose-hygiene★ 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 repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    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:

    Do not change code unless I ask.

    line 27
  2. Distinctive:

    If the right answer is a redesign, say so briefly and stop.

    line 29
  3. Distinctive:

    Keep these jobs separate:

    line 31
  4. Very specific:

    If something is a contradiction, say it is /drift territory and move on.

    line 37

“Common” is measured: kept by at least 6 in 10 of the 3 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

Scrub

Find agent fingerprints left in the work just done.

Strip leftover AI habits that make the code noisier without solving the asked-for problem. Do not redesign the system.

Inspect the actual recent work, changed files, or current context. Do not invent a lecture about AI code in general.

Look For

  • narrating or restating comments,
  • speculative helpers or abstractions not required by the asked-for change,
  • redundant wrappers and pass-through layers,
  • defensive try/catch or null guards that paper over real issues,
  • leftover scaffolding, unused imports, and dead example code,
  • docs or comments that duplicate what the code already says.

Separate real residue from intentional design. Do not invent problems.

For each finding, show the path and a snippet, why it looks like agent residue, and the surgical fix: delete, simplify, or inline.

Do not change code unless I ask. Propose the removal first.

If the right answer is a redesign, say so briefly and stop. That belongs to a different conversation.

Keep these jobs separate:

  • /drift finds where the project disagrees with itself.
  • /challenge tries to break the idea: bugs, weak assumptions, edge cases.
  • /scrub finds leftover agent habits.

If something is a contradiction, say it is /drift territory and move on. If something is a bug or a weak assumption, say it is /challenge territory and move on.

Core Rule

Strip the agent fingerprints. Don't redesign the work.

Finish with:

Residue: concrete findings with evidence and surgical fixes.

Keep: things that look intentional or load-bearing, briefly.

Out of scope: anything that belongs to /drift or /challenge instead.

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.