scrub
Skill0 starsChanged 37 days agoApache-2.0View on GitHub
Sweep this repository for inconsistency and drift - markdown lint, unresolved links, unfilled placeholders, mixed line endings, privacy, settings that no longer match reality, an incomplete AGENTS.md index, stale TODO entries, and drift in the files forked from dotnet new templates. Reports; does not fix.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- ZimoLiao/scholaraiotheir own version, first seen Oct 8, 2026
- cyb3rcricket/cricket-modetheir own version, first seen Sep 26, 2026
- tweakyourpc/prose-hygienetheir own version, first seen Apr 4, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ZimoLiao/scholaraio★ 585same name
- cyb3rcricket/cricket-mode★ 0same name
- 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 repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- change-trackingSkill
- newSkill
- optimizeSkill
- reviewSkill
- source-controlSkill
- upgradeSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
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
- Distinctive: line 20
Read the first that exists and follow it as written.
“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.
Files
A consistency and drift pass. Not a bug hunt - that is the built-in
/code-review. Not a rules review - that is /review. Not about what
the documents cost to read - that is /optimize. Building, testing
and dependency licences are deliberately outside it, so a scrub stays cheap
enough to run without deciding to.
Find the standard
agentics/rules/scrub.md- an initialized repositoryrepo/scrub.md- the dc-agentics toolkit, which adds its own checks on top ofrepo/payload/agentics/rules/scrub.md
Read the first that exists and follow it as written. Never scrub from memory: the checks exist because each one caught something that review did not.
Scope
The whole repository, always. Most checks are repository-wide by nature - the
AGENTS.md index, .agentics.yaml truthfulness, TODO.md, baseline drift,
duplication - and a narrowed pass reported as clean is worse than no pass. If
$ARGUMENTS names paths, run everything and lead the report with those.
Report
A findings table - number, check, pass / fail / skipped, and detail - with
what would close each failure. Change nothing. Fixes happen only when asked,
as a separate reviewable change, and a baseline drift is a decision for the user
rather than a file to rewrite.
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
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.