audit-loop
Skill0 starsChanged 7 months agoMITView on GitHub
Run a continuous audit-fix-audit loop that scores a codebase and automatically fixes gaps until a target score is reached. Use when the user asks to "get us to 10/10", "keep improving until perfect", "run a continuous improvement loop", "audit and fix automatically", or wants an autonomous cycle of scoring, generating fix tasks, executing them, and re-scoring.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- ProxiBlue/claude-skillstheir own version, first seen Oct 7, 2026
- wolverin0/claude-skillstheir own version, first seen Aug 24, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- wolverin0/claude-skills★ 41same name
- ProxiBlue/claude-skills★ 18same 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.
- check-progressSkill
- run-queueSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Check: - if score >= target (default 10.0), exit success
≈ “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.
Files
Audit-Fix Loop
Set up and run a self-sustaining loop that audits a codebase, generates fix tasks for remaining gaps, executes them, and re-audits until the target score is reached.
How It Works
Each round:
- Wait - polls for any running overnight runner to finish
- Audit - Claude CLI audits the codebase, writes a report, outputs
OVERALL_SCORE=X.X - Check - if score >= target (default 10.0), exit success
- Generate - Claude CLI reads the audit, creates a task queue for remaining gaps
- Fix - the overnight runner executes all tasks
- Repeat from step 1
Starting the Loop
nohup bash devops/cloud-coder/audit-fix-loop.sh > /tmp/audit-fix-loop.log 2>&1 &Audit Dimensions
The audit scores 7 dimensions (1-10 each): Security, Reliability, Observability, Testing, Infrastructure, Code Quality, Compliance
Key Design Decisions
- Uses claude-sonnet-4-6 for audits and queue generation (fast, cheap)
- Score comparison uses
awkto avoid bash integer arithmetic issues with decimals - Each round writes a separate audit file for historical tracking
- The runner runs in foreground within the loop so it blocks until complete
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.