self-audit
Skill2 starsChanged 16 days agoMITView on GitHub
The self-improving consistency loop - mine what the maintainer had to point out, audit the whole repository for drift between sources of truth, propose each finding as a failing check (draft pull request) or an issue, measure precision and escapes in a public ledger, and, rarely, improve the two auditing agents against recorded cases. Arguments tier=mine|weekly|deep (default weekly) and dry-run. Use from a scheduled task, before a release, or when asked to audit the repository.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- provenwork/noblufftheir own version, first seen Nov 16, 2026
- 5uck1ess/devkittheir own version, first seen Nov 15, 2026
- 0xUrsanomics/utopia-ostheir own version, first seen Nov 1, 2026
- daichi-0818/claude-code-ops-kittheir own version, first seen Oct 15, 2026
- poa-box/poa-clitheir own version, first seen Jul 31, 2026
- faizkhairi/claude-code-blueprinttheir own version, first seen Jul 3, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- faizkhairi/claude-code-blueprint★ 73same name
- 5uck1ess/devkit★ 4same name
- 0xUrsanomics/utopia-os★ 2same name
- jamestexas/agents★ 2same name
- poa-box/poa-cli★ 2same name
- provenwork/nobluff★ 2same name
- Xxt-XN/agent-self-audit★ 1same name
- daichi-0818/claude-code-ops-kit★ 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 repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/CLAUDE.mdCLAUDE.md
- starter/CLAUDE.mdCLAUDE.md
- template/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- add-moduleSkill
- add-operationSkill
- codifySkill
- raise-the-barSkill
- releaseSkill
- reviewSkill
- scaffold-pluginSkill
- ship-smallSkill
- write-adrSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
0
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
- Very specific: line 30
Audit: Start consistency-auditor with the ledger summary from steps 1–2.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Self-audit
The loop finds what would otherwise need the maintainer to point it out. It proposes; the maintainer decides. It
never merges, never marks a pull request ready, never pushes to main and never edits its own guardrails.
Arguments. tier=mine (nightly: step 1 only), tier=weekly (default: steps 2–6 and 8), tier=deep (monthly:
steps 1–8). dry-run runs every step but 5 and 7, writes nothing outside the report and appends nothing to the ledger.
Budgets. mine: model haiku, at most 20 turns. weekly: at most 60 turns and 30 minutes. deep: at most 120 turns and 60 minutes. Stop at the budget and report what is unfinished.
State. .claude/audit/ledger.jsonl is append-only, one JSON object per line, with a kind of correction,
finding, outcome, metrics or self-edit. The repository is public: the ledger holds fingerprints, classes and
paraphrases of at most 15 words, never quotes, names or transcript paths. Create it empty if it is missing.
.claude/audit/inbox/ is git-ignored; the SessionEnd hook queue_transcript.py appends transcript paths to its
queue.
Steps
- Mine (tiers mine and deep). Start
correction-miner. Append its lines to the ledger, then empty.claude/audit/inbox/queue. Tier mine stops here and reports counts per class and recurrences. - Record outcomes.
gh issue list --label audit --state all --json number,state,title,body,closedAtand the same forgh pr list. Append anoutcomeline per proposal decided since the last run: merged =accepted, closed unmerged =rejectedwith the closing comment paraphrased as the reason, open more than 14 days =stale. - Audit. Start
consistency-auditorwith the ledger summary from steps 1–2. On tier deep, start it with modelfableand effortmax, and ask it to also compare I8 with two or three well-regarded peer projects, as skillraise-the-bardoes. - Select. Drop findings whose fingerprint is open in the ledger, whose class was rejected twice, that are
Unconfirmed, or that match a
do_not_codifycorrection. Keep at most five; at most two become pull requests. - Propose (skipped on dry-run). Titles and bodies pass
uv run --script scripts/check_confidentiality.py --text.- A finding with a failing check: in a fresh worktree from
origin/main, apply skillcodify(a plugin without it adds the check undertests/unit/), fix the violations, thenDRAFT=1 make pr TITLE="test(dx): ...". Label itauditand put the fingerprint in the body. Never enable auto-merge, never mark it ready. - Any other finding: one issue labelled
auditwith the fingerprint, the evidence and the proposed check. - Append a
findingline per proposal: fingerprint, class,prorissueand its number.
- A finding with a failing check: in a fresh worktree from
- Measure. Over the last 90 days: precision = accepted / (accepted + rejected); escapes = new A–F corrections
whose location no earlier finding named; recurrences = corrections marked
recurrence; cost = turns and minutes of this run. Append onemetricsline. - Improve itself (tier deep only, at most once a month, and only after at least ten decided proposals since the
last
self-editline). Propose one change of at most 30 lines to.claude/agents/consistency-auditor.mdor.claude/agents/correction-miner.md, aimed at the escapes and rejections. Score current and proposed prompts against every case in.claude/audit/evals.yaml(skip this step when the file is missing): for each case, a worktree at itscommit, the agent on modelsonnet, a hit when it reports the expected class at the expected location. Open a draft pull request only if the proposal misses no case the current prompt catches and catches at least one more; append aself-editline either way. Never edit this skill, the budgets, the guardrails, the safety or confidentiality lines of the agents, or any test. - Report. Findings kept and dropped (with the reason), proposals opened, outcomes recorded, the metrics line, and anything unfinished. On dry-run, the proposals that would have been opened.
Scheduling
The maintainer schedules the loop as local desktop scheduled tasks in this repository, not CI (transcripts are
local): nightly /self-audit tier=mine, weekly on Monday /self-audit tier=weekly, and monthly on the first Monday
/self-audit tier=deep.
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.

