findings-ledger
Skill0 starsChanged 4 months agoMITView on GitHub
Track every review finding to an explicit, recorded disposition so nothing is lost in conversational triage. Use when triaging code-review or audit findings (agent or human), before merging a branch that received review feedback, or when deferring or rejecting a finding. Skip when a review produced zero findings.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- LazyIsEfficient/agentic-ostheir own version, first seen Oct 22, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- LazyIsEfficient/agentic-os★ 17same 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 repository16 other files it gives its agents.
- answer-shapesSkill
- claim-verificationSkill
- create-prSkill
- git-safetySkill
- invariant-auditSkill
- lossless-doc-compressSkill
- model-orchestrationSkill
- office-hoursSkill
- plan-reviewSkill
- prompt-caching-playbookSkill
- review-ratchetSkill
- spec-fidelity-reviewSkill
- staff-reviewSkill
- systematic-debuggingSkill
- test-adequacy-reviewSkill
- verification-before-completionSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 36
Every disposition cites evidence.
- Distinctive: line 38
Never end a session with findings outside the ledger.
≈ “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
Findings ledger
A finding may only leave the conversation through the ledger. Verbal triage ("agreed, will fix", "accepted, known risk") is how confirmed findings ship to production.
The ledger
One file per branch or PR — REVIEW-LEDGER.md unless the repo says otherwise
— with append-only rows:
| ID | Finding (1 line + source) | Disposition | Evidence |
Exactly four dispositions:
- fixed — commit hash plus the check that proves the fix
- deferred — ticket/issue link, never a prose promise
- refuted — the code or output that disproves the finding
- accepted-risk — one-line rationale, named human who accepted it
Rules
- Record findings at intake, before fixing anything — the fix session is where findings get lost.
- Every disposition cites evidence;
verification-before-completionapplies to the "fixed" rows. - Never end a session with findings outside the ledger; the ledger is the handoff to the next session.
- Merge gate: no rows without a disposition. Accepted-risk is a valid answer; silence is not.
- A dropped fix (revert, force-push, "delete that commit") reopens every row whose evidence pointed at it — re-check the ledger before any reply or PR text cites those rows.
Provenance
Distilled from an internal retrospective of two production PRs (2026-08): roughly a third of the second-pass reviewer's comments were re-discoveries of findings agent reviews had already reported and lost in conversational triage.
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.

