agentleFS
t-manitejat-maniteja/codex-failsafe/skills/adjudicate/SKILL.md

adjudicate

Skill0 starsChanged 3 months agoMITView on GitHub

Adjudicate the claims from a codex-failsafe review — give every claim an evidence-backed disposition (confirmed / refuted / governed / out-of-scope / open) and write the ledger entry. Use after a pre or post run, or when the user asks to work through a review's findings.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ComplexAR/Insight-Engine★ 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 repository3 other files it gives its agents.

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
  1. Distinctive:

    Read reference/adjudication.md — it is the protocol.

    line 8

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Adjudicating a review

Read reference/adjudication.md — it is the protocol. In short:

  1. Locate the raw claims — the most recent *.codex.json in .codex-failsafe/ (or the path the run printed). Never edit this file.
  2. For each claim, run its how_to_falsify first. The failsafe itself named the command or document that would prove it wrong; that is the cheapest adjudication and was chosen by the party with no stake.
  3. Assign a disposition — confirmed, refuted (evidence required), governed (citation required), out-of-scope (destination required), or open. If you cannot produce evidence against a claim, it is open, not refuted — "I disagree" is not a disposition.
  4. Route what survives: a confirmed finding is a fix, plus the test or check that should have caught it, plus a sweep of its defect_class across every sibling surface — done now, not when the next pass rediscovers the same shape one file over. An open question goes to the user with the fork stated plainly.
  5. Write the ledger entry beside the raw file: same stamp, .json extension — task, scope, the pass accounting, and each claim with its disposition and evidence.
  6. Once in a while, read the ledger backwards for the four failure smells: everything refuted (fishing or capture), falsifications never run (capture), no decision ever moved (ceremony), most findings against code the review itself caused or second instances of a class already confirmed (the loop reviewing its own output). Tell the user which smell you see; retuning or retiring the failsafe is their call.

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.