agentleFS
Sign inStart free
timursafiullintimursafiullin/aod/skills/verify/SKILL.md

verify

Skill0 starsChanged 29 days agoApache-2.0View on GitHub

Verify an AOD task an implementer finished - deterministic gates first, then a fresh-context review of the diff, then a verdict (ACCEPT, REVISE or REJECT). Use when a delegated task reaches review status.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use instinct-export, instinct-import and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TheKREATORSSkill

    instinct-export

    Export instincts from project/global scope to a file

    Also in 3 projects that use this

  • TheKREATORSSkill

    instinct-import

    Import instincts from file or URL into project/global scope

    Also in 3 projects that use this

  • AviadPSkill

    risk-assess

    Assess the risk and blast radius of a proposed code change before implementing it. Evaluates CI impact, framework-wide vs localized scope, rollback path, and identifies blindspots. Use when user says "what's the risk", "is this safe", "assess the impact", "risk assess", "blast radius", or before applying framework-wide or CI-affecting changes. Do NOT use for code quality review (use code-quality) or plan validation (use design-validator).

    Also in 3 projects that use this

  • diego-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 6 projects that use this

  • AaravChadhaSkill

    secure

    Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high/medium/low confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization/crypto/transport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.

    Also in 3 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 10 projects that use this

  • +1 more from TheKREATORS

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If mutation.command is configured, a mutation run on the changed source files comes last.

    line 20
  2. Very specific:

    REVISE: write the findings to .agents/tasks/jobs/T-xxxx/findings-<round>.md, one per line:

    line 35

“Common” is measured: kept by at least 6 in 10 of the 167 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.

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

Verify T-xxxx

Cheapest check first; stop at the first failing level. CLI: aod means node "${CLAUDE_PLUGIN_ROOT}/scripts/aod.mjs".

1. Gates (no model tokens)

aod gates T-xxxx

Checks commits, clean slot at codex/T-xxxx, scope and forbidden paths, added skip/only/xfail markers, report schema, and re-runs every acceptance command in the slot. Any failure -> REVISE with one blocker finding per failed gate. A weakened, skipped or edited test is always a blocker. Integrity checks also fail on deleted tests and on production code that detects a test run; they only warn (warnings in the result) on modified existing tests, changed tolerances and comparisons against acceptance-test literals. Pass every warning to the reviewer. If mutation.command is configured, a mutation run on the changed source files comes last. A score below the threshold means surviving mutants: the tests do not check that code. Treat it as a major finding asking for stronger tests, or a blocker when mutation.level is fail. Pass --no-mutation only for a quick re-check.

2. Fresh-context review

Launch the aod:reviewer subagent (fresh context; do not review the diff in your own long context). Give it only: the task id, the slot path (from aod status), the main repository path and any gate warnings. It is read-only and returns a verdict and findings. Also run the unit tests of the touched packages if the acceptance commands do not cover them.

3. Verdict

  • ACCEPT: gates green, no blocker/major findings -> /aod:close T-xxxx. Minor findings go to the journal's backlog line.
  • REVISE: write the findings to .agents/tasks/jobs/T-xxxx/findings-<round>.md, one per line: F1 [blocker] path:line - <problem>. Required: <change>. Verify: <command>. Then resume the same Codex thread in the background: aod revise T-xxxx --findings <file> and verify again when notified (exit 5: Codex unavailable, stop and ask the user). rounds in the ledger counts REVISE rounds only. Exit 4 means the 3-round limit is reached: escalate to the user with the task, the disagreement, options and a recommendation.
  • REJECT (wrong approach, wrong brief, repeated scope escapes): aod reject T-xxxx, then rewrite or split the packet.

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.

Check your setup, free