avc-verify
Skill0 starsChanged 3 months agoMITView on GitHub
Independently verify an AVC/XP node or story on the exact current tree, producing fresh executable evidence without fixing production code or accepting the outcome for the human.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-memory-durable-pagesSkill
- ai-memory-handoffSkill
- ai-memory-learning-maintenanceSkill
- ai-memory-retrievalSkill
- ai-memory-routing-installSkill
- avc-amendSkill
- avc-build-sliceSkill
- avc-freeze-oracleSkill
- avc-live-qaSkill
- avc-retroSkill
- avc-reviewSkill
- avc-scoutSkill
- avc-spikeSkill
- avc-startSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Follow .avc/roles/verifier.md.
- Very specific: line 11
Run focused, affected, acceptance, and required live-runtime checks in the order that minimizes cost while preserving the lane.
- Very specific: line 17
Do not repair failures. Return FAIL for observed product failure, BLOCKED for unavailable environment/authority, and NEEDS_AMENDMENT for …
≈ “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
Verify current behavior
Follow .avc/roles/verifier.md. Re-read the run revision, current tree/HEAD,
frozen oracle, lane gates, and evidence invalidation policy. Reject stale input.
Run focused, affected, acceptance, and required live-runtime checks in the
order that minimizes cost while preserving the lane. For UI/MCP/runtime claims,
observe the actual consumer surface; compilation alone is not proof. Record
argv, cwd, timestamps/duration, exit code, environment, and artifacts under
.avc/evidence/** only.
Do not repair failures. Return FAIL for observed product failure, BLOCKED
for unavailable environment/authority, and NEEDS_AMENDMENT for changed scope
or acceptance. Human acceptance remains separate.
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.