avc-amend
Skill0 starsChanged 3 months agoMITView on GitHub
Create an explicit AVC/XP amendment when scope, acceptance, lane, dependency, rollback, risk, or authority must change; use instead of silently drifting the active run.
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-build-sliceSkill
- avc-freeze-oracleSkill
- avc-live-qaSkill
- avc-retroSkill
- avc-reviewSkill
- avc-scoutSkill
- avc-spikeSkill
- avc-startSkill
- avc-verifySkill
The file
Files
Amend the active contract
Act as Navigator. State the evidence that invalidated the current assumption, the exact proposed change, affected acceptance ids/nodes/paths/gates, new risk, and rollback impact. Preserve the old value and increment the run revision.
Lane promotion may proceed when configured evidence confirms the trigger.
Lane reduction, scope expansion, oracle change after freeze, dependency,
migration, waiver, and external authority require the human decision specified
in .avc/config.yaml. Until that decision exists, record the proposal and
return BLOCKED or NEEDS_AMENDMENT without changing the authorized value.
Invalidate stale evidence and graph nodes after an accepted amendment. Return the canonical result; never disguise a repair as an amendment.
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.