Adversarial Verify

Prove a claim before acting on it: spawn N independent skeptics prompted to REFUTE it (optionally through distinct lenses — correctness, reproduction, security, regression, measurement) and keep it only if a majority fails. Fails closed on ties. Use to gate findings before fixing, fixes before committing, and any "clean/safe" verdict before trusting it.

ulpi-io Updated 15 repo stars

File contents

ulpi-io/autonomous-engineering commit 5f0fe0262c

Frequently asked questions

npx get-skill add ulpi-io/adversarial-verify