/adversarial

Identifies failure modes, attack vectors, and security risks in provided system or code, applying adversarial constraints like no good faith assumptions and human factors.

Runs adversarial code review on uncommitted changes: challenges design decisions, probes assumptions, identifies failure modes, questions trade-offs with severity-rated recommendations.

Run the adversarial quality pipeline on a managed file. Extracts behaviour, generates black-box tests, and validates via mutation.

Run three-agent adversarial analysis -- advocate builds the case, adversary challenges it, judicial analyst synthesizes