adversarial-review

SkillDev tools

Lets your agent run an adversarial code review that returns PASS or FAIL with cited evidence.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the adversarial-review skill

About this capability

Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/metaswarm/skills/adversarial-review/SKILL.md and read by ahel’s review.

  • For final comprehensive cross-unit review
  • When verifying spec compliance of any implementation

Key Differences from Collaborative Review

AspectCollaborativeAdversarial
GoalHelp improve codeVerify spec compliance
VerdictSuggestionsBinary PASS/FAIL
EvidenceOptionalRequired (file:line)
ReviewerCan be reusedMust be fresh
ContextSharedIndependent

Fresh Reviewer Rule

On re-review after FAIL, a NEW reviewer instance spawns with no memory of the previous review. This prevents anchoring bias where a reviewer fixates on previously identified issues.

Anti-Patterns

  • Reusing reviewers after FAIL
  • Passing previous findings to new reviewers
  • Providing subjective or advisory feedback
  • Accepting partial compliance as PASS

Tool Use

Invoke as part of: methodologies/metaswarm/metaswarm-execution-loop (Phase 3)

Signals

GitHub stars
2k
Forks
106
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
adversarial-review
Source
github.com/a5c-ai/babysitter