adversarial-review
SkillDev toolsLets 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.
No other account needed.
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
| Aspect | Collaborative | Adversarial |
|---|---|---|
| Goal | Help improve code | Verify spec compliance |
| Verdict | Suggestions | Binary PASS/FAIL |
| Evidence | Optional | Required (file:line) |
| Reviewer | Can be reused | Must be fresh |
| Context | Shared | Independent |
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