Назад към всички

adversarial-review

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

$ git log --oneline --stat
stars:384
forks:73
updated:March 4, 2026
SKILL.mdreadonly
SKILL.md Frontmatter
nameadversarial-review
descriptionFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
allowed-toolsRead, Write, Edit, Bash, Grep, Glob, WebFetch, WebSearch, Agent, AskUserQuestion

Adversarial Review

Overview

Independent adversarial code review checking spec compliance. Uses binary PASS/FAIL verdicts (not subjective feedback) with required file:line evidence citations.

When to Use

  • After quality gates pass in the execution loop
  • 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)