a5c-ai/adversarial-review
library/methodologies/metaswarm/skills/adversarial-review/SKILL.md
Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
$ install --global
skillsauthnpx skillsauth add a5c-ai/babysitter adversarial-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 1, 2026, 11:55 AM56.8s2 files scanned
SKILL.md
- name:
- adversarial-review
- description:
- Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
- allowed-tools:
- Read, 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
| 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)
Related Skills
a5c-ai/model-card-generator
development
VerifiedTrustedCommunity
Model documentation skill for generating model cards following Google's model card framework.
680SKILL.mdUpdated Apr 28, 2026
a5c-ai/mlflow-experiment-tracker
development
VerifiedTrustedCommunity
MLflow integration skill for experiment tracking, model registry, and artifact management. Enables LLMs to log experiments, compare runs, manage model lifecycle, and retrieve artifacts through the MLflow API.
680SKILL.mdUpdated Apr 28, 2026
a5c-ai/lime-explainer
data-ai
VerifiedTrustedCommunity
LIME-based local explanation skill for individual predictions across tabular, text, and image data.
680SKILL.mdUpdated Apr 28, 2026
a5c-ai/kubeflow-pipeline-executor
devops
VerifiedTrustedCommunity
Kubeflow Pipelines skill for ML workflow orchestration, component management, and Kubernetes-native ML.
680SKILL.mdUpdated Apr 28, 2026