# Adversarial Review

> Reusable adversarial review methodology for prosecution, defense, design challenge, and proxy review passes. Use when reviewing code, plans, designs, or external review ledgers with evidence-first rigor; also when prosecuting a remedy for the defect class it closes, when a change demotes or removes a signal, when judging whether a proposed guard or a substring pin actually holds, when a finding narrows a guard or hardens a selector, and when the thing under review is a newly built mechanism. DO NOT USE FOR: final judgment ownership, GitHub intake routing, or fix execution decisions (use review-judgment or code-review-intake).

## Facts
- Page: https://tashan.sh/capability/skill-grimblaz-adversarial-review
- tashan id: skill:Grimblaz/adversarial-review
- Source: https://github.com/Grimblaz/agent-orchestra
- Type: skill
- Category: security
- tashan score: 47.0 / 100
- Adoption: 14.0
- Upkeep: 82.0
- Freshness: 99.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: MIT
- Official: no

## Install

```sh
cp -r adversarial-review ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-14 by tashan (https://tashan.sh) from public evidence. Scorer s5.