adversarial-review
Installation
SKILL.md
Adversarial review
Two-harness review loop for AFK “get me clean code” runs. A critic (agent CLI) finds issues; a validator (codex exec, different model/provider) stress-tests each finding; the parent (this session) adjudicates and applies fixes with one commit per finding. Loop until nothing actionable remains.
Inspired by address-pr-comments for fix discipline; critic lenses from grug-review and thermo-nuclear-code-quality-review (typically ~/.agents/skills/thermo-nuclear-code-quality-review/SKILL.md).
Roles
| Role | Harness | Default | Mode |
|---|---|---|---|
| Critic | Cursor agent |
composer-2.5 |
Read-only (--mode plan) |
| Validator | codex exec |
gpt-5.5-medium |
Read-only sandbox |
| Fixer | Parent Task or agent |
configurable | Writes + commits |
| Parent | This session | — | Orchestrates, adjudicates |
Critic and validator must use different harnesses and models (enforced via config).