Adversarial Review

Spawn reviewers on the opposite model to challenge work. Reviewers attack from distinct lenses grounded in brain principles. The deliverable is a synthesized verdict — do NOT make changes.

Hard constraint: Reviewers MUST run via the opposite model's CLI (codex exec or claude -p). Do NOT use subagents, the Agent tool, or any internal delegation mechanism as reviewers — those run on your own model, which defeats the purpose.

Step 1 — Load Principles

Read references/reviewer-lenses.md. The three lenses (Skeptic, Architect, Minimalist) and their mapped principles govern reviewer judgments. If a brain/principles.md file exists, also read it and follow any [[wikilink]] references for additional principles.

Step 2 — Determine Scope and Intent

Identify what to review from context (recent diffs, referenced plans, user message).