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 ( or ). 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 . Follow every and read each linked principle file. These govern reviewer judgments. Step 2 — Determine Scope and Intent Identify what to revi…