feat: auto-scaled adversarial review by diff size

Replace config-driven Codex review step with automatic adversarial review
that scales by diff size: small (<50 lines) skips adversarial, medium
(50-199) gets cross-model adversarial, large (200+) gets all 4 passes.

Adds Claude adversarial subagent as fallback when Codex unavailable.
Review log uses new "adversarial-review" skill name with source/tier fields.
Dashboard updated to read both adversarial-review and legacy codex-review.

review/SKILL.md.tmpl

@@ -13,6 +13,7 @@ allowed-tools:
   - Write
   - Grep
   - Glob
+  - Agent
   - AskUserQuestion
 ---
 
@@ -231,7 +232,7 @@ If no documentation files exist, skip this step silently.
 
 ---
 
-{{CODEX_REVIEW_STEP}}
+{{ADVERSARIAL_STEP}}
 
 ## Important Rules