{"name":"prime-radiant-inc-parallel-adversarial-review","owner":{"name":"ClaudePluginHub"},"plugins":[{"name":"prime-radiant-inc-parallel-adversarial-review","source":{"source":"github","repo":"prime-radiant-inc/parallel-adversarial-review"},"description":"Two skills for adversarial code review. parallel-adversarial-review dispatches two same-model reviewer subagents in parallel under a competitive scoring frame, aggregating findings and taking the worst severity on disagreement. multi-model-adversarial-review extends this to N installed coding-agent CLIs (claude, codex, gemini, opencode, amp, aider) with a cross-critique stage that catches hallucinations and severity inflation, then synthesizes a deduplicated report. Includes a fixture-based eval suite that scores precision and recall against planted defects.","version":"0.1.0","strict":true,"keywords":["code-review","adversarial","multi-model","evaluation"],"category":"development"}]}