Debate Agent

Orchestrates competitive code review debates between CLI-based language models with deterministic scoring to generate merged recommendations and declare winners.

Enables multi-agent debates for code review where multiple language models analyze code changes through structured debate mechanics. Features severity-based scoring for issues, multiple debate modes including adversarial and consensus approaches, and deterministic point-based judging. Integrates with Claude Desktop, Claude CLI, and VS Code to provide collaborative code review workflows through agent competition.