Multi-agent debate plugin for Claude Code — adversarial review, brainstorm, hypothesis testing with structured multi-round debates
-
Updated
Apr 8, 2026 - JavaScript
Multi-agent debate plugin for Claude Code — adversarial review, brainstorm, hypothesis testing with structured multi-round debates
Governance harness for decision-making systems with structured review, epistemic honesty, and retrospective calibration.
AI-powered research idea generation through adversarial debate. Trains a calibrated judge on 50K real reviews, then uses a 3-agent (Critic-Proposer-Judge) loop to generate and stress-test novel research ideas to publication quality.
ChatGPT, Claude, and Gemini debate each other to solve your toughest problems
Claude Code skill for deep critical analysis through multi-agent adversarial debates. Steelmanning → Advocate vs Skeptic → Chain of Verification → Hegelian Synthesis.
Portable Claude Code Standard Workflow — drop CLAUDE.md into any repo. 7-step dev process, model routing, design routing, agent orchestration. Works on CLI, Desktop, IDE, and Claude Cloud.
Add a description, image, and links to the adversarial-debate topic page so that developers can more easily learn about it.
To associate your repository with the adversarial-debate topic, visit your repo's landing page and select "manage topics."