ai-debate

ai-debate is a plugin for Claude Code from Eivor79/ai-debate-plugin. Its manifest loads nothing; the 1 skill, 4 commands it bundles cost 230 tokens per session together, scanned A, original, MIT.

An automated review process in which Claude and Codex discuss a topic through repeated design, criticism, and rebuttal rounds, then write their decision to a file.

In plain words
What is it for?
Use it to review designs or other topics in Git or non-Git projects. It can handle multiple topics in a priority queue, while code changes still require human approval.
Why use it?
It gives you a structured comparison of different views without requiring you to manage every discussion round.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add Eivor79/ai-debate-plugin
agentmods
npx agentmods add plugins/eivor79/ai-debate-plugin/ai-debate
Clone the repo
git clone --depth 1 https://github.com/Eivor79/ai-debate-plugin

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-debate

README.md
[![agentmods](https://agentmods.dev/badge/plugins/eivor79/ai-debate-plugin/ai-debate.svg)](https://agentmods.dev/plugins/eivor79/ai-debate-plugin/ai-debate)
Your own site
<a href="https://agentmods.dev/plugins/eivor79/ai-debate-plugin/ai-debate"><img src="https://agentmods.dev/badge/plugins/eivor79/ai-debate-plugin/ai-debate.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 4 commands cost 230 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

ai-debate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

ai-debate/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "ai-debate",
  "displayName": "AI Debate Review",
  "version": "0.5.2",
  "description": "Open a review topic and AI agents (Claude, Codex) debate it round after round -- design, attack, rebuttal -- fully hands-free until they deliver a reasoned decision.md. Multi-topic priority queue with a hardened unattended coordinator; human approval only for code changes. Windows + (beta) macOS/Linux, git and non-git projects, claude-solo fallback when codex is missing.",
  "author": {
    "name": "Eivor79"
  },
  "license": "MIT",
  "homepage": "https://github.com/Eivor79/ai-debate-plugin",
  "repository": "https://github.com/Eivor79/ai-debate-plugin"
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 4 commands travel with it, and installing the plugin installs all of them — 230 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 14 lines scan A 64e6189b22ef

Subscribe to this mod's changes

ai-debate is a plugin published in the GitHub repository Eivor79/ai-debate-plugin (1 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other plugins, from other repositories

adversarial-review

Cross-host adversarial review for coding workflows. Material-only findings include over-engineering and missed reuse. Provider routing uses Codex GPT-5.6 Luna max, OpenCode Go DeepSeek V4 Flash xhigh, direct Moonshot Kimi K3 xhigh, direct-xAI Grok 4.5 high, and Gemini 3.7 Flash High first in the Antigravity ladder.

robertoecf/adversarial-review · not measured

omniforge

AI-powered code review toolkit — review MRs/PRs with 3 parallel adversarial agents, auto-fix review findings, verify applied changes, and create MRs/PRs from commits. Supports both GitLab and GitHub. 19 MCP tools, git worktree isolation, confidence-scored findings.

nexiouscaliver/OmniForge · not measured

river-review

Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development, delivered as a capability pack for Claude Code: your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that runs perspective-based reviewer roles (code, security…

s977043/river-review · not measured

codex-debate

Second opinions: iterative adversarial debates between Claude and Codex over any subject, from specs, designs, and code to non-technical positions, ending in genuine agreement or a documented dispute.

octanevz/codex-debate · not measured

claude-bionify

Bionic reading for Claude's responses that bolds the leading part of each word to guide your eyes and enable you to read faster.

abullard1/claude-bionify · not measured

rails-consultant marketplace

Plugin marketplace listing 1 plugin: rails-consultant.

thoughtbot/rails-consultant · not measured