ai-debate

ai-debate is a skill for Claude Code, Codex from Eivor79/ai-debate-plugin. It costs 132 tokens per session (2,124 once invoked), scanned A, original, MIT.

A file-based workflow where Claude and Codex debate a topic through design, attack, rebuttal, and decision stages.

In plain words
What is it for?
Use it to review designs, decisions, or other topics that need adversarial testing and a reasoned verdict.
Why use it?
It gives a structured way to challenge assumptions and compare opposing arguments before settling on a conclusion.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also runs codex exec. Also seen: mentions Codex.

Part of the ai-debate plugin — 1 skill, 4 commands shipped together

Good fit Use it to review designs, decisions, or other topics that need adversarial testing and a reasoned verdict.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eivor79/ai-debate-plugin/ai-debate
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.

Any agent
npx skills add Eivor79/ai-debate-plugin --skill ai-debate
Clone the repo
git clone --depth 1 https://github.com/Eivor79/ai-debate-plugin

Made for: Claude Code, Codex.

Or install ai-debate, the plugin that ships this one along with the rest of its 1 skill, 4 commands.

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/skills/eivor79/ai-debate-plugin/ai-debate/github.svg)](https://agentmods.dev/skills/eivor79/ai-debate-plugin/ai-debate)
Your own site
<a href="https://agentmods.dev/skills/eivor79/ai-debate-plugin/ai-debate"><img src="https://agentmods.dev/badge/skills/eivor79/ai-debate-plugin/ai-debate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-debate

Your own site · 80×15
<a href="https://agentmods.dev/skills/eivor79/ai-debate-plugin/ai-debate"><img src="https://agentmods.dev/badge/skills/eivor79/ai-debate-plugin/ai-debate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00132 $0.02124
Opus 5 $0.00066 $0.01062
Sonnet 5 $0.00026 $0.00425
Haiku 4.5 $0.00013 $0.00212

Measured 9d ago against content hash db69c33037b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

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 9d 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/skills/ai-debate/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Debate Review workflow

The review workspace is a file-based, multi-agent debate space: agents (Claude, Codex) exchange design → attack → rebuttal → decision documents about one topic, adversarially verifying each other's claims, and converge on a decision delivered to the user. It is NOT a finished-docs store; confirmed knowledge graduates to the wiki, in-flight argument stays in the workspace. Default workspace folder: llm_wiki/ai_debate/ (configurable; the coordinator is folder-name-agnostic).

Default happy path — one command, hands-free to the verdict

When the user names something to debate/review ("X를 토론해봐", "debate whether we should X", "리뷰 붙여줘"), the ENTIRE flow is one command — /review-new <topic> — which:

  1. scaffolds the workspace if missing (no separate init step),
  2. creates the topic in one shot — slug derived from the user's phrase, topic.md written from conversation context (do not interrogate the user; one clarifying question max), auto=true,
  3. starts the coordinator in the background (run_auto.ps1 -Watch; the single-instance mutex makes a duplicate start harmless), so the agents cycle design → attack → rebuttal → decision by themselves,
  4. waits in the background (wait_for_review.ps1 <topic> -UntilStatusLike decided*, run_in_background) and, on completion, reports the decision.md verdict: adopted findings, ruling, residual risks, next step.

Do NOT hand-write rounds yourself, do NOT poll. Multiple topics? Run /review-new for each; the queue drains by priority. A round cap (default 5 numbered docs, per-topic max_rounds) forces a JUDGE verdict if the debate ping-pongs, so autonomous runs always terminate.

Round count control — "이 주제 5라운드로" applies immediately

1 round = 1 numbered doc (design = round 1, attack = round 2, rebuttal = round 3, …). "5 rounds" means 5 numbered docs, then a forced JUDGE writes decision.md.

  • At creation — user says "5라운드로 토론해줘" / "debate this in 5 rounds": pass --rounds 5 to /review-new (sets max_rounds: 5 in the topic's status.json).
  • Existing / already-running topic — user says "해당 주제 5라운드로 해줘" / "make that topic 5 rounds": update the topic's status.json immediately via the workspace script: update_status.ps1 -TopicDir <topic-path> -Set @{ max_rounds = 5 } -Force This takes effect on the coordinator's very next poll — no restart needed (the cap is re-read from status.json every turn). Confirm to the user: current numbered-doc count vs the new cap (if the topic already has ≥ N docs, the next turn becomes the JUDGE round).
  • max_rounds: 0 (or absent) = coordinator default (-MaxNumberedDocs, 5).

Read the full file on GitHub · 106 lines

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. 9d ago First seen · 106 lines · 132 tokens per session scan A db69c33037b9

Subscribe to this mod's changes

ai-debate is a skill published in the GitHub repository Eivor79/ai-debate-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 132 tokens to every session and 2,124 once invoked, about $0.0007 per session on Opus 5. 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 skills, from other repositories