debate-claude

debate-claude is a skill for Codex from Magnus-Gille/claude-skills. It costs 36 tokens per session (677 once invoked), scanned A, original, MIT.

A structured debate with Claude, another AI model, to challenge a draft, plan, research claim, design decision, or security assessment.

In plain words
What is it for?
Use it for adversarial review of consequential technical or research work, while recording the critique, response, rebuttal, and final summary.
Why use it?
It exposes weak assumptions and missed risks before an important decision or document is finalised.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it for adversarial review of consequential technical or research work, while recording the critique, response, rebuttal, and final summary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/magnus-gille/claude-skills/debate-claude
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 Magnus-Gille/claude-skills --skill debate-claude
Clone the repo
git clone --depth 1 https://github.com/Magnus-Gille/claude-skills

Made for: Codex.

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 debate-claude

README.md
[![agentmods](https://agentmods.dev/badge/skills/magnus-gille/claude-skills/debate-claude/github.svg)](https://agentmods.dev/skills/magnus-gille/claude-skills/debate-claude)
Your own site
<a href="https://agentmods.dev/skills/magnus-gille/claude-skills/debate-claude"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/debate-claude/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 debate-claude

Your own site · 80×15
<a href="https://agentmods.dev/skills/magnus-gille/claude-skills/debate-claude"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/debate-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 677 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 $0.00036 $0.00677
Opus 5 $0.00018 $0.00338
Sonnet 5 $0.00007 $0.00135
Haiku 4.5 $0.00004 $0.00068

Measured 6d ago against content hash cffea881bb17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

debate-claude 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 6d 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.

debate-claude/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debate with Claude

This is a Codex-conductor workflow: Codex writes the draft and self-review, invokes Claude as the independent reviewer, and writes the response, summary, and index. Do not have Claude invoke this skill or present a Claude-run self-review as independent cross-model review. Other harnesses may read these references for context, but should route execution back to the Codex conductor.

Use this skill when a consequential architecture, protocol, security assessment, research claim, product priority, or similarly substantive decision benefits from an independent adversarial review. Do not invoke it for typos, formatting, routine implementation details, or mechanical refactors.

Codex owns the artifact, context, model choice, and final decision. This skill does not authorize publication, deployment, credential access, or external messages.

Read only the references needed for the current stage:

  • Protocol — the two-round lifecycle, frozen inputs, draft, self-review, response, and rebuttal.
  • Reviewer safety — the isolated CLI invocation, model selection, prompt envelope, and output metadata.
  • Type lenses — universal and topic-specific self-review and critique questions.
  • Artifacts and records — scratch/trackable files, critique-log schema, sanitization, summary, index, and completeness checks.

Non-negotiable boundaries

  • Freeze a scoped, sanitized input package before each round. Feed that package through stdin; do not give the reviewer live repository, Munin, filesystem, browser, hook, plugin, or MCP access by default.
  • If extra project context is warranted, the conductor selects, sanitizes, and freezes it explicitly in the round package. Round 2 gets a refreshed frozen package that includes the conductor's response and any explicitly selected new context.
  • Use the exact model the user specifies. Do not add an automatic fallback or substitute another model. If no model is specified, choose a suitable configured model and record both the requested and actual model from invocation metadata.
  • Verify current CLI flags with claude --help before changing the invocation. The safe baseline is print mode, plan permissions, no session persistence, safe mode, restricted mode, an empty tool list, and an empty strict MCP configuration. Use only flags confirmed by local help.
  • Record the actual model from structured CLI metadata when available; never treat a model name written in the reviewer's prose as verification.
  • Capture stdout yourself and write the debate artifacts. Do not ask Claude to write files or invoke tools.

Read the full file on GitHub · 35 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago Changed · -365 lines · -22 tokens per session cffea881bb17
  2. 12d ago First seen · 400 lines · 58 tokens per session scan A 17776f8aefc3

Subscribe to this mod's changes

debate-claude is a skill published in the GitHub repository Magnus-Gille/claude-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 677 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens