What is codex-debate CLAUDE.md?

A set of repository instructions for Claude Code and other coding agents. It describes how this plugin marketplace is organised and how to edit, test, format, and release its plugins.

Use it when working in the repository, especially when editing a skill, running its compliance tests, formatting files, or preparing a release.

It gives agents a consistent workflow for changing skills and checking their work before a commit.

How octanevz/codex-debate configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to octanevz/codex-debate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/octanevz/codex-debate/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/octanevz/codex-debate

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/octanevz/codex-debate/claude-md/github.svg)](https://agentmods.dev/instructions/octanevz/codex-debate/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/octanevz/codex-debate/claude-md"><img src="https://agentmods.dev/badge/instructions/octanevz/codex-debate/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/octanevz/codex-debate/claude-md"><img src="https://agentmods.dev/badge/instructions/octanevz/codex-debate/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 943 This file is loaded in full into every session.

When invoked 943 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00943	$0.00943
Opus 5.5	$0.00377	$0.00377
Sonnet 5.5	$0.00189	$0.00189
Haiku 4.5	$0.00094	$0.00094

Measured 2mo ago against content hash a8b53089020f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-debate CLAUDE.md 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 2mo 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.

CLAUDE.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code and other coding agents (see AGENTS.md) when working in this repository, ordered by workflow: edit → test → lint → release.

Layout: the repository root is the marketplace (.claude-plugin/marketplace.json); each installable plugin lives under plugins/<plugin>/ with its own .claude-plugin/plugin.json, skills/<name>/ directories, README.md, LICENSE, and CHANGELOG.md. Tests, baselines, and contributor files stay at the repository root — installations copy only the plugin directory.

Editing and testing skills

When editing a skill that has a compliance suite under tests/<name>/, run the relevant scenarios before committing (each scenario run costs one headless Claude session); CONTRIBUTING.md documents usage. The suites load the skill via a ~/.claude/skills symlink into plugins/<plugin>/skills/<name>/.
Some suites include a live check against a real external CLI (currently tests/codex-debate/live-contract.sh, covering the three fragments it assembles from the skill's references/prompts/: role-and-rules.md, advisory-inline-extras.md, and fenced-subject.md). Run a live check after changing what it covers or upgrading the CLI it calls, not routinely.
After changing a skill's frontmatter description, run the triggering suite (tests/skill-triggering/run.sh; costs API calls, not in CI): compliance suites exercise behavior after invocation, not routing. (Adopt claude plugin eval for this once it leaves early access.)
After changing manifests or the repository layout, run the install smoke test: tests/plugin-install/smoke.sh.
Recorded RED baselines under tests/<name>/baselines/ are historical evidence; do not re-run or overwrite them casually.

Before committing: lint and format

CI (.github/workflows/ci.yml) runs these on every push to main and every PR; run them locally first and fix findings — each must come back clean.

# all from the repository root

# shell scripts: every tracked script and test stub, same command as CI
git ls-files '*.sh' 'tests/*/bin/*' | xargs shellcheck

# report formatting diffs; fix with: shfmt -w <files>
shfmt -d .

# markdown
markdownlint-cli2 "**/*.md"

# manifests
claude plugin validate . --strict
claude plugin validate plugins/codex-debate --strict

Read the full file on GitHub · 48 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.

2mo ago First seen · 48 lines · 943 tokens per session scan A a8b53089020f

Subscribe to this mod's changes

codex-debate CLAUDE.md is an instructions file published in the GitHub repository octanevz/codex-debate (4 stars, last pushed 3mo ago), licensed MIT. It adds 943 tokens to every session, about $0.0038 per session on Opus 5.5. 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.

Building agents adversarial-review ai-debate claude-code-plugin debate devils-advocate llm-council

codex-debate CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-debate CLAUDE.mdoctanevz/codex-debate	Instructions file	4	3mo ago	MIT	A	943	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

codex-debate: Instructions file for Claude Code