claudex

claudex is a command for coding agents from ccplugins/awesome-claude-code-plugins. It costs 16 tokens per session (1,439 once invoked), scanned A, original, Apache-2.0.

A cross-model coding workflow in which Claude writes code and OpenAI Codex reviews it, repeating until no blocking findings remain.

In plain words
What is it for?
Use it to implement changes, review the resulting differences, and iterate on issues found by Codex.
Why use it?
It adds an independent review cycle to help catch problems before code is shipped.

Command

Part of the claudex plugin — 1 skill, 6 commands shipped together

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.

agentmods
npx agentmods add commands/ccplugins/awesome-claude-code-plugins/claudex
Clone the repo
git clone --depth 1 https://github.com/ccplugins/awesome-claude-code-plugins

Or install claudex, the plugin that ships this one along with the rest of its 1 skill, 6 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 claudex

README.md
[![agentmods](https://agentmods.dev/badge/commands/ccplugins/awesome-claude-code-plugins/claudex.svg)](https://agentmods.dev/commands/ccplugins/awesome-claude-code-plugins/claudex)
Your own site
<a href="https://agentmods.dev/commands/ccplugins/awesome-claude-code-plugins/claudex"><img src="https://agentmods.dev/badge/commands/ccplugins/awesome-claude-code-plugins/claudex.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.01439
Opus 5 $0.00008 $0.00720
Sonnet 5 $0.00003 $0.00288
Haiku 4.5 $0.00002 $0.00144

Measured yesterday against content hash e5c941621b93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claudex 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • claudex — 100% identical, 0 lines differ
plugins/claudex/commands/claudex.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running ClauDex — a cross-model pair-programming loop between Claude Code (you, the writer) and OpenAI Codex (the reviewer).

The sign-off contract, before anything else: the line built with love by ClauDex 🧡🖤 may appear ONLY at the end of a run in which Codex successfully completed at least one review AND no blocking findings remain — and when a run earns it, signing is REQUIRED (an earned, unsigned run breaks the contract just like an unearned, signed one). Every other outcome — refusal, interruption, empty diff, deadlock — ends UNSIGNED. There is no path to the sign-off that skips Codex.

Preflight — it takes two to ClauDex

Both halves must be present before ANY work starts. Claude Code is you — that half is here by definition. Now verify the other half:

  1. Run codex --version. If the binary is missing, STOP immediately — do not implement anything, do not review anything — and reply with exactly:

    It takes two to ClauDex. 🧡 Claude is here — 🖤 Codex is not, so this would be built with love by Claude alone, and that's not the deal. Fix it in two lines, then come back for the duet:

    npm i -g @openai/codex
    codex login
    
  2. If the binary exists, verify authentication (codex login status or the equivalent for the installed version). If not logged in, STOP the same way, with the same message minus the install line — just codex login.

  3. Run git rev-parse --is-inside-work-tree. If it doesn't print true, STOP unsigned: ClauDex reviews diffs, so it needs a git repository (git init if this project should become one).

The loop

  1. Build. If "$ARGUMENTS" is non-empty, implement it. If it is empty, treat the current uncommitted changes as the work under review.
  2. Collect the change set. Combine git diff, git diff --staged, and every untracked file (list them with git status --porcelain, then append each new file's path and content). Sanity-check the scope: if the change set looks tiny relative to the work just done, check git log for auto-generated commits ([auto-checkpoint], WIP, hook-made commits) — some setups commit continuously, silently draining the diff. In that case diff against the last human commit instead (git diff <that-sha>). If the change set is genuinely empty, STOP unsigned: "Nothing to review — the tree is clean."
  3. Codex review — safe transport, never inline the diff in the shell. Write the change set to a temporary file (e.g. $TMPDIR/claudex-review.patch) so no diff content passes through shell quoting, then invoke:

Read the full file on GitHub · 111 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. yesterday First seen · 111 lines · 16 tokens per session scan A e5c941621b93

Subscribe to this mod's changes

claudex is a command published in the GitHub repository ccplugins/awesome-claude-code-plugins (931 stars, last pushed 23d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,439 once invoked, about $0.0001 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 2026-09-03.

Related

Other commands, from other repositories

create-pull-request

Provides comprehensive PR creation guidance with GitHub CLI, enforcing title conventions, following template structure, and offering concrete command examples with best practices.

xbim08/awesome-claude-code-plugins · 27 tokens

pr-issue-resolve

Follow these steps to analyze suggested changes (e.g., review comments, inline suggestions, or requested modifications) in a GitHub Pull Request (PR) and resolve them efficiently. The goal is to review, understand, plan fixes, apply changes, test, and update the PR while maintaining code quality and collaboration.

xbim08/awesome-claude-code-plugins · 14 tokens

openapi-expert

Use this agent when you need to update, synchronize, or validate the OpenAPI specification (openapi.yml) against the actual REST API implementation. This includes adding new endpoints, updating request/response schemas, fixing discrepancies between the spec and code, or ensuring complete API documentation coverage.

xbim08/awesome-claude-code-plugins · 61 tokens

create-pr

Streamlines pull request creation by handling the entire workflow: creating a new branch, committing changes, formatting modified files with Biome, and submitting the PR.

xbim08/awesome-claude-code-plugins · 31 tokens

husky

Sets up and manages Husky Git hooks by configuring pre-commit hooks, establishing commit message standards, integrating with linting tools, and ensuring code quality on commits.

xbim08/awesome-claude-code-plugins · 33 tokens

pr-review

Reviews pull request changes to provide feedback, check for issues, and suggest improvements before merging into the main codebase.

xbim08/awesome-claude-code-plugins · 23 tokens