A command for asking OpenAI Codex, another AI coding agent, to brainstorm, delegate work, answer a question, or give a second opinion. It runs Codex in a chosen project directory and returns its response.

Use it for design discussions, code-related questions, delegated implementation work, and independent reviews of an approach.

It gives you another AI perspective on a coding problem or lets Codex handle a delegated task.

codex — Skill for Claude Code by cukas

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add cukas/claudes-ai-buddies

Claude Code

/plugin install claudes-ai-buddies

Made for: Claude Code.

Or install claudes-ai-buddies, the plugin that ships this one along with the rest of its 12 skills, 1 command, 1 hook.

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/skills/cukas/claudes-ai-buddies/codex.svg)](https://agentmods.dev/skills/cukas/claudes-ai-buddies/codex)

Your own site

<a href="https://agentmods.dev/skills/cukas/claudes-ai-buddies/codex"><img src="https://agentmods.dev/badge/skills/cukas/claudes-ai-buddies/codex.svg" alt="Measured on agentmods" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 716 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.00716
Opus 5	$0.00010	$0.00358
Sonnet 5	$0.00004	$0.00143
Haiku 4.5	$0.00002	$0.00072

Measured 8d ago against content hash 080f0114ffd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

codex 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 8d 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.

skills/codex/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/codex — Peer AI via OpenAI Codex

You have access to OpenAI's Codex CLI as a peer AI. Use it to brainstorm, delegate tasks, get second opinions, or ask questions from a different AI perspective.

How to invoke

Run the wrapper script via Bash. IMPORTANT: Codex regularly takes 3-6 minutes for non-trivial tasks. You MUST set the Bash tool's timeout parameter to 420000 (7 minutes) to prevent Claude Code from killing the process before Codex finishes.

bash "${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.sh" \
  --prompt "YOUR PROMPT HERE" \
  --cwd "/path/to/relevant/directory" \
  --mode exec

Then read the output file path it prints and present the results to the user.

Step-by-step workflow

Parse the user's request. The user says /codex "some prompt" or /codex followed by a question.
Determine the working directory. Default to the current project root. If the user references a specific repo or directory, use that.
Run codex-run.sh with --mode exec and the user's prompt via the Bash tool.
Read the output file using the Read tool. The script prints the output file path to stdout.
Show Codex's raw response directly. Use this format — show their actual words, don't paraphrase or summarize:

🔵 **Codex:**
> [their full response here, verbatim, as a blockquote]

Add your own take only if asked. If the user wants a comparison or synthesis, add it after Codex's response. Otherwise, let Codex's voice stand on its own.

Options

Flag	Default	Description
`--prompt`	(required)	The question or task for Codex
`--cwd`	current dir	Working directory for Codex
`--mode`	`exec`	Always `exec` for this skill
`--timeout`	from config (360s)	Max seconds to wait
`--model`	from config	Override the Codex model
`--sandbox`	`full-auto`	Sandbox mode: `full-auto` or `suggest`

Example invocations

/codex "What's the best way to implement a rate limiter in Go?"
/codex "Review this architecture: we have a React frontend calling a FastAPI backend with Redis caching"
/codex "Write a bash script that finds duplicate files by hash"
/codex "Debug this error: TypeError: Cannot read property 'map' of undefined"

Read the full file on GitHub · 63 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.

8d ago First seen · 63 lines · 19 tokens per session scan A 080f0114ffd5

Subscribe to this mod's changes

codex is a skill published in the GitHub repository cukas/claudes-ai-buddies (9 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 716 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 2026-08-31.

Building agents Claude Code brainstorming claude-code-plugin codex openai

optimize-claude-opus-5-prompts

Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus 5 prompt…

IchenDEV/prompt-optimizer-plugins · 182 tokens

optimize-claude-fable-5-prompts

A prompt-editing method for Claude Fable 5, an AI model. It turns rough or existing instructions into clearer prompts while keeping the original goal and important limits.

IchenDEV/prompt-optimizer-plugins · 137 tokens

optimize-gpt-5-6-prompts

A guide for improving prompts written for OpenAI’s GPT-5.6 models, including GPT-5.6 Sol.

IchenDEV/prompt-optimizer-plugins · 135 tokens

optimize-gpt-6-astra-prompts

Clarify, audit, migrate, and rewrite prompts for GPT-6 Astra using OpenAI's official latest-model prompting guidance. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a GPT-6 Astra prompt, including requests phrased as GPT-6, Astra, or gpt-6-astra prompt optimization, or when an…

IchenDEV/prompt-optimizer-plugins · 134 tokens

optimize-deepseek-v4-prompts

Clarify, audit, and rewrite rough or existing prompts specifically for DeepSeek-V4 Pro and Flash using the DeepSeek-AI V4 technical report as the model-specific evidence base. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a DeepSeek-V4 prompt, including requests phrased as DeepSeek…

IchenDEV/prompt-optimizer-plugins · 151 tokens

optimize-gemini-prompts

A prompt-editing skill for clarifying and rewriting prompts intended for Google’s Gemini models.

IchenDEV/prompt-optimizer-plugins · 126 tokens