What is codex-skills CLAUDE.md?

Repository instructions for organizing, publishing, and installing coding-agent skills in a project. A skill is a reusable set of instructions that guides an agent through a type of work.

Use them when adding skills to the repository, updating plugin metadata, installing skills locally, or checking slash-command changes.

They reduce mistakes such as missing documentation, inconsistent folder names, duplicate installations, or validating the wrong installed copy.

codex-skills CLAUDE.md — Instructions file for coding agents by CCDawn: Repository instructions for organizing, publishing, and installing c

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 instructions/ccdawn/codex-skills/claude-md

Clone the repo

git clone --depth 1 https://github.com/CCDawn/codex-skills

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/ccdawn/codex-skills/claude-md.svg)](https://agentmods.dev/instructions/ccdawn/codex-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ccdawn/codex-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ccdawn/codex-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 357 This file is loaded in full into every session.

When invoked 357 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00357	$0.00357
Opus 5	$0.00179	$0.00179
Sonnet 5	$0.00071	$0.00071
Haiku 4.5	$0.00036	$0.00036

Measured 4d ago against content hash 8319a2a881f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-skills 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 4d 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 · 24 lines

What it actually says

Skills are organized into bucket folders under skills/:

engineering/ - code work and implementation workflows
research/ - research planning, evidence synthesis, and paper-readiness workflows

Every skill in engineering/ or research/ must have:

a reference in the top-level README.md
an entry in .claude-plugin/plugin.json

Published skills in this repository must also follow the live-install rules:

the skill folder name must match the name field in SKILL.md
the default local install target is ~/.codex/skills/<briefbound-skill-name>
use ~/.agents/skills/<briefbound-skill-name> only when you explicitly need an extra local catalog copy
installing the same skill into both .codex/skills and .agents/skills can produce duplicate slash-command entries
the default install shape is a real directory, not a symlink or junction
after updating a skill, validate the installed live Codex copy before treating the change as done
after updating install metadata or agents/openai.yaml, inspect the installed live copy and restart Codex before concluding that the slash-command change failed
keep agents/openai.yaml aligned with the minimal working shape already used in this repo: an interface: block with a distinctive display_name, short_description, and default_prompt
if the current trusted workspace is this repository, remember that .claude-plugin/plugin.json can also influence visible skill entries during slash-command debugging

Each bucket folder should have a README.md that lists every skill in the bucket with a one-line description, and each skill name should link to its SKILL.md.

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.

4d ago First seen · 24 lines · 357 tokens per session scan A 8319a2a881f7

Subscribe to this mod's changes

codex-skills CLAUDE.md is an instructions file published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 22d ago), licensed MIT. It adds 357 tokens to every session, about $0.0018 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 agent-skills ai-agents ai-coding chinese codex

codex-skills CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other instructions, from other repositories

superpowers-zh CLAUDE.md

superpowers-zh GEMINI.md

spec-kit-zh AGENTS.md

awesome-cursorrules-zh copilot-instructions.md

spare-me CLAUDE.md

agent-zero-to-one-cn CLAUDE.md