agentmods.dev

codex-skills AGENTS.md

A set of maintenance instructions for the CCDawn/codex-skills repository, which publishes reusable coding-agent skills and slash commands.

In plain words
What is it for?
Adding or updating skills, checking for duplicate or missing slash commands, updating repository documentation, and verifying installed copies.
Why use it?
It helps keep skill folders, documentation, installation locations, and command entries consistent when the catalogue changes.

Instructions file for CodexOpenCode

4 20d ago A scan 627 tokens original MIT
View the source file CCDawn/codex-skills
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/agents-md
Clone the repo
git clone --depth 1 https://github.com/CCDawn/codex-skills

Made for: Codex, OpenCode.

Per session 627 This file is loaded in full into every session.
When invoked 627 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.

ModelPer sessionOnce invoked
Fable 5 $0.00627 $0.00627
Opus 5 $0.00313 $0.00313
Sonnet 5 $0.00125 $0.00125
Haiku 4.5 $0.00063 $0.00063

Measured 2d ago against content hash d44f2cecb600, 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 AGENTS.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 2d 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.

AGENTS.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

This repository publishes local Codex skills. Treat slash-command behavior as a packaging problem first, not as a prompt-writing problem.

Repo rules

  • One skill lives under skills/<bucket>/<briefbound-skill-name>/.
  • The folder name must match the name field in SKILL.md.
  • When the catalog changes, update README.md, README.zh-CN.md, the bucket README.md, and .claude-plugin/plugin.json in the same change.
  • The default install target is ~/.codex/skills/<briefbound-skill-name>.
  • The native Grok target is ~/.grok/skills/<briefbound-skill-name> with global activation in ~/.grok/AGENTS.md.
  • Use ~/.agents/skills/<briefbound-skill-name> only when you explicitly need an extra local catalog copy.
  • Do not rely on symlinks or junctions as the default install shape.

Slash-command lessons learned

  • Do not install the same skill into both .codex/skills and .agents/skills unless the user explicitly wants both copies. Codex can show duplicate slash-command entries when both are present.
  • After changing a skill, inspect the installed live copy under ~/.codex/skills/<briefbound-skill-name>, not just the repo copy. A repo file and the live loaded file can drift.
  • After changing install metadata or agents/openai.yaml, restart Codex and verify the slash-command entry in a fresh thread.
  • Keep agents/openai.yaml aligned with the working pattern already used in this repo: a minimal interface: block with a distinctive display_name, short_description, and default_prompt.
  • If this repository is the active trusted workspace, its .claude-plugin/plugin.json can also influence visible skill entries. When debugging duplicates, check both installed global copies and the repo-local manifest.

Duplicate or missing slash-command checklist

  1. Check the live installed copy in ~/.codex/skills/<briefbound-skill-name>.
  2. Check whether an extra ~/.agents/skills/<briefbound-skill-name> copy exists.
  3. Check agents/openai.yaml for the live copy, not only the repo copy.
  4. Check whether the current workspace is this repo and whether .claude-plugin/plugin.json also exposes the same skill.
  5. Restart Codex before concluding that a metadata change failed.

Read the full file on GitHub · 39 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. 2d ago First seen · 39 lines · 627 tokens per session scan A d44f2cecb600

Subscribe to this mod's changes

codex-skills AGENTS.md is an instructions file published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 627 tokens to every session, about $0.0031 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.

agent-skillsai-agentsai-codingchinesecodex
Related

Other instructions, from other repositories

superpowers-zh CLAUDE.md

Instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.

jnMetaCode/superpowers-zh · 2,083 tokens

superpowers-zh GEMINI.md

Instructions for jnMetaCode/superpowers-zh, covering superpowers-zh 中文增强版, 核心规则, 可用 skills and 如何使用.

jnMetaCode/superpowers-zh · 1,105 tokens

spec-kit-zh AGENTS.md

Instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.

loulanyue/spec-kit-zh · 3,968 tokens

awesome-cursorrules-zh CLAUDE.md

Claude Code instructions for holtwood/awesome-cursorrules-zh, covering claude.md, 项目概述, 技术栈, 常用命令 and 目录结构.

holtwood/awesome-cursorrules-zh · 848 tokens

awesome-cursorrules-zh AGENTS.md

AGENTS.md instructions for holtwood/awesome-cursorrules-zh, covering agents.md, 项目定位, 权威源, 技术栈 and 常用命令.

holtwood/awesome-cursorrules-zh · 396 tokens

awesome-cursorrules-zh copilot-instructions.md

Copilot instructions for holtwood/awesome-cursorrules-zh, covering github copilot instructions, 项目概述, 技术栈, 代码规范 and 提交格式.

holtwood/awesome-cursorrules-zh · 241 tokens