Borrowing it
Nothing to install: this file belongs to CCDawn/codex-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CCDawn/codex-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/CCDawn/codex-skillsWrote 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.
[](https://agentmods.dev/instructions/ccdawn/codex-skills/agents-md)<a href="https://agentmods.dev/instructions/ccdawn/codex-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ccdawn/codex-skills/agents-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.
<a href="https://agentmods.dev/instructions/ccdawn/codex-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ccdawn/codex-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00627 | $0.00627 |
| Opus 5.5 | $0.00251 | $0.00251 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
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 1mo 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.
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
namefield inSKILL.md. - When the catalog changes, update
README.md,README.zh-CN.md, the bucketREADME.md, and.claude-plugin/plugin.jsonin 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/skillsand.agents/skillsunless 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.yamlaligned with the working pattern already used in this repo: a minimalinterface:block with a distinctivedisplay_name,short_description, anddefault_prompt. - If this repository is the active trusted workspace, its
.claude-plugin/plugin.jsoncan also influence visible skill entries. When debugging duplicates, check both installed global copies and the repo-local manifest.
Duplicate or missing slash-command checklist
- Check the live installed copy in
~/.codex/skills/<briefbound-skill-name>. - Check whether an extra
~/.agents/skills/<briefbound-skill-name>copy exists. - Check
agents/openai.yamlfor the live copy, not only the repo copy. - Check whether the current workspace is this repo and whether
.claude-plugin/plugin.jsonalso exposes the same skill. - Restart Codex before concluding that a metadata change failed.
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.
- 1mo ago First seen · 39 lines · 627 tokens per session scan A d44f2cecb600
codex-skills AGENTS.md is an instructions file published in the GitHub repository CCDawn/codex-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 627 tokens to every session, about $0.0025 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).