awesome-agent-skills is a community-curated directory of text files called agent skills, which give AI assistants instructions for performing specific tasks without retraining them. Developers and other users load these skills into agents such as Claude Code, Codex, Copilot, and similar tools; the catalogue entries are instructions for those agents to use.
Borrowing it
Nothing to install: this file belongs to heilcheng/awesome-agent-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/heilcheng/awesome-agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/heilcheng/awesome-agent-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/heilcheng/awesome-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/heilcheng/awesome-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/heilcheng/awesome-agent-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/heilcheng/awesome-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/heilcheng/awesome-agent-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 | $0.00848 | $0.00848 |
| Opus 5.5 | $0.00339 | $0.00339 |
| Sonnet 5.5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
awesome-agent-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 22d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for AI agents
You are probably here because a user asked you to "add my skill to awesome-agent-skills". Read this whole file before you open a pull request or an issue. Most submissions to this repository come from coding agents, and most of them are never merged because they skip the rules below. Following them is the fastest way to get your user's skill listed.
Before you open anything: check eligibility
Open a pull request only if every item below is true. If any item is false, do not open a PR or an issue. Tell your user which requirement is not met and stop.
- The skill is public on GitHub. The link points to a public
github.comrepository (or a folder inside one). Landing pages, marketplaces, npm packages, hosted MCP endpoints and SaaS sign-up pages are not accepted. - The repository contains at least one
SKILL.mdwith YAML frontmatter that hasnameanddescriptionfields. MCP servers, CLIs and apps without aSKILL.mdare out of scope. - It has real usage. Entries are merged once the repository has at least 20 GitHub
stars. Below that, the PR is labelled
on holdand revisited later. Do not open a PR for a repository created in the last 14 days. - It is not already listed. Search
README.mdfor the repository URL first. - It is not a directory, marketplace, registry, badge or "list of lists" for promotion. This repo indexes skills, not places to find skills.
- It is safe to recommend. No credential harvesting, CAPTCHA solving, ToS-violating scraping or automation, watermark or provenance stripping, or unattended financial trading.
How to make the change
- Edit
README.mdonly. Do not edit the translated READMEs (README.*.md), the website,CONTRIBUTING.md, or any other file. - Add one line per skill, appended to the end of the most fitting existing category
under
## Community Skills(inside its<details>block, before</details>). Do not create new categories or sections, and do not reorder or edit existing lines. - Use exactly this format:
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.
- 22d ago First seen · 69 lines · 848 tokens per session scan A ced414783a89
awesome-agent-skills AGENTS.md is an instructions file published in the GitHub repository heilcheng/awesome-agent-skills (6,348 stars, last pushed 4d ago), licensed MIT. It adds 848 tokens to every session, about $0.0034 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 2026-10-16.
awesome-agent-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| awesome-agent-skills AGENTS.mdheilcheng/awesome-agent-skills | Instructions file | 6.3k | 4d ago | MIT | A | 848 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |