Borrowing it
Nothing to install: this file belongs to dirtybits/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/dirtybits/agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/dirtybits/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/dirtybits/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/dirtybits/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dirtybits/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/dirtybits/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dirtybits/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 | $0.00293 | $0.00293 |
| Opus 5.5 | $0.00117 | $0.00117 |
| Sonnet 5.5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
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 2mo 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.
What it actually says
Agent Instructions
Finding and installing skills
When a task would benefit from a capability that is not already available in this repository or the active agent environment, use the Vercel Agent Skills directory and its CLI to find an appropriate skill:
npx skills find <query>
Install a skill from a repository with:
npx skills add <owner/repo>
For a repository that contains more than one skill, install only the required one:
npx skills add <owner/repo> --skill <skill-name>
Before installing, inspect the skill's source and confirm that it is appropriate for the task. Use the CLI's destination and agent prompts to install it for the active coding agent; do not treat an installed third-party skill as authored content in this repository.
Repository contributions
- Keep authored or intentionally mirrored skills in
skills/<skill-name>/and follow the rules inREADME.mdandCONTRIBUTING.md. - Preserve upstream attribution and licenses for any skill brought into the repository.
- Do not add a discovered third-party skill to
registry.jsonor publish it through AgentVouch unless its provenance, license, and publishing decision have been reviewed. - Run
npm run kb:formatafter metadata or index changes andnpm run validatebefore proposing a change.
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.
- 2mo ago First seen · 31 lines · 293 tokens per session scan A 41db36d4b9e4
agent-skills AGENTS.md is an instructions file published in the GitHub repository dirtybits/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 293 tokens to every session, about $0.0012 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.
agent-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-skills AGENTS.mddirtybits/agent-skills | Instructions file | 2 | 1mo ago | MIT | A | 293 | 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 |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |