hf-discover is a client and server for finding agent resources in registries that follow the Agent Resource Discovery standard. Agents and their users use it to search catalogs, navigate federated registries, and discover skills, MCP servers, and Hugging Face Spaces.
Borrowing it
Nothing to install: this file belongs to huggingface/hf-discover. 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/huggingface/hf-discover/main/AGENTS.mdgit clone --depth 1 https://github.com/huggingface/hf-discoverWrote 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/huggingface/hf-discover/agents-md)<a href="https://agentmods.dev/instructions/huggingface/hf-discover/agents-md"><img src="https://agentmods.dev/badge/instructions/huggingface/hf-discover/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/huggingface/hf-discover/agents-md"><img src="https://agentmods.dev/badge/instructions/huggingface/hf-discover/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 | $0.00254 | $0.00254 |
| Opus 5.5 | $0.00102 | $0.00102 |
| Sonnet 5.5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
hf-discover 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
- ARD specification is in spec/ard.md
- Keep a high level log of Features and Capabilities in README.md under ##features.
- Project documentation is a lightweight orientation record, not the full source of truth. It should help humans quickly understand the big idea and help future agents know which scripts, workflows, specs, and plans to inspect for detailed question-answering. Prefer concise summaries with explicit artifact pointers over duplicating shell/script logic.
- Do NOT test things that the
tytypechecker automatically enforces. - Any HF_TOKEN usage must only remain temporarily in memory during a request scope, and must never be stored or emitted in a plain format.
- Avoid mocking or
monkeypatchfor testing purposes, preferring to use typechecks, simple logic-focussed unit tests and stubs/simulators. Small integration or e2e tests are preferred over lots of unit tests for tightly coupled scenarios. - Avoid testing properties and other data transfer scenarios unless transformations or other behaviour is involved.
- Prefer a functional style of programming where possible.
- Feature additions should consider the CLI surface as well as adherence to the ARD specification. Both CLI and HTTP should wrap the same, clean, well factored core logic.
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 · 13 lines · 254 tokens per session scan A 9d9933d8fe90
hf-discover AGENTS.md is an instructions file published in the GitHub repository huggingface/hf-discover (49 stars, last pushed 11d ago), licensed MIT. It adds 254 tokens to every session, about $0.0010 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 2026-08-30.
hf-discover AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hf-discover AGENTS.mdhuggingface/hf-discover | Instructions file | 49 | 11d ago | MIT | A | 254 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | 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 | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |