Borrowing it
Nothing to install: this file belongs to sphinx-contrib/mcp. 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/sphinx-contrib/mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/sphinx-contrib/mcpWrote 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/sphinx-contrib/mcp/agents-md)<a href="https://agentmods.dev/instructions/sphinx-contrib/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sphinx-contrib/mcp/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/sphinx-contrib/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sphinx-contrib/mcp/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 | $0.00752 | $0.00752 |
| Opus 5.5 | $0.00301 | $0.00301 |
| Sonnet 5.5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
mcp 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository.
Project overview
sphinx-mcp is a Sphinx extension (src/sphinx_mcp/) that documents MCP
(Model Context Protocol) servers — their tools, prompts, resources and
resource templates — by connecting to a configured server via fastmcp and
rendering its metadata as RST/docutils sections at build time.
src/sphinx_mcp/common.py— Sphinx event handlers and MCP client setup.src/sphinx_mcp/mcpdocs.py— theMCPDocsDomainthat renders collected tools/prompts/resources/resource templates into documentation sections.src/sphinx_mcp/utils.py— shared helpers.docs/— the extension's own Sphinx documentation (built with itself, against example MCP servers underdocs/conf.py'smcp_config).tests/— pytest suite;tests/test_mcpdocs.pybuilds Sphinx docs against a local fixture MCP server (tests/servers/fixture_server.py) and asserts on the generated docutils tree.
Tooling
This project uses uv for dependency and
environment management, and just as the
task runner. Run just --list to see all recipes. Common ones:
just install-all # install all dependency groups (dev, docs, test)
just format # format code (ruff format, via pre-commit)
just lint # run all pre-commit hooks against all files
just test # run the pytest suite
just docs-html # build the HTML docs
just docs-pdf # build the PDF docs and copy to the project root
Prefer just recipes over ad hoc uv run ... invocations so behaviour stays
consistent with CI and CONTRIBUTING.md.
Code style
- Formatting and linting are enforced by
ruff(via theruff-pre-commithook pinned in.pre-commit-config.yaml) — runjust format/just lintrather than hand-formatting. - Follow the "no unnecessary comments" / "no speculative abstraction"
conventions already used throughout
src/sphinx_mcp/: prefer clear naming over comments, and only comment on non-obvious why, not what. - Python 3.12+ only (see
requires-pythoninpyproject.toml).
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 · 67 lines · 752 tokens per session scan A 9f2444ae3802
mcp AGENTS.md is an instructions file published in the GitHub repository sphinx-contrib/mcp (8 stars, last pushed 9d ago), licensed BSD-3-Clause. It adds 752 tokens to every session, about $0.0030 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 2026-09-18.
mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp AGENTS.mdsphinx-contrib/mcp | Instructions file | 8 | 9d ago | BSD-3-Clause | A | 752 | 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 | yesterday | 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 | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |