Borrowing it
Nothing to install: this file belongs to gabrielassisxyz/docs-to-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/gabrielassisxyz/docs-to-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/gabrielassisxyz/docs-to-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/gabrielassisxyz/docs-to-mcp/agents-md)<a href="https://agentmods.dev/instructions/gabrielassisxyz/docs-to-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrielassisxyz/docs-to-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00776 | $0.00776 |
| Opus 5 | $0.00388 | $0.00388 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
docs-to-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 7d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — read this first
docs-to-mcp turns a documentation site into a searchable local MCP server: Firecrawl captures the pages, an ingester normalizes them into a Markdown corpus with frontmatter, an SQLite FTS5 index makes them searchable, and a FastMCP stdio server exposes search_docs / get_doc / list_docs / refresh_docs to a coding agent. The point is that the agent answers from the real docs of the version in use, not from whatever version it memorized in training. README.md is the user-facing reference — commands, discovery rules, ranking rationale, known limitations; this file is only what an agent needs to work on the repo.
Build / run / test
Python 3.11+, managed with uv. There is no build step beyond dependency sync.
uv sync # install deps (incl. dev group: pytest)
uv run pytest # full test suite — offline, fast, no Firecrawl needed
uv run docs-to-mcp --help # CLI: crawl | categories | reindex | serve
bin/ci # the exact pre-PR gate: gitleaks + shellcheck + pytest
- Tests are hermetic: they exercise ingestion, indexing, sitemap parsing, the pipeline, and a server smoke test against fixtures. A test that needs a live Firecrawl or network access does not belong in the suite.
- Only
crawl,categories, andrefresh_docsneed a Firecrawl API (FIRECRAWL_API_URL, optionallyFIRECRAWL_API_KEY);serve,reindex, and search work entirely offline againstdata/docs/<slug>/. data/is git-ignored regenerable output, never source. Do not commit captured corpora.
Conventions
- Default branch:
master. Never commit to it directly — branch, then PR. - Work in your own worktree, never in the main tree. Before your first write, run
bin/worktree new <type>/<kebab-desc>and do everything in the directory it prints. It branches off a freshorigin/masterand keeps the worktree outside the repo. The main tree stays onmasteras a clean reference. Remove the worktree withbin/worktree rm <task>once the branch is merged. - After clone, run
bin/install-hooksonce. It points git at.githooks/: a gitleaks pre-commit secret scan and a commit-msg gate that rejects assistant attribution. - Commits follow Conventional Commits (
<type>(scope): <description>); branches follow<type>/<kebab-description>. One logical change per commit. - No assistant attribution in commits or PRs — no
Co-Authored-By:naming an assistant, no "Generated with", no robot emoji. The commit-msg hook enforces it; do not bypass it. bin/cigreen before opening a PR. It is the whole gate: "green locally" is the same claim as "green in CI".- PR bodies explain what + why: a short summary of the change, then the decisions and trade-offs behind it. The diff already shows the what.
- Comments explain intent (why), not mechanics (what). Keep existing comments — they carry the reasoning behind non-obvious choices (chrome stripping, lead-only indexing, sitemap-first discovery).
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.
- 7d ago First seen · 35 lines · 776 tokens per session scan A 45517515c597
docs-to-mcp AGENTS.md is an instructions file published in the GitHub repository gabrielassisxyz/docs-to-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 776 tokens to every session, about $0.0039 per session on Opus 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.