Borrowing it
Nothing to install: this file belongs to rogerawong/cudaq-docs-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/rogerawong/cudaq-docs-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/rogerawong/cudaq-docs-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/rogerawong/cudaq-docs-mcp/claude-md)<a href="https://agentmods.dev/instructions/rogerawong/cudaq-docs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rogerawong/cudaq-docs-mcp/claude-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/rogerawong/cudaq-docs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rogerawong/cudaq-docs-mcp/claude-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 | $0.00507 | $0.00507 |
| Opus 5 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
cudaq-docs-mcp CLAUDE.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 8d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cudaq-docs-mcp
MCP server serving NVIDIA CUDA-Q docs to agents, version-pinned to the installed cudaq package.
Commands
.venv/bin/pytest # unit tests, offline
.venv/bin/cudaq-docs-mcp build --limit 25 # smoke index build (network)
.venv/bin/cudaq-docs-mcp build --version latest # full index build
.venv/bin/cudaq-docs-mcp info # cache dir, indexed versions
.venv/bin/python scripts/smoke_mcp.py # end-to-end MCP stdio session
Commands assume the repo venv at .venv. Where the package is installed into a different environment (a codespace, for example), drop the prefix and call cudaq-docs-mcp, pytest, and python from that environment directly.
Architecture
Pipeline: inventory.py parses CUDA-Q's Sphinx objects.inv (crawl manifest + API symbols) → ingest.py fetches the site's .md mirrors and repo example files → clean.py strips RTD theme chrome from the pandoc-converted mirrors, rebuilds fenced code blocks, extracts heading anchors, chunks by heading → db.py stores pages/chunks/api/examples in one SQLite file per docs version with FTS5 (porter, bm25). server.py exposes five tools + two resources on MCP SDK v2's MCPServer; detect.py resolves the default docs version from installed cudaq distribution metadata; targets.py + data/targets.json is the hand-curated backend matrix; assets.py downloads prebuilt indexes from GitHub release assets; cli.py wires serve/build/info.
Constraints
- Runtime deps are exactly
mcpandhttpx; everything else is stdlib. Do not add deps casually. - Tests must stay offline; network behavior is exercised through the manual commands above.
- Version resolution order (explicit arg → installed cudaq → latest) is the product thesis; do not change it silently.
data/targets.jsonis curated from the docs by hand; when editing, verify names against the backends pages and updatedocs_reviewed.- Repo prose (README, CONTRIBUTING) follows the maintainer's style: no em dashes, "via" is banned, Oxford comma, AP-style numbers.
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.
- 8d ago First seen · 28 lines · 507 tokens per session scan A cbdde2e84742
cudaq-docs-mcp CLAUDE.md is an instructions file published in the GitHub repository rogerawong/cudaq-docs-mcp (1 stars, last pushed 14d ago), licensed Apache-2.0. It adds 507 tokens to every session, about $0.0025 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.