Borrowing it
Nothing to install: this file belongs to noelroehrig/onenote-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/noelroehrig/onenote-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/noelroehrig/onenote-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/noelroehrig/onenote-mcp/claude-md)<a href="https://agentmods.dev/instructions/noelroehrig/onenote-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/noelroehrig/onenote-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/noelroehrig/onenote-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/noelroehrig/onenote-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 | $0.00450 | $0.00450 |
| Opus 5.5 | $0.00180 | $0.00180 |
| Sonnet 5.5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
onenote-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 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.
What it actually says
CLAUDE.md
Running commands
This repo uses a local .venv. Always call the venv's Python via its
absolute path (resolve it from the repo root) — bare python, bare
pytest, and relative forms like .venv\Scripts\python.exe or
.\.venv\Scripts\python.exe fail in this environment:
<repo-root>\.venv\Scripts\python.exe
Common commands
| Task | Command (prefix with the absolute venv python) |
|---|---|
| Unit tests | -m pytest tests/unit/ -q |
| E2E tests | -m pytest -m e2e tests/e2e/ -v |
| Collect tests | -m pytest tests --collect-only |
| Run a script | scripts/<script>.py |
| Run the server | -m onenote_mcp.server |
Architecture
src/onenote_mcp/
server.py MCP tool definitions (FastMCP, stdio transport)
com.py COM wrapper: worker threads, timeouts, image-handle cache,
notebook allowlist
builders.py model <-> OneNote XML conversion
models.py Pydantic models = the JSON schema of the structured tools
images.py pixel size from image header bytes (proportional image scaling)
Layering: server.py → com.py → builders.py/models.py, and com.py →
images.py. COM calls run on
fresh daemon threads with hard timeouts (_run_com); functions named _*_impl
run on the worker thread and must not call CoInitialize themselves.
Tests
- Unit tests need no OneNote and must stay that way (fake
appobjects stand in for COM where needed). - E2E tests drive the real MCP server against the real OneNote desktop app and create pages. Open the ClaudeSpike notebook in OneNote first; the suite skips automatically when OneNote is unreachable.
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 Changed · +2 lines · +27 tokens per session f6750d5490a4
- 2mo ago First seen · 46 lines · 423 tokens per session scan A d7aeab0e6506
onenote-mcp CLAUDE.md is an instructions file published in the GitHub repository noelroehrig/onenote-mcp (2 stars, last pushed 29d ago), licensed MIT. It adds 450 tokens to every session, about $0.0018 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.
onenote-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| onenote-mcp CLAUDE.mdnoelroehrig/onenote-mcp | Instructions file | 2 | 29d ago | MIT | A | 450 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | 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 | 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 |