Borrowing it
Nothing to install: this file belongs to sham-devs/mcp-md-pdf. 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/sham-devs/mcp-md-pdf/main/CLAUDE.mdgit clone --depth 1 https://github.com/sham-devs/mcp-md-pdfWrote 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/sham-devs/mcp-md-pdf/claude-md)<a href="https://agentmods.dev/instructions/sham-devs/mcp-md-pdf/claude-md"><img src="https://agentmods.dev/badge/instructions/sham-devs/mcp-md-pdf/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/sham-devs/mcp-md-pdf/claude-md"><img src="https://agentmods.dev/badge/instructions/sham-devs/mcp-md-pdf/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 | $0.02011 | $0.02011 |
| Opus 5.5 | $0.00804 | $0.00804 |
| Sonnet 5.5 | $0.00402 | $0.00402 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade B, and why
mcp-md-pdf CLAUDE.md scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Linux**: Requires LibreOffice (`sudo apt-get install libreoffice`) How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MD-PDF-MCP is a Model Context Protocol (MCP) server that converts Markdown files to Word (.docx) and PDF documents with professional styling and optional .dotx template support.
Key Architecture:
- FastMCP Server (
src/md_pdf_mcp/server.py): Exposes 3 MCP tools for AI assistants - Markdown Converter (
src/md_pdf_mcp/converter.py): Core conversion engine using python-docx - XML Styling System: Uses OpenXML (via
OxmlElement) for professional document styling
Development Commands
Installation
# Development install (editable mode)
pip install -e .
# With dev dependencies
pip install -e ".[dev]"
Testing
# Run all tests
pytest
# Run tests excluding slow ones (e.g., PDF conversion)
pytest -m "not slow"
# Run specific test file
pytest tests/test_converter.py
# Run specific test
pytest tests/test_converter.py::TestDocumentContent::test_headings_present
# Run with coverage
pytest --cov=src/md_pdf_mcp --cov-report=html
# Run verbose with short traceback
pytest -v --tb=short
Test Markers:
@pytest.mark.unit- Unit tests@pytest.mark.integration- Integration tests@pytest.mark.slow- Long-running tests (PDF conversion)@pytest.mark.requires_word- Requires Microsoft Word
Code Quality
# Format code
black src/ tests/
# Lint code
ruff check src/ tests/
Running the MCP Server
# Run server directly
python -m md_pdf_mcp.server
# Test with MCP Inspector
npx @modelcontextprotocol/inspector python -m md_pdf_mcp.server
Architecture Details
Two-Layer Conversion System
-
MCP Layer (
server.py):- Exposes tools:
convert_markdown,convert_markdown_batch,list_supported_formats - Handles validation, file I/O, error messaging
- Shared internal function
_convert_markdown_impl()for DRY
- Exposes tools:
-
Converter Layer (
converter.py):markdown_to_word(): Markdown → .docx using python-docxword_to_pdf(): .docx → .pdf (cross-platform: MS Word on Windows, LibreOffice on Linux/macOS)_word_to_pdf_windows(): MS Word COM automation implementation_word_to_pdf_libreoffice(): LibreOffice headless mode implementation- Template support via
_load_template()
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 · 253 lines · 2,011 tokens per session scan B f1caa8747338
mcp-md-pdf CLAUDE.md is an instructions file published in the GitHub repository sham-devs/mcp-md-pdf (1 stars, last pushed 1y ago), licensed MIT. It adds 2,011 tokens to every session, about $0.0080 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
mcp-md-pdf CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-md-pdf CLAUDE.mdsham-devs/mcp-md-pdf | Instructions file | 1 | 1y ago | MIT | B | 2,011 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | yesterday | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |
| generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginners | Instructions file | 124k | today | MIT | A | 2,981 | Codex, OpenCode |