Borrowing it
Nothing to install: this file belongs to vivekVells/mcp-pandoc. 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/vivekVells/mcp-pandoc/main/CLAUDE.mdgit clone --depth 1 https://github.com/vivekVells/mcp-pandocWrote 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/vivekvells/mcp-pandoc/claude-md)<a href="https://agentmods.dev/instructions/vivekvells/mcp-pandoc/claude-md"><img src="https://agentmods.dev/badge/instructions/vivekvells/mcp-pandoc/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/vivekvells/mcp-pandoc/claude-md"><img src="https://agentmods.dev/badge/instructions/vivekvells/mcp-pandoc/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 | $0.06032 | $0.06032 |
| Opus 5 | $0.03016 | $0.03016 |
| Sonnet 5 | $0.01206 | $0.01206 |
| Haiku 4.5 | $0.00603 | $0.00603 |
Grade B, and why
mcp-pandoc 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 10d 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.
sudo apt-get install pandoc && pip install uv # Ubuntu/Debian How it starts
The opening of the file, as written. The whole thing — 707 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - mcp-pandoc Development Guide
Last Updated: 2025-07-13
Project Overview
mcp-pandoc is a Model Context Protocol (MCP) server that provides document format conversion capabilities using Pandoc. This project enables seamless bidirectional conversion between 10+ document formats including Markdown, HTML, PDF, DOCX, LaTeX, EPUB, and more.
Core Architecture
- MCP Server: Implements JSON-RPC 2.0 protocol for tool-based document conversion
- Primary Tool:
convert-contents- handles all format conversions with comprehensive validation - Backend Engine: Pandoc with pypandoc Python wrapper
- Special Features: Reference document styling for DOCX, ODT and PPTX, advanced format support
🎯 Project Philosophy & Decision Framework
Core Principle: "Pandoc, Perfected for MCP"
mcp-pandoc follows the "iPhone approach" - do fewer things, but do them perfectly. We are the definitive Pandoc MCP server for document format conversion, not a universal document processor.
Decision Framework for New Features
When evaluating any new feature request, assess against these criteria:
✅ Green Light Criteria:
- Native Pandoc capability that we're not fully leveraging
- High user value with low to medium implementation complexity
- Improves reliability or performance of existing features
- Enhances the core document conversion workflow
⚠️ Yellow Light Criteria (Requires Strong Justification):
- Adds new dependencies but provides significant user value
- Complex implementation but addresses critical user need
- Extension of Pandoc capabilities through well-established patterns
❌ Red Light Criteria (Default: No):
- Requires external tools not related to Pandoc
- Significant maintenance burden for niche use cases
- Better served by specialized servers in the MCP ecosystem
- Scope creep beyond document format conversion
Maintenance Philosophy
- Focused Excellence > Feature Breadth
- Reliability > Cutting-Edge Features
- Pandoc-Native > External Integrations
- Sustainable Development > Complex Dependencies
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.
- 10d ago First seen · 707 lines · 6,032 tokens per session scan B 736f6c5b0d9e
mcp-pandoc CLAUDE.md is an instructions file published in the GitHub repository vivekVells/mcp-pandoc (579 stars, last pushed 25d ago), licensed MIT. It adds 6,032 tokens to every session, about $0.0302 per session on Opus 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 2026-08-30.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.