Borrowing it
Nothing to install: this file belongs to leanzero-srl/leanzero-mcp-doc-processor. 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/leanzero-srl/leanzero-mcp-doc-processor/main/CLAUDE.mdgit clone --depth 1 https://github.com/leanzero-srl/leanzero-mcp-doc-processorWrote 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/leanzero-srl/leanzero-mcp-doc-processor/claude-md)<a href="https://agentmods.dev/instructions/leanzero-srl/leanzero-mcp-doc-processor/claude-md"><img src="https://agentmods.dev/badge/instructions/leanzero-srl/leanzero-mcp-doc-processor/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/leanzero-srl/leanzero-mcp-doc-processor/claude-md"><img src="https://agentmods.dev/badge/instructions/leanzero-srl/leanzero-mcp-doc-processor/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 | $0.12025 | $0.12025 |
| Opus 5.5 | $0.04810 | $0.04810 |
| Sonnet 5.5 | $0.02405 | $0.02405 |
| Haiku 4.5 | $0.01202 | $0.01202 |
Grade A, and why
leanzero-mcp-doc-processor 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 11d 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 — 573 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 on code in this repository.
Working rules
Read the relevant context first: this file, README.md, the files you will change and the code around them, and the test suite that covers them. Then act: the owner's global autonomy rules apply here. Do not restate the task and wait for a go-ahead; do the work end to end (change, run the covering npm run test:X suites, commit) and report what you did. Ask only for the DANGER ZONE items below, or when the request is genuinely ambiguous after reading the code.
PROJECT OVERVIEW
This is an MCP (Model Context Protocol) server that processes PDF, DOCX, and Excel files. It exposes 14 active tools advertised via ListToolsRequestSchema (plus backward-compatible aliases dispatched in CallToolRequestSchema) over stdio transport, enabling AI models to read, create, edit, and manage documents with intelligent styling, categorization, and lineage tracking.
Server identity: mcp-doc-processor v1.0.0
SDK: @modelcontextprotocol/sdk ^1.25.2
Runtime: Node.js with ES modules ("type": "module")
Transport: StdioServerTransport (stdin/stdout for MCP protocol, stderr for logging)
COMMANDS
# Start MCP server (stdio transport)
npm start
# Test suites
npm test # Markdown format router (custom-assert)
npm run test:read-doc # read-doc URL-fetch extension — 14 tests (node:test)
npm run test:schemas # MCP schema invariants + detect-format E2E — 6 tests (node:test)
npm run test:render # parseMarkdownToDocx + create-doc round-trip — 15 tests (node:test)
npm run test:upload # uploadFileToTarget + create-doc upload integration — 18 tests (node:test)
npm run test:create-tags # create-doc tag-based style resolution (getTemplateByTag crash regression)
npm run test:create-pdf # create-pdf render + read-doc round-trip (Puppeteer)
npm run test:format-router # detect-format semantic routing (pdf/csv/pptx/nuance)
npm run test:all # Run all suites in sequence
npm run lint:no-console-log # Fail if any src/ file uses console.log (corrupts MCP stdio)
npm run insights # Summarize logs/insights.jsonl (per-tool success, categories, clients)
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.
- 11d ago Changed · -104 lines · -696 tokens per session 4bb2c405b344
- 26d ago Changed · +1 lines · +494 tokens per session fee8db3bd87c
- 2mo ago First seen · 676 lines · 12,227 tokens per session scan A c7b636d493c3
leanzero-mcp-doc-processor CLAUDE.md is an instructions file published in the GitHub repository leanzero-srl/leanzero-mcp-doc-processor (1 stars, last pushed yesterday), licensed MIT. It adds 12,025 tokens to every session, about $0.0481 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.
leanzero-mcp-doc-processor CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| leanzero-mcp-doc-processor CLAUDE.mdleanzero-srl/leanzero-mcp-doc-processor | Instructions file | 1 | yesterday | MIT | A | 12,025 | 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 |