oarx-docs-mcp: Instructions file for Claude Code

CLAUDE.md

oarx-docs-mcp CLAUDE.md is an instructions file for Claude Code from dantte-lp/oarx-docs-mcp. It costs 466 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for oarx-docs-mcp, an MCP server that searches ObjectARX 2026 documentation. ObjectARX is the C++ programming interface for extending AutoCAD.

In plain words
What is it for?
Use it when developing, testing, running, scraping, or indexing the oarx-docs-mcp project, or when writing ObjectARX code.
Why use it?
It tells the coding agent which commands, architecture, tools, and project rules to follow when working on this documentation server. The server combines text search with semantic search across indexed guides.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is dantte-lp/oarx-docs-mcp's own configuration. It tells Claude Code how to work on oarx-docs-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oarx-docs-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dantte-lp/oarx-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.

Copy the file
curl -O https://raw.githubusercontent.com/dantte-lp/oarx-docs-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dantte-lp/oarx-docs-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for oarx-docs-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dantte-lp/oarx-docs-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dantte-lp/oarx-docs-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dantte-lp/oarx-docs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dantte-lp/oarx-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.

agentmods 80×15 button for oarx-docs-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dantte-lp/oarx-docs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dantte-lp/oarx-docs-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 466 This file is loaded in full into every session.
When invoked 466 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00466 $0.00466
Opus 5.5 $0.00186 $0.00186
Sonnet 5.5 $0.00093 $0.00093
Haiku 4.5 $0.00047 $0.00047

Measured 2mo ago against content hash becbefcea949, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oarx-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 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.

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.

CLAUDE.md · 63 lines

What it actually says

oarx-docs-mcp

MCP server for semantic search across ObjectARX 2026 documentation. 89,715 text chunks from 22 guides indexed in ChromaDB with sentence-transformers.

Tech Stack

  • Python 3.13+ / uv
  • MCP SDK (FastMCP, stdio transport)
  • ChromaDB (HNSW + cosine similarity)
  • sentence-transformers (BAAI/bge-m3)
  • BeautifulSoup4 + lxml
  • httpx
  • Podman

Commands

# Install dependencies
uv sync
uv sync --all-extras

# Run tests
uv run pytest

# Lint and format
uv run ruff check src/ tests/
uv run ruff format src/ tests/

# Type checking
uv run mypy

# Run MCP server
uv run python -m oarx_docs_mcp

# Run scraper
uv run python -m oarx_docs_mcp.scraper

# Run indexer
uv run python -m oarx_docs_mcp.indexer

Architecture

  • config.py — settings + guide registries
  • data_manager.py — database auto-download (GitHub/HuggingFace/local)
  • scraper.py — CloudHelp downloader
  • indexer.py — CHM/HTML to ChromaDB
  • retriever.py — BM25 + dense + RRF + reranking
  • server.py — 3 MCP tools: list_guides, search_docs, lookup_class

Rules

  • Use oarx-docs-mcp tools when writing ObjectARX code
  • Use Context7 MCP for all other libraries
  • No secrets or .env files in commits
  • Run ruff check and ruff format before every commit
  • Run mypy before every commit
  • Type hints required on all functions (mypy strict mode)
  • Tests must mock all external dependencies
  • Documentation: English first, then Russian translation
  • Use Mermaid diagrams for architecture docs
  • NEVER mention Claude, Anthropic, or AI assistants in commits, PRs, code, or documentation. No Co-Authored-By headers
Changes

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.

  1. 2mo ago First seen · 63 lines · 466 tokens per session scan A becbefcea949

Subscribe to this mod's changes

oarx-docs-mcp CLAUDE.md is an instructions file published in the GitHub repository dantte-lp/oarx-docs-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 466 tokens to every session, about $0.0019 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.

Related

oarx-docs-mcp CLAUDE.md compared with instructions from other repositories

oarx-docs-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
oarx-docs-mcp CLAUDE.mddantte-lp/oarx-docs-mcpInstructions file08mo agoMITA466Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode