Borrowing it
Nothing to install: this file belongs to benethos-hub/lexware-office-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/benethos-hub/lexware-office-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/benethos-hub/lexware-office-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/benethos-hub/lexware-office-mcp/claude-md)<a href="https://agentmods.dev/instructions/benethos-hub/lexware-office-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/benethos-hub/lexware-office-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/benethos-hub/lexware-office-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/benethos-hub/lexware-office-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 | $0.04280 | $0.04280 |
| Opus 5 | $0.02140 | $0.02140 |
| Sonnet 5 | $0.00856 | $0.00856 |
| Haiku 4.5 | $0.00428 | $0.00428 |
Grade A, and why
lexware-office-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 6d 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working guidelines for Claude
How to work in this repository. Read this before making changes. See SPECS.md for what the project is and does.
Golden rules
- Nothing is enabled by default. This server talks to a live accounting
system holding real business records. The
tools.jsonpolicy file is the only thing that decides which tools exist, a tool it does not name is off, and an installation without the file offers none at all. Nothing may weaken that: no tool may register itself past the file, and no default may stand in for a decision nobody made. Never call a write tool against an account that has not been explicitly confirmed as a test account — callget_profilefirst and check the organization. - Virtual environment only. Never the global Python or pip. A
uv-created.venvcounts, souv run ...satisfies this rule. Without uv, invoke the project interpreter directly:.\.venv\Scripts\python.exe ...(PowerShell).venv/Scripts/python.exe ...(Bash on Windows)
- English in the repo. All code, comments, docstrings and documentation
are English. Conversation with the user may be German. One exception,
and only one: the text a person reads on screen in
configui/is German, because that interface has exactly one audience and Lexware Office is sold for German companies only. Code, comments and docstrings there are English like everywhere else, and a message raised outsideconfigui/is quoted into the page rather than translated — a German paraphrase would be a second copy of a rule that lives in the code. - stdio is sacred. stdout carries the MCP JSON-RPC stream. Never
print()to stdout from server or library code, log to stderr only. - One rate limiter. Every outbound request passes the single
ratelimit.TokenBucketthatclient.pyowns — retries and pagination follow-ups included. The upstream limit is global across all endpoints, so a second bucket anywhere is a bug. See SPECS.md section 10.1. A throwaway probe script is not an exception: build aLexwareClientrather than a barehttpx.AsyncClient, or the third request comes back 429 and the account has been told this key misbehaves. - Secrets never travel. The API key is never logged, never returned in a tool result, and redacted from error text. No real key, tenant ID, organization ID, voucher ID or customer record in any versioned file. Nor does a filesystem path of this machine. Anything handed to the client ends up in a model's context: a path carries a user name and a directory layout, and the caller cannot act on it anyway. Say what to set or which command to run, and let stderr name the file for the person sitting at the machine. The one exception is a path the caller supplied or asked for, such as a download's destination.
- The repo stands on its own. State a convention as this project's decision. Do not reference the author's other repositories, local filesystem paths, or email addresses in versioned files.
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.
- 6d ago Changed · +37 lines · +511 tokens per session 4e5d398c93d1
- 9d ago First seen · 281 lines · 3,769 tokens per session scan A 4bf0c3898142
lexware-office-mcp CLAUDE.md is an instructions file published in the GitHub repository benethos-hub/lexware-office-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 4,280 tokens to every session, about $0.0214 per session on Opus 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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.