victron-tcp: Instructions file for Claude Code

CLAUDE.md

victron-tcp CLAUDE.md is an instructions file for Claude Code from lubosstrejcek/victron-tcp. It costs 1,618 tokens per session, scanned A, original, MIT.

Repository instructions for a read-only MCP server that lets AI assistants read data from Victron Energy GX devices on a local network. It uses Modbus TCP or MQTT, which are ways for devices to exchange data.

In plain words
What is it for?
Use it when building, testing, simulating, or inspecting this Victron device integration, including its TypeScript build and local data reads.
Why use it?
They give an AI coding assistant the project’s structure, commands, testing setup, and important limits, reducing mistakes when changing or checking the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is lubosstrejcek/victron-tcp's own configuration. It tells Claude Code how to work on victron-tcp 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 victron-tcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lubosstrejcek/victron-tcp. 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/lubosstrejcek/victron-tcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lubosstrejcek/victron-tcp

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 victron-tcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lubosstrejcek/victron-tcp/claude-md/github.svg)](https://agentmods.dev/instructions/lubosstrejcek/victron-tcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lubosstrejcek/victron-tcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lubosstrejcek/victron-tcp/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 victron-tcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lubosstrejcek/victron-tcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lubosstrejcek/victron-tcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,618 This file is loaded in full into every session.
When invoked 1,618 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 $0.01618 $0.01618
Opus 5 $0.00809 $0.00809
Sonnet 5 $0.00324 $0.00324
Haiku 4.5 $0.00162 $0.00162

Measured 11d ago against content hash 89e4de83aaf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

victron-tcp 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.

CLAUDE.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 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.

What this is

An MCP server (stdio transport) that exposes a Victron Energy GX device to AI assistants as read-only tools, reading real-time data over Modbus TCP or MQTT on the local network. It is the local/LAN half of a pair; the cloud half is the separate victron-vrm-mcp repo. This package never speaks HTTP and is not reachable by the Anthropic MCP Connector directly.

Commands

After a fresh clone there is no node_modules — run npm install first or tsc/vitest fail with "command not found".

npm run build      # tsc → dist/
npm run dev        # tsc --watch
npm start          # run compiled server (node dist/index.js)
npm test           # vitest run (whole suite)
npm run simulate   # local Modbus TCP simulator — test tools without real hardware
npm run convert <ccgx-xlsx> [evcs-xlsx]   # regenerate data/*.json from the Victron Excel register list
npm run smoke      # tsx scripts/smoke.ts — boots the stdio server and does a real
                   # end-to-end Modbus read AND MQTT read against the simulator
npm run inspect     # MCP Inspector against locally-built server
npm run inspect:npm # MCP Inspector against the published npm package

CI (.github/workflows/ci.yml) runs npm ci → build → test → smoke on Node 24. npm test alone will not catch a broken stdio handshake or transport regression — run npm run smoke before pushing. engines still declares >=18.0.0, so 18 remains the supported floor even though CI pins 24.

Run a single test file or test:

npx vitest run tests/decoders.test.ts
npx vitest run -t "decodeNumeric"

Node 18+. The project is ESM ("type": "module", tsconfig Node16): all relative imports must use the .js extension, even when importing a .ts source file.

Architecture

The request flow for every device tool is the same:

tool (src/tools/*.ts)
  → buildConnectionParams(input)        # helpers.ts: merge tool args + env config, pick transport
  → readDeviceRegisters(params, service, registers)   # transport.ts: dispatch
      → withModbusClient(...)  OR  withMqttClient(...)  # connect-per-request, then close
  → formatResults(title, results)  /  errorResult(error)  # helpers.ts

Read the full file on GitHub · 72 lines

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. 11d ago First seen · 72 lines · 1,618 tokens per session scan A 89e4de83aaf6

Subscribe to this mod's changes

victron-tcp CLAUDE.md is an instructions file published in the GitHub repository lubosstrejcek/victron-tcp (3 stars, last pushed 2d ago), licensed MIT. It adds 1,618 tokens to every session, about $0.0081 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,126 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens