nickol-knx-mcp: Instructions file for Claude Code

CLAUDE.md

nickol-knx-mcp CLAUDE.md is an instructions file for Claude Code from NickoScope/nickol-knx-mcp. It costs 955 tokens per session, scanned A, original, MIT.

A project instruction file for an ETS/KNX assistant. KNX is a building-automation system, while ETS is the software used to configure it; the file explains how KNX projects and Home Assistant configurations must be handled.

In plain words
What is it for?
Use it when reading KNX project files, generating Home Assistant configuration, creating ETS group-address exports, or preparing reports for review.
Why use it?
It prevents unsafe live-control proposals and requires a reviewable report and tracked changes before importing or deploying configuration.

Instructions file for Claude Code

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

This is NickoScope/nickol-knx-mcp's own configuration. It tells Claude Code how to work on nickol-knx-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 nickol-knx-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NickoScope/nickol-knx-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/NickoScope/nickol-knx-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/NickoScope/nickol-knx-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 nickol-knx-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nickoscope/nickol-knx-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nickoscope/nickol-knx-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 955 This file is loaded in full into every session.
When invoked 955 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 $0.00955 $0.00955
Opus 5 $0.00477 $0.00477
Sonnet 5 $0.00191 $0.00191
Haiku 4.5 $0.00096 $0.00096

Measured 10d ago against content hash b7eb846576bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nickol-knx-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 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.

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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ETS / KNX Assistant — project rules

This file is the design playbook for working on this KNX project with the nickol-knx MCP server. Claude Code loads it automatically as project context. Apply these rules when reading the .knxproj, generating Home Assistant config, or producing ETS group-address exports.

Hard safety rules

  • Never propose writing to a live KNX bus. The nickol-knx server has no bus access; keep it that way. Live control happens only through the Home Assistant layer, and only when the user explicitly asks.
  • Always generate a Markdown report (project_report) and let the user read it before any import into ETS or deploy into Home Assistant.
  • All generated files go into the Git-tracked workspace. Commit before and after changes so every step is reversible.

Two-layer architecture

  • KNX (ETS) owns foundational logic and runs autonomously. The integrator programs it. Treat the .knxproj as the source of truth for addresses + DPTs.
  • Home Assistant is the upper smart layer (automations, templates). HA must read real device state, never assume it.

Group address structure (3-level Main/Middle/Sub)

  • Main group = function domain. Suggested split: 0 Central/Scenes · 1 Lighting · 2 Shutters/Blinds · 3 HVAC · 4 Sensors · 5 Energy · 6 Diagnostics · 7 Reserve.
  • Middle group = sub-function or zone (e.g. Switch / Dimming / Status / Position).
  • Keep commands and status in distinct, predictable middle groups (e.g. command in .../0/..., feedback in .../4/...). The pairing engine matches by name tokens, so consistent naming matters more than adjacency.
  • Reserve address space in every range; never pack ranges 100%.

Command / status pairs (the most important rule)

  • Every controllable actuator must have a status object. A switch needs a state GA; a dimmer needs a brightness-state GA; a blind needs position + position state. check_missing_status flags anything without one.
  • HA entities must have a state_address (or *_state_address) wherever the KNX device can report it. No status = HA shows stale/guessed state.

Read the full file on GitHub · 71 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. 10d ago First seen · 71 lines · 955 tokens per session scan A b7eb846576bb

Subscribe to this mod's changes

nickol-knx-mcp CLAUDE.md is an instructions file published in the GitHub repository NickoScope/nickol-knx-mcp (23 stars, last pushed today), licensed MIT. It adds 955 tokens to every session, about $0.0048 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 2026-08-30.

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 · 7,104 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

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