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.
curl -O https://raw.githubusercontent.com/NickoScope/nickol-knx-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/NickoScope/nickol-knx-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/nickoscope/nickol-knx-mcp/claude-md)<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.
<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>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 | $0.00955 | $0.00955 |
| Opus 5 | $0.00477 | $0.00477 |
| Sonnet 5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00096 | $0.00096 |
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.
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-knxserver 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
.knxprojas 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_statusflags 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.
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.
- 10d ago First seen · 71 lines · 955 tokens per session scan A b7eb846576bb
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.
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.