Borrowing it
Nothing to install: this file belongs to SukramJ/aiohomematic. 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/SukramJ/aiohomematic/main/CLAUDE.mdgit clone --depth 1 https://github.com/SukramJ/aiohomematicWrote 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/sukramj/aiohomematic/claude-md)<a href="https://agentmods.dev/instructions/sukramj/aiohomematic/claude-md"><img src="https://agentmods.dev/badge/instructions/sukramj/aiohomematic/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/sukramj/aiohomematic/claude-md"><img src="https://agentmods.dev/badge/instructions/sukramj/aiohomematic/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 | $0.08084 | $0.08084 |
| Opus 5.5 | $0.03234 | $0.03234 |
| Sonnet 5.5 | $0.01617 | $0.01617 |
| Haiku 4.5 | $0.00808 | $0.00808 |
Grade A, and why
aiohomematic 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 22d 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 — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - AI Assistant Guide for aiohomematic
This document is the entry point for AI assistants (like Claude) working on the aiohomematic codebase.
It intentionally stays concise and delegates deep details to docs/ — treat the linked documents
as the source of truth and only fall back to this file for orientation.
Table of Contents
- CUxD / CCU-Jack Special Handling (critical)
- Project Overview
- Codebase Structure
- Development Environment
- Code Quality & Standards
- Testing Guidelines
- Architecture & Design Patterns
- Common Development Tasks
- Git Workflow
- Key Conventions
- Implementation Policy
- Interaction Protocol
- Token Use
- Tips for AI Assistants
⚠️ CRITICAL: CUxD/CCU-Jack Special Handling
STOP AND READ THIS BEFORE ANY REFACTORING
CUxD and CCU-Jack are NOT normal Homematic interfaces. They require special handling that has been broken multiple times during AI-assisted refactoring. Before making any changes, run:
pytest tests/contract/test_cuxd_ccu_jack_contract.py -v
What Makes CUxD/CCU-Jack Different
| Aspect | Standard Interfaces (HmIP-RF, BidCos-RF) | CUxD / CCU-Jack |
|---|---|---|
| Protocol | XML-RPC | JSON-RPC |
| Ports | 2001, 2010, 2000, 2002 | 80 (HTTP) / 443 (HTTPS) |
| Events | XML-RPC Server (push) | Polling (default) or MQTT (optional via HA) |
| Ping/Pong | ✅ Yes | ❌ No |
| Backend Class | CcuBackend or HomegearBackend |
JsonCcuBackend |
| XML-RPC Proxy | Required | NOT used |
| Capabilities | CCU_CAPABILITIES |
JSON_CCU_CAPABILITIES |
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.
- 22d ago Changed · +38 lines · +689 tokens per session 14111b5207d0
- 1mo ago Changed · +3 lines · +37 tokens per session ce9807b805c3
- 2mo ago Changed · +7 tokens per session ac5d73c636f4
- 2mo ago First seen · 716 lines · 7,351 tokens per session scan A 1a3c894cbb21
aiohomematic CLAUDE.md is an instructions file published in the GitHub repository SukramJ/aiohomematic (169 stars, last pushed yesterday), licensed MIT. It adds 8,084 tokens to every session, about $0.0323 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 2026-08-30.
aiohomematic CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aiohomematic CLAUDE.mdSukramJ/aiohomematic | Instructions file | 169 | yesterday | MIT | A | 8,084 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |