claude-hawin: Instructions file for Claude Code

CLAUDE.md

claude-hawin CLAUDE.md is an instructions file for Claude Code from dashdevil/claude-hawin. It costs 546 tokens per session, scanned A, original, MIT.

A CLAUDE.md instruction file for a specific Home Assistant setup. Home Assistant is software for controlling smart-home devices and automations.

In plain words
What is it for?
Use it as agent guidance when maintaining this Home Assistant configuration, especially its packages, scripts, validation workflow, and KNX integration.
Why use it?
It records project-specific rules for editing YAML packages, validating changes, handling KNX addresses, and deploying through SSH. This reduces the chance of violating the setup's conventions.

Instructions file for Claude Code

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

This is dashdevil/claude-hawin's own configuration. It tells Claude Code how to work on claude-hawin 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 claude-hawin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dashdevil/claude-hawin. 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/dashdevil/claude-hawin/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dashdevil/claude-hawin

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 claude-hawin CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dashdevil/claude-hawin/claude-md"><img src="https://agentmods.dev/badge/instructions/dashdevil/claude-hawin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 546 This file is loaded in full into every session.
When invoked 546 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 $0.00546 $0.00546
Opus 5.5 $0.00218 $0.00218
Sonnet 5.5 $0.00109 $0.00109
Haiku 4.5 $0.00055 $0.00055

Measured 2mo ago against content hash 534a2a2b1ac1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-hawin 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 2mo 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 · 62 lines

What it actually says

Home Assistant -- Claude Code Context

HA 2025.x | Bewohner: BEWOHNER_1 & BEWOHNER_2

Regeln

  • Alles in Packages -- niemals automations.yaml, scripts.yaml oder GUI
  • Keine HA-Scenes -- ausschliesslich Scripts verwenden
  • MCP nur zum Pruefen -- Coding in YAML-Packages, Deployment per SSH
  • Validation ist Pflicht -- Hooks laufen automatisch, Pre-Push blockiert bei Fehlern
  • Vor KNX-Aufgaben immer KNX_group_addresses_xml.csv lesen
  • NIEMALS .storage/-Dateien manipulieren -- nur HA-UI, MCP oder REST API
  • Vor groesseren Umbauten Backup erstellen (bash ha backup)

Entity-ID Umlaute

HA slugifiziert Umlaute ohne ae/oe/ue-Ersetzung:

Zeichen Entity-ID Falsch
ae prasenz praesenz
oe scholl schoell
ue kuche kueche
ss strasse --

Zugang

ssh [email protected]          # TODO: Dein HA-Host
# Packages: /config/packages/
# Secrets:  /config/secrets.yaml      # NIE ausgeben!

Workflow

bash ha pull                # Packages vom Server holen
bash ha push <datei.yaml>   # Validieren + pushen
bash ha push-all            # Alle Packages pushen
bash ha test                # Validatoren lokal ausfuehren
bash ha check               # Config-Check auf dem Server
bash ha errors              # ERROR-Zeilen aus HA-Log
bash ha backup              # Timestamped Backup

Nach Push: Reload via MCP (automation.reload / script.reload). Nicht ha core reload!

Schluessel-Entities

notify.mobile_app_DEIN_HANDY              # TODO: Haupt-Benachrichtigung
# notify.mobile_app_PARTNER               # TODO: Partner
# switch.tag_nacht                        # Tag/Nacht
# binary_sensor.jemand_zuhause            # Praesenz

Namensschema

  • Alias: [Gewerk]: [Ort --] Funktion
  • ID: slugifizierter Alias (alarm_kueche_wassermelder)
  • Gewerke: Alarm, Beleuchtung, Beschattung, Heizung, ...
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. 2mo ago First seen · 62 lines · 546 tokens per session scan A 534a2a2b1ac1

Subscribe to this mod's changes

claude-hawin CLAUDE.md is an instructions file published in the GitHub repository dashdevil/claude-hawin (2 stars, last pushed 8mo ago), licensed MIT. It adds 546 tokens to every session, about $0.0022 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 2026-08-31.

Related

claude-hawin CLAUDE.md compared with instructions from other repositories

claude-hawin CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-hawin CLAUDE.mddashdevil/claude-hawinInstructions file28mo agoMITA546Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file282k3d agoMITA4,335Codex, OpenCode