homeassistant-claude-kit CLAUDE.md

homeassistant-claude-kit CLAUDE.md is an instructions file for Claude Code from dcb/homeassistant-claude-kit. It costs 2,909 tokens per session, scanned A, original, MIT.

Project instructions for managing Home Assistant, a platform for controlling smart-home devices and automations, plus a custom dashboard. They define setup steps, approval boundaries, validation rules, and documentation requirements.

In plain words
What is it for?
Use them when setting up Home Assistant, changing YAML, automations, helpers, dashboards, device entities, or domain-specific documentation. They also guide diagnosis and the reload process after deployment.
Why use it?
They make changes safer by requiring existing system information to be checked and by limiting changes that could affect household routines. They also require validation and documentation before changes are pushed.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/dcb/homeassistant-claude-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/dcb/homeassistant-claude-kit

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 homeassistant-claude-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dcb/homeassistant-claude-kit/claude-md.svg)](https://agentmods.dev/instructions/dcb/homeassistant-claude-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dcb/homeassistant-claude-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/dcb/homeassistant-claude-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,909 This file is loaded in full into every session.
When invoked 2,909 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.02909 $0.02909
Opus 5 $0.01455 $0.01455
Sonnet 5 $0.00582 $0.00582
Haiku 4.5 $0.00291 $0.00291

Measured 6d ago against content hash cbec548caa4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

homeassistant-claude-kit CLAUDE.md scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **`curl http://localhost:8123` from inside HA container** (via SSH) — connection refused. HA's HTTP server binds to the host network.
CLAUDE.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Home Assistant Configuration Management

You are an expert Home Assistant developer building reliable, maintainable automations and a custom React dashboard. You have deep knowledge of HA's YAML configuration, entity model, and automation engine.

First Run

If this is a new setup (no config/ files yet, no .env), invoke the setup skills in order:

  1. setup-infrastructure — configure SSH, HA token, pull existing config
  2. setup-customize — map areas/entities to dashboard, configure helpers

Three-Tier Boundaries

Always do Ask first Never do
Read docs/system-*.md before touching a domain Change configuration.yaml includes Modify .storage/ files
Run make validate before make push Create new input_* helpers Hardcode thresholds or timeouts
Reload relevant domain after push Add new automations that affect other domains Guess entity IDs
Update docs/system-*.md after any change Delete or rename automations Use continue_on_error: true to hide failures

Critical Rules

  1. Diagnose root causes before touching anything. Trace the full code path — read actual data, state values, and execution flow — until you can explain why it breaks. Only then fix the cause, not the symptom. Never use band-aids: continue_on_error: true, hardcoded fallbacks, duplicate automations, or !important/z-index hacks.

  2. Never assume — read or ask first. Before writing code that touches an existing file, read it. Never guess entity IDs, service names, sensor states, config values, schema shapes, or API response structures.

  3. Never hardcode configurable values. All thresholds, timeouts, temperatures, and tunable parameters must be exposed as input_number/input_boolean/input_select helpers and shown in the dashboard Settings view.

Before Making Changes

  1. Read docs/system-*.md for the relevant domain before modifying automations or config. These describe hardware, sensors, entity names, and design decisions.
  2. Read docs/house-rules.md for behavioral patterns and physical constraints. If blocked by privacy mode, ask the user for relevant constraints before proceeding.
  3. Consult the Home Assistant docs — HA updates frequently.

Read the full file on GitHub · 214 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. 6d ago First seen · 214 lines · 2,909 tokens per session scan A cbec548caa4a

Subscribe to this mod's changes

homeassistant-claude-kit CLAUDE.md is an instructions file published in the GitHub repository dcb/homeassistant-claude-kit (119 stars, last pushed yesterday), licensed MIT. It adds 2,909 tokens to every session, about $0.0145 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.