Home Assistant YAML

Home Assistant YAML is a skill for Claude Code from tonylofgren/aurora-smart-home. It costs 84 tokens per session (5,731 once invoked), scanned B, original, MIT.

A guide for configuring Home Assistant, an open-source system for controlling smart-home devices, using YAML text files. It covers automations, reusable blueprints, scripts, scenes, dashboards, sensors, and templates.

In plain words
What is it for?
Use it to create or adjust smart-home automations, dashboards, notifications, presence detection, voice commands, calendar actions, and Jinja2 templates.
Why use it?
It helps avoid writing configuration that does not match the user's devices or Home Assistant setup. It first clarifies whether the user needs an automation or a reusable blueprint, and whether they use the interface or YAML files.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aurora plugin — 6 skills, 1 command shipped together

Good fit Use it to create or adjust smart-home automations, dashboards, notifications, presence detection, voice commands, calendar actions, and Jinja2 templates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tonylofgren/aurora-smart-home/home-assistant
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.

Any agent
npx skills add tonylofgren/aurora-smart-home --skill home-assistant
Clone the repo
git clone --depth 1 https://github.com/tonylofgren/aurora-smart-home

Made for: Claude Code.

Or install aurora, the plugin that ships this one along with the rest of its 6 skills, 1 command.

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 Home Assistant YAML

README.md
[![agentmods](https://agentmods.dev/badge/skills/tonylofgren/aurora-smart-home/home-assistant/github.svg)](https://agentmods.dev/skills/tonylofgren/aurora-smart-home/home-assistant)
Your own site
<a href="https://agentmods.dev/skills/tonylofgren/aurora-smart-home/home-assistant"><img src="https://agentmods.dev/badge/skills/tonylofgren/aurora-smart-home/home-assistant/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 Home Assistant YAML

Your own site · 80×15
<a href="https://agentmods.dev/skills/tonylofgren/aurora-smart-home/home-assistant"><img src="https://agentmods.dev/badge/skills/tonylofgren/aurora-smart-home/home-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,731 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high System Prompt Leakage · line 138
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
  • high System Prompt Leakage · line 260
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
How audits are shown
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 $0.00084 $0.05731
Opus 5 $0.00042 $0.02865
Sonnet 5 $0.00017 $0.01146
Haiku 4.5 $0.00008 $0.00573

Measured 11d ago against content hash df23e0ace650, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

Home Assistant YAML scanned grade B 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 11d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

- **Markdown** (README, automation docs, blueprint instructions): `> *Generated by [aurora@aurora-smart-home (home-assistant skill)](https://github.com/tonylofgren/aurora-smart-home)*` as a blockquote banner directly und
home-assistant/SKILL.md · 513 lines

How it starts

The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Home Assistant Automation

Reference skill for Home Assistant configuration and automation.

Overview

Core principle: Never generate YAML without understanding the user's intent. Automation vs blueprint, UI editor vs YAML files, and entity naming conventions must be clarified first.

Context: This skill requires intent clarification before any YAML generation. Automations are specific to a user's setup; blueprints are reusable templates. The format (UI vs YAML) affects how entities are referenced.

The Iron Law

CLARIFY INTENT BEFORE GENERATING ANY YAML
USE MODERN SYNTAX: action: (not service:), triggers:/conditions:/actions: (plural)

Ask: Automation or Blueprint? Format: UI or YAML? Never assume. Never skip these questions.

Official Reference Files (read before generating YAML)

Before generating any automation YAML, read the relevant official reference file:

YAML element Official reference
Actions (action:, target:, data:) references/actions-2026-official.md
Triggers (triggers:, trigger:) references/triggers-2026-official.md
Conditions (conditions:, condition:) references/conditions-2026-official.md

These files capture the current official HA docs (snapshot 2026-05-30) and supersede the older actions.md, conditions.md, and triggers-advanced.md files for syntax questions. Read only the file(s) relevant to what the user is building.

The Process

User request
    │
    ▼
Ask: Automation or Blueprint?
    │
    ▼
Ask: UI editor or YAML files?
    │
    ▼
Ask: Output method?
    │
    ▼
Intent clear? ──no──▶ Ask more questions
    │ yes
    ▼
Read official reference file(s) above
    │
    ▼
Generate YAML
    │
    ▼
Run pre-completion checklist
    │
    ▼
Deliver configuration

Common Pitfalls

Watch out for these assumptions:

Thought Reality
"Request is clear enough" NO. Always ask automation vs blueprint, UI vs YAML
"They want an automation" ASK. Could be blueprint, script, or scene
"Simple request needs simple answer" NO. Simple requests still need intent clarification
"User just wants code quickly" NO. Wrong code is slower than asking first
"I'll provide options instead" NO. Ask questions, don't provide multiple YAML versions
"Sunset/motion light is obvious" NO. Which lights? What brightness? Conditions?
"YAML format is standard" ASK. Many users prefer UI editor format
"This entity_id looks right" VERIFY. Users have different naming conventions
"I'll skip the questions for simple requests" NO. This IS the rationalization the skill forbids
"service_template works fine" DEPRECATED. Use action: "{{ ... }}"
"data_template is cleaner" DEPRECATED. Use data: with templates
"service: is the correct keyword" RENAMED in HA 2024.8. Use action: instead
"trigger: is singular" RENAMED in HA 2024.10. Use plural: triggers:, conditions:, actions:
"states() is the easiest approach" SLOW. Filter by domain: states.sensor

Read the full file on GitHub · 513 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 513 lines · 84 tokens per session scan B df23e0ace650

Subscribe to this mod's changes

Home Assistant YAML is a skill published in the GitHub repository tonylofgren/aurora-smart-home (104 stars, last pushed 6d ago), licensed MIT. It adds 84 tokens to every session and 5,731 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

bat-story-eval

Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.

homeassistant-ai/ha-mcp · 26 tokens

contrib-pr-review

Review a contribution PR for safety, quality, and readiness. Checks for security concerns, test coverage, size appropriateness, and intent alignment. Use when reviewing external contributions.

homeassistant-ai/ha-mcp · 39 tokens

bat-adhoc

Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs.

homeassistant-ai/ha-mcp · 48 tokens

issue-to-pr-resolver

Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean. Use when you need to fully implement a GitHub issue from start to merge-ready. Triggers on "implement issue", "resolve…

homeassistant-ai/ha-mcp · 85 tokens

my-pr-checker

Manage your own GitHub pull requests — check CI status, inline review comments, PR-level comments, resolve review threads, fix issues, and iterate until all checks pass and threads are resolved. Use for managing your own PRs (not external contributions). Triggers on "check my PR", "check PR", "/my-pr-checker ".

homeassistant-ai/ha-mcp · 75 tokens

contributors-update

Find merged PR authors missing from README and update the contributors list after approval.

homeassistant-ai/ha-mcp · 17 tokens