What is ha-automation-author?

A guide for creating one Home Assistant automation or command artifact from a plain-language intent. The result can be YAML configuration or a sandboxed Python file for automations, scripts, scenes, template entities, or commands.

Use it to create a Home Assistant automation, script, scene, template entity, REST command, shell command, or Python script.

It removes the need to decide the correct Home Assistant configuration format and write it from scratch. It also checks the result against the relevant specification.

ha-automation-author — Skill for Claude Code by nolte

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 nolte/claude-home-assistant --skill ha-automation-author

Clone the repo

git clone --depth 1 https://github.com/nolte/claude-home-assistant

Made for: Claude Code.

Or install claude-home-assistant, the plugin that ships this one along with the rest of its 45 skills, 11 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-automation-author/github.svg)](https://agentmods.dev/skills/nolte/claude-home-assistant/ha-automation-author)

Your own site

<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-automation-author"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-automation-author/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-automation-author"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-automation-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,185 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00215	$0.02185
Opus 5	$0.00108	$0.01092
Sonnet 5	$0.00043	$0.00437
Haiku 4.5	$0.00021	$0.00218

Measured 11d ago against content hash 055313590590, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ha-automation-author 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 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.

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.

skills/ha-automation-author/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HA Automation Author

Spec: spec/claude/ha-automation-author/en.md (EN canonical) / spec/claude/ha-automation-author/de.md (DE translation).

Why this is a skill, not an agent

Human-visible authoring surface — the user describes an intent and reads back the generated YAML and the conformance report; a skill keeps that on the visible command surface, like the sibling ha-blueprint-scaffold.
Mid-flow interactivity — artifact-type confirmation and the legacy-helper redirect are per-run dialogues the user must see and approve before generation.
Orchestrator-leaning — it may later dispatch a generation agent (as ha-blueprint-scaffold dispatches ha-blueprint-author); the skill-orchestrates default keeps the entry point in skill form.
Counter-dimension considered: the draft→validate→iterate loop could be an agent, but the type decision and the report belong in the user's working context; skill wins.

When this skill activates

Use this skill to author one non-blueprint automation-logic or command artifact from a described intent: an automation, script, scene, generic template entity, or a rest_command / shell_command / python_script.

When NOT to activate

a parameterized, shareable blueprint → ha-blueprint-scaffold / ha-blueprint-author
a stateful helper (input_*, counter, timer, schedule) → ha-helper-scaffold
a derived/statistical helper sensor (bayesian, derivative, filter, min_max, statistics, threshold, trend, history_stats, integration, utility_meter, group) → ha-derived-sensor-author
a Python custom integration → ha-integration-scaffold
deploying/importing into a running HA instance → out of scope (generation only)

Hard rules

One artifact, one type, one run. No multi-artifact batches.
Intent is mandatory. Without a described intent there is no generation; everything else may fall back to a documented default, stated in the output.
Read the topic spec first. Before generating, read the matching ha-automation/<topic> spec; do not generate from memory.
Never generate a legacy trigger helper. If the intent targets flux, device_sun_light_trigger, or a hand-built platform: trigger helper, propose the modern equivalent per spec/ha-automation/legacy-trigger-helpers/en.md instead.
Never overwrite an existing entity. Collision on id / unique_id / object_id aborts with the identifier quoted.
Deliberate mode, stable identity, guarded templates. automation/script carry a consciously chosen mode (with max for parallel/queued); every entity gets a stable id/unique_id and an English alias (≤50 chars); every Jinja template guards unavailable/unknown (has_value(), is_number(), float(default), availability). Names follow spec/ha/naming-conventions/en.md.
Command-artifact safety. shell_command never interpolates untrusted input unquoted (runs as root), no pipes/redirects in templates; python_script uses no import and only hass/data/logger/output; rest_command keeps verify_ssl: true unless justified and credentials out of the URL.
Verify HA internals against the official docs. Don't reproduce HA schemas/conventions from memory — consult Developer docs developers.home-assistant and home-assistant.io (see spec/ha/upstream-docs-verification/en.md).

Read the full file on GitHub · 116 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.

11d ago First seen · 116 lines · 215 tokens per session scan A 055313590590

Subscribe to this mod's changes

ha-automation-author is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 215 tokens to every session and 2,185 once invoked, about $0.0011 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 2026-08-31.

Claude Code Hardware and IoT agents anthropic automation blueprints claude home-assistant scene script yaml

embedded-iot

Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.

travisjneuman/.claude · 80 tokens

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

security-compliance

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

sangrokjung/claude-forge · 56 tokens

stride-analysis-patterns

Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.

sangrokjung/claude-forge · 30 tokens

review-loop

Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…

sangrokjung/claude-forge · 100 tokens