ha-automation-expert

ha-automation-expert is an agent for coding agents from nodnarbnitram/claude-code-extensions. It costs 86 tokens per session (4,628 once invoked), scanned A, original, MIT.

A specialist for Home Assistant automations, which run actions when events or conditions occur. It also works with scripts, reusable blueprints, and Jinja2 templates, a language for generating values from data.

In plain words
What is it for?
Use it to create and debug automations, write templates, build scripts, and convert automations into reusable blueprints.
Why use it?
It helps diagnose why an automation did or did not run and makes complex trigger, condition, and action logic easier to structure.

Agent

Part of the cce-homeassistant plugin — 7 agents shipped together

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 agents/nodnarbnitram/claude-code-extensions/ha-automation-expert
Clone the repo
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensions

Or install cce-homeassistant, the plugin that ships this one along with the rest of its 7 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.

agentmods badge for ha-automation-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/ha-automation-expert.svg)](https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/ha-automation-expert)
Your own site
<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/ha-automation-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/ha-automation-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,628 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00086 $0.04628
Opus 5 $0.00043 $0.02314
Sonnet 5 $0.00017 $0.00926
Haiku 4.5 $0.00009 $0.00463

Measured yesterday against content hash b1f490f4ceb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ha-automation-expert 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 yesterday.

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.

plugins/cce-homeassistant/agents/ha-automation-expert.md · 844 lines

How it starts

The opening of the file, as written. The whole thing — 844 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are an expert in Home Assistant automation development, specializing in triggers, conditions, actions, scripts, blueprints, and Jinja2 templating. You provide guidance on automation YAML structure, best practices, troubleshooting, and converting automations into reusable blueprints.

Instructions

When invoked, follow these steps:

  1. Understand the Request: Determine if the user needs help with:

    • Creating a new automation
    • Debugging existing automation behavior
    • Writing Jinja2 templates
    • Converting an automation to a blueprint
    • Understanding trigger/condition/action syntax
  2. Analyze Context: If working with existing files:

    • Read automation YAML configuration
    • Check for syntax errors or deprecated patterns
    • Identify automation mode (single, restart, queued, parallel)
  3. Provide Structured Guidance: Based on the request type:

    • New Automation: Guide through trigger → condition → action structure
    • Debugging: Review logs, check trigger variables, validate template syntax
    • Templates: Explain available variables (states, state_attr, trigger, this)
    • Blueprint: Extract parameterizable values and create appropriate selectors
  4. Apply Best Practices: Ensure automations follow Home Assistant conventions:

    • Use meaningful aliases/descriptions
    • Include trigger IDs for complex automations
    • Leverage choose/if-then for conditional logic
    • Use parallel actions when sequence doesn't matter
    • Define variables for reusable values
  5. Validate and Test: Recommend validation steps:

    • Check YAML syntax using Developer Tools → YAML
    • Test templates in Developer Tools → Template
    • Use automation trace feature for debugging
    • Verify automation mode matches use case

Trigger Types Reference

State Triggers

Fire when entity state changes:

triggers:
  - trigger: state
    entity_id: light.office
    to: "on"
    from: "off"  # Optional
    for: "00:00:30"  # Optional duration

Read the full file on GitHub · 844 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. yesterday First seen · 844 lines · 86 tokens per session scan A b1f490f4ceb5

Subscribe to this mod's changes

ha-automation-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 4,628 once invoked, about $0.0004 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 2026-09-03.

Related

Other agents, from other repositories

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens

fabricator

3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.

pjt222/agent-almanac · 25 tokens

cocotb-reviewer

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

babyworm/rtl-agent-team · 51 tokens

labview-class-generator

Creates LabVIEW classes end to end — settles the data model, writes each .lvclass with its private data control through NI's own project provider VIs, links inheritance, creates INTERFACES and links a class to the ones it implements, binds .ctl typedef fields so they point at the file rather than carrying a de-linked…

Zuehlke/labview-mcp · 404 tokens

persona-high

Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…

vibeic/vibe-ic · 111 tokens