What is ha-coordinator-add?

A change guide for adding another DataUpdateCoordinator to an existing Home Assistant custom integration. A coordinator regularly retrieves and stores data, and separate coordinators can use different update intervals.

Use it when adding a coordinator for alerts, slower master data, or another distinct data role, including its options flow, translations, runtime data, and tests.

It helps separate data that needs different refresh speeds without manually working out all the related integration files and wiring.

ha-coordinator-add — 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-coordinator-add

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-coordinator-add/github.svg)](https://agentmods.dev/skills/nolte/claude-home-assistant/ha-coordinator-add)

Your own site

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

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,812 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	$0.00120	$0.01812
Opus 5	$0.00060	$0.00906
Sonnet 5	$0.00024	$0.00362
Haiku 4.5	$0.00012	$0.00181

Measured 10d ago against content hash fba660aba6a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ha-coordinator-add 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 10d 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-coordinator-add/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HA Coordinator Add

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

Why this is a skill, not an agent

Quick, targeted change in the current context (decisive): appending one coordinator touches a handful of known files in the integration the conversation is already working on; per the skill-vs-agent change-scope dimension that routes to the main thread.
Mid-flow approval: role, update interval, and RuntimeData wiring are confirmed with the operator before writing.
Counter-dimension considered: the addition has a well-defined input/output shape (agent bias), but the spin-up and report boundary of a subagent buys nothing for a change this local — latency and interactivity win.

When this skill activates

Use this skill when the user wants to add a new DataUpdateCoordinator to an existing integration — typically because a subset of data needs a faster (alerts) or slower (master data) update interval than the existing coordinator.

When NOT to activate

greenfield scaffold → ha-integration-scaffold
removing or merging coordinators → manual code edit
bespoke push transport wiring (webhook server, MQTT broker setup) → out of scope; the push-style coordinator variant itself is supported (see Hard rules)

Hard rules

Never modify the existing coordinator. Add only; never touch the existing class signature, name, or update interval.
Never rewire platform modules. The new coordinator key lands in RuntimeData.coordinators; which platforms read from it is a follow-up user decision.
Never set min cap below 30 s without warning. Sub-30s polling risks rate-limiting / DDoS. Warn the user explicitly when they request it.
Always update the options flow. A new coordinator without a configurable interval defeats the user's ability to tune polling. The new CONF_POLL_<ROLE> lands in OPTIONS_SCHEMA plus strings.json plus translations.
Always ship tests. Three tests for the new coordinator (auth error, connection error, happy path) are mandatory.
Store the new coordinator on a typed runtime_data. The coordinator lands in the RuntimeData.coordinators mapping on a typed config entry (a typed alias such as type <Domain>ConfigEntry = ConfigEntry[RuntimeData], used throughout); re-verify the RuntimeData dataclass field type when the mapping key is added so the typed entry stays sound (ha/runtime-data-pattern).
Surface PARALLEL_UPDATES for the backed platforms. This skill adds the coordinator, not the entity-platform modules — but every platform that reads the new coordinator needs a module-level PARALLEL_UPDATES (Silver parallel-updates rule). Surface this in the report and point the user at ha-entity-platform-add / ha-entity-description-map to emit it.
Push-style variant for local_push / cloud_push. For a push iot_class a poll-based coordinator is the wrong shape — a push-style coordinator (async_set_updated_data, no update_interval) MAY be produced instead; the bespoke transport wiring (webhook server, MQTT broker) stays out of scope.
Verify HA internals against the official docs. Don't reproduce HA API signatures, lifecycle hooks, conventions, or schemas from memory — when uncertain, consult the official docs before generating or relying on it: Developer docs developers.home-assistant, architecture/blueprint/YAML docs home-assistant.io (see spec/ha/upstream-docs-verification/en.md).

Read the full file on GitHub · 112 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.

10d ago First seen · 112 lines · 120 tokens per session scan A fba660aba6a1

Subscribe to this mod's changes

ha-coordinator-add is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,812 once invoked, about $0.0006 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 coordinator custom-integration home-assistant

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