What is ha-update-check?

A scheduled Home Assistant check that finds pending updates for the platform, its operating system, add-ons, and HACS integrations. It reports each available update for review.

It helps review and track updates across a smart-home installation.

It removes the need to inspect every Home Assistant component manually and keeps skipped updates from repeatedly appearing.

ha-update-check — Skill for Claude Code by gtapps

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add gtapps/claude-code-hermit

Claude Code

/plugin install claude-code-homeassistant-hermit

Made for: Claude Code.

Or install claude-code-homeassistant-hermit, the plugin that ships this one along with the rest of its 18 skills, 3 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/gtapps/claude-code-hermit/ha-update-check.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-update-check)

Your own site

<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-update-check"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-update-check.svg" alt="Measured on agentmods" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 704 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	$0.00047	$0.00704
Opus 5	$0.00023	$0.00352
Sonnet 5	$0.00009	$0.00141
Haiku 4.5	$0.00005	$0.00070

Measured 3d ago against content hash b9b0b4c705be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ha-update-check 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 3d 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.

plugins/claude-code-homeassistant-hermit/skills/ha-update-check/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HA Update Check

Purpose

Home Assistant surfaces pending updates as update.* entities — one domain covering Core, OS/Supervisor, add-ons, and HACS integrations, each carrying installed_version/latest_version/release_summary/release_url. This skill lists what's pending and reports it in a fixed format the proposal pipeline can fan out into per-update proposals.

Native fields only — no web fetch for breaking-change detail (keeps this check cheap; fetch on accept if that's ever needed). HA-native skipped_version is honored: an update the operator skipped in the HA UI stays quiet here too.

Steps

Run the update check via the CLI:

${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha updates

The CLI:

Fetches live entity states and filters to update.* entities where state == "on" (an update is pending) and the pending version hasn't been skipped in HA.
Classifies each into a tier: core (HA Core), os (Operating System), supervisor, addon, or hacs. Core/OS/Supervisor are recognized by their well-known entity_ids; add-ons are recognized by the native backup capability they advertise (HA's supported_features BACKUP bit), which HACS/custom-integration updates lack; anything without it aggregates into the hacs bucket rather than risking noise.
Prints the findings block to stdout in the documented format below.

Output contract

reflect --scheduled-checks routes the findings block through the proposal pipeline. The stdout shape is fixed:

ha-update-check findings — <date>
Updates pending: N
- [core] Home Assistant Core: 2026.6.3 → 2026.7.1 — <release_url>
- [addon] Mosquitto broker: 6.4 → 6.5 — <release_url>
- [hacs] 7 HACS updates pending

If nothing is pending: No actionable findings. (no updates pending). If HA is unreachable: No actionable findings. (skipped: <error>).

Keep stdout to this shape — no prose, no extra sections. Each proposal title should carry the concrete target version (e.g. [ha-update] HA Core → 2026.7.1) — that keeps same-version re-emits byte-identical so proposal-triage reliably suppresses repeats; Core/OS/Supervisor and each add-on become individual proposals, all pending HACS updates aggregate into one.

Read the full file on GitHub · 49 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.

3d ago First seen · 49 lines · 47 tokens per session scan A b9b0b4c705be

Subscribe to this mod's changes

ha-update-check is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 704 once invoked, about $0.0002 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.

Claude Code Hardware and IoT ai ai-agent anthropic claude claude-code-plugin

kicad-jlcpcb-workflow

Use this skill when the user asks to "design a PCB", "make a board", "build a PCB project", "order from JLCPCB", "create a schematic", "source LCSC parts", "wire up a board", "generate a PCB from a BOM", or any KiCad + JLCPCB workflow. Also use when working with .kicadpro or .kicadpcb files. Phase 1.6 handles project…

BeckhamLabsLLC/kicad-jlcpcb · 145 tokens

especialista-em-engenharia-de-hardware

Especialista em Engenharia de Hardware. Use para design eletrônico, microcontroladores, PCB, firmware embarcado, sinais, energia e prototipagem. Palavras-chave: hardware, eletrônica, microcontrolador, PCB, embarcado, firmware, Arduino.

euwebertdefreitas/ai-skills-for-claude-code · 63 tokens

qector-hardware-engineer

Physical-layer quantum circuits, detector-error-model preparation, qLDPC reasoning, and honest target-device hardware reporting for QECTOR. The bundled library MCP server is app-free; the companion bench server adds DEM inspection, DEM collapse, code-family introspection, and hardware probes (all Provisional).…

GuillaumeLessard/qector-claude-plugin · 103 tokens

ha-update-check