What is ha-apply-update?

A controlled updater for Home Assistant, the software that manages smart-home devices. It applies approved updates according to whether they affect an add-on, community integration, or core system component.

Use it to apply an update proposal after checking the configured policy and update tier.

It prevents updates from being installed automatically when they could affect the main Home Assistant system. It also makes the operator explicitly approve sensitive updates.

ha-apply-update — 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-apply-update.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-apply-update)

Your own site

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

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 811 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	$0.00058	$0.00811
Opus 5	$0.00029	$0.00405
Sonnet 5	$0.00012	$0.00162
Haiku 4.5	$0.00006	$0.00081

Measured 3d ago against content hash 65f5a88ed4a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ha-apply-update 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-apply-update/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply HA Update

When this runs

Invoked from proposal-act's Accept flow for a [ha-update] proposal (originated by /claude-code-homeassistant-hermit:ha-update-check). The proposal body carries the entity_id, tier (core/os/supervisor/addon/hacs), and target version.

Steps

Read the flag: check ha_update_auto_apply in .claude-code-hermit/config.json.
- Absent or false: this is advisory-only. Resolve the proposal — tell the operator the update is available and where (Settings → System → Updates in the HA UI), and stop. Do not call update.install.
- true: continue.
Branch on tier (from the proposal body). The addon vs hacs split is defined by the native backup capability: ha-update-check tiers an entity addon precisely when it advertises HA's BACKUP update feature, so backup:true is always valid for an addon proposal, and a hacs entity is one that can't back itself up (hence the separate full-backup step).
- addon: ${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha call-service update.install --data '{"entity_id":"<entity_id>","backup":true}' --confirm. HA backs up the add-on natively and rolls back on install failure. Report the result to the operator once done.
- hacs (an individual HACS entity accepted out of an aggregated proposal — HACS entities don't support the native backup parameter): first ${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha create-backup --agent-ids <configured agent> --confirm. If the backup call is blocked or fails, stop and stay advisory — tell the operator why. Only on a successful backup: ha call-service update.install --data '{"entity_id":"<entity_id>"}' --confirm.
- core / os / supervisor: never auto-apply, even with the flag on. Use AskUserQuestion (or the channel, if this is a routine-fired context — see Operator Notification protocol in CLAUDE.md): "Home Assistant update ready: <installed_version> → <latest_version>. This can affect access to your dashboard, so I'll wait for your go-ahead. Install now?" Only on an explicit yes: ha call-service update.install --data '{"entity_id":"<entity_id>","backup":true}' --confirm.

Read the full file on GitHub · 31 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 · 31 lines · 58 tokens per session scan A 65f5a88ed4a2

Subscribe to this mod's changes

ha-apply-update is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 811 once invoked, about $0.0003 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-apply-update