agentmods.dev

ha-apply-change

ha-apply-change is a skill for Claude Code from gtapps/claude-code-hermit. It costs 30 tokens per session (562 once invoked), scanned A, original, MIT.

A safety and deployment step for Home Assistant automation or script YAML. It checks the configuration, sends it to Home Assistant, and can reload the relevant domain.

In plain words
What is it for?
Use it after drafting a rule to check its safety, validate the YAML, apply it, reload automations or scripts, and verify the result.
Why use it?
It prevents unsafe changes from being applied without policy checks and operator confirmation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-code-homeassistant-hermit plugin — 18 skills, 3 agents shipped together

not rated 74repo +1 changed yesterday A scan 30 tokens original MIT

Good fit Use it after drafting a rule to check its safety, validate the YAML, apply it, reload automations or scripts, and verify the result.

Compare 6 skills from other repositories ↓
View source ↗ gtapps/claude-code-hermit
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.

agentmods badge for ha-apply-change

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-apply-change.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-apply-change)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-apply-change"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-apply-change.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 562 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00562
Opus 5 $0.00015 $0.00281
Sonnet 5 $0.00006 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured yesterday against content hash ba2487120de5, 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-change 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/claude-code-homeassistant-hermit/skills/ha-apply-change/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply HA Change

Steps

  1. Pre-check: Run ${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha policy-check <artifact_path> to verify safety. Read the severity field in the JSON output:

    • "block" (strict mode): stop and explain why. Create a proposal via /claude-code-hermit:proposal-create.
    • "ask" (ask mode): include the sensitive entities in the confirmation in step 2.
    • "allow": proceed to step 2.

  2. Confirm with operator before applying: Present the artifact, policy result, affected entities, and domain to reload. Obtain explicit approval for that concrete change, using the Operator Notification protocol in CLAUDE.md for channel sessions. If the operator already approved the same artifact and reload in this task, reuse that approval; changed content or targets require a new confirmation. Declined or unanswered: stop before step 3.

  3. Validate and apply: Run ${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha validate-apply <artifact_path> --reload automation (or script).

    • This runs HA config check, pushes the config to HA via REST, then reloads the domain.
    • The artifact must include id: at the top level — if missing, the CLI derives an ID from the alias or filename and warns in the output. A derived ID drifts if the alias is renamed, creating a duplicate.

  4. Post-apply: Check the JSON output for creation_ok and read .claude-code-hermit/raw/audit-ha-apply-latest.md.

    • creation_ok: true — config was pushed and verified via REST. Reload picks it up immediately.
    • creation_ok: false + message contains "YAML mode" — HA is in YAML config mode (403). Tell the operator to place the generated YAML in their HA config directory and reload manually.
    • creation_ok: false + other message — push failed with a validation error from HA. Show the error message and suggest fixing the YAML.
    • If overall successful: update your auto memory if this automation introduces a new pattern.

Safety

  • The apply path only reloads automation and script domains.
  • A block policy verdict stops the apply; an ask verdict requires approval covering the sensitive entities.
  • The operator must confirm before any reload happens.

Read the full file on GitHub · 36 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 Changed · -3 lines ba2487120de5
  2. 4d ago First seen · 39 lines · 30 tokens per session scan A 79711a1a72b0

Subscribe to this mod's changes

ha-apply-change is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 562 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 CodeHardware and IoTaiai-agentanthropicclaudeclaude-code-plugin
Related

Other skills, from other repositories

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

jensen-skills

Invoke Jensen Huang — Hardware & AI Infrastructure. Use for AI infrastructure planning, GPU and data center strategy, compute TCO analysis, and build-vs-buy decisions. Sets Claude into the Jensen Huang persona for the current conversation.

markusbegerow/board-of-directors · 50 tokens

actual-setup

Set up Actual Computer (actual.inc) inference in Hermes.

NousResearch/hermes-agent · 16 tokens

cco-tools

Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.

egorfedorov/claude-context-optimizer · 27 tokens