agentmods.dev

homectl

homectl is a skill for Claude Code from larsboes/Axon. It costs 98 tokens per session (389 once invoked), scanned A, original, MIT.

A command-line tool for generating Home Assistant templates and adding pinned Home Assistant components from a private configuration overlay.

In plain words
What is it for?
Use it to check template coverage, materialize Home Assistant files, or vendor selected components through the supplied CLI.
Why use it?
It keeps private device details, entity IDs, and component choices separate from the public tooling while producing reviewed output.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the home-automation plugin — 10 skills shipped together

not rated 1repo changed 1mo ago A scan 98 tokens original MIT

Good fit Use it to check template coverage, materialize Home Assistant files, or vendor selected components through the supplied CLI.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/larsboes/axon/homectl
View source ↗ larsboes/Axon larsboes.github.io
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 larsboes/Axon --skill homectl
Clone the repo
git clone --depth 1 https://github.com/larsboes/Axon

Made for: Claude Code.

Or install home-automation, the plugin that ships this one along with the rest of its 10 skills.

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 homectl

README.md
[![agentmods](https://agentmods.dev/badge/skills/larsboes/axon/homectl/github.svg)](https://agentmods.dev/skills/larsboes/axon/homectl)
Your own site
<a href="https://agentmods.dev/skills/larsboes/axon/homectl"><img src="https://agentmods.dev/badge/skills/larsboes/axon/homectl/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.

agentmods 80×15 button for homectl

Your own site · 80×15
<a href="https://agentmods.dev/skills/larsboes/axon/homectl"><img src="https://agentmods.dev/badge/skills/larsboes/axon/homectl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 389 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 $0.00098 $0.00389
Opus 5.5 $0.00039 $0.00156
Sonnet 5.5 $0.00020 $0.00078
Haiku 4.5 $0.00010 $0.00039

Measured 1mo ago against content hash d86b5b51691b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

homectl 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 1mo 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.

Packs/home-automation/skills/homectl/SKILL.md · 41 lines

What it actually says

homectl

Operate the public materialization mechanism over a private Home Assistant definition. Axon owns the parser, validation, and vendoring behavior. The selected overlay owns the templates, variable map, component lockfile, helpers, and generated output.

Commands

scripts/homectl doctor
scripts/homectl materialize
scripts/homectl components [--only NAME] [--dry-run]

Defaults resolve from AXON_OVERLAY_ROOT, AXON_HOME_ROOT, or the overlay declared by axon.local.toml:

  • capability input: <overlay>/capabilities/home-assistant
  • variables: <overlay>/config/home-assistant.vars
  • generated output: <overlay>/build/home-assistant
  • component destination: <overlay>/config/home-assistant

Every path remains overridable for isolated tests.

Boundary

  • Never point generated output into public Axon.
  • Never place a real entity ID, hostname, component selection, or device name in this Pack.
  • Treat the set of templates and components as a private inventory even when their contents use placeholders and public Git references.
  • Review component diffs before replacement; runtime fetching is not allowed.

Read references/templating.md for the token contract and references/automation-doctrine.md for reusable reliability rules.

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago Changed · +39 tokens per session d86b5b51691b
  2. 2mo ago First seen · 41 lines · 59 tokens per session scan A e4a0f3617b76

Subscribe to this mod's changes

homectl is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 389 once invoked, about $0.0004 per session on Opus 5.5. 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.

Hardware and IoTagent-skillsai-agentsbazelclaudeintegration-platformlocal-first
Related

homectl compared with skills from other repositories

homectl next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
homectllarsboes/AxonSkill11mo agoMITA98Claude Code
usecase-smart-home-brainCoWork-OS/CoWork-OSSkill537todayMITA22Claude Code, Codex
openhuetaracodlabs/aidenSkill87518d agoAGPL-3.0A15Claude Code, Codex
freecadEldanRing/qubiclSkill137d agoApache-2.0A23Claude Code, Codex
ryu-local-modelamajorai/ryuSkill44todaynoneA75Claude Code, Codex
beryl-it-techStunspot/nova-the-optimal-ai-mindSkill3110d agononeA17Claude Code, Codex
it-work-reviewerStunspot/nova-the-optimal-ai-mindSkill3110d agononeA17Claude Code, Codex