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.
npx skills add sammcj/agentic-coding --skill home-assistantgit clone --depth 1 https://github.com/sammcj/agentic-codingWrote 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.
[](https://agentmods.dev/skills/sammcj/agentic-coding/home-assistant)<a href="https://agentmods.dev/skills/sammcj/agentic-coding/home-assistant"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/home-assistant/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.
<a href="https://agentmods.dev/skills/sammcj/agentic-coding/home-assistant"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/home-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 33 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00057 | $0.03259 |
| Opus 5.5 | $0.00023 | $0.01304 |
| Sonnet 5.5 | $0.00011 | $0.00652 |
| Haiku 4.5 | $0.00006 | $0.00326 |
Grade A, and why
home-assistant 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.
How it starts
The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Assistant Helper
Overview
This skill provides tools and workflows for working with Home Assistant installations. It enables querying the live HA instance for entities, services, and configuration data, debugging automations, and generating YAML configurations for automations and dashboards.
Key Capabilities:
- Query entities, states, and services from the live HA installation
- Search for similar entities to use as examples
- Check automation states and execution history
- Generate YAML configurations for copy/paste into HA
- Find real examples from the user's setup to inform new configurations
Core Workflow
When helping with Home Assistant tasks, follow this general approach:
- Understand the requirement - What is the user trying to accomplish?
- Discover existing entities - Use scripts to find relevant entities in their setup
- Find similar examples - Search for existing automations or entities that do something similar
- Generate YAML - Create well-formed YAML that can be copied directly into HA
- Explain the configuration - Describe what the YAML does and how to install it
Available Scripts
All scripts require the HA_TOKEN environment variable to be set, which contains the Home Assistant long-lived access token. The HA instance is available at http://homeassistant.local:8123.
Important: All scripts now use uv with inline PEP 723 dependency declarations and the homeassistant-api library for consistent, maintainable code. Dependencies are automatically installed by uv on first run.
Entity Discovery
ha_get_entities.py [domain]
Retrieve all entities, optionally filtered by domain.
Usage:
uv run scripts/ha_get_entities.py # All entities
uv run scripts/ha_get_entities.py light # Just lights
uv run scripts/ha_get_entities.py sensor # Just sensors
When to use: To discover what entities are available, especially when building new automations.
ha_get_state.py <entity_id>
Get the current state and attributes of a specific entity.
What ships with it
12 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.
- scripts/ha_call_service.py 2.0 KB runs code
- scripts/ha_get_automations.py 3.2 KB runs code
- scripts/ha_get_config_entries.py 2.2 KB runs code
- scripts/ha_get_config.py 938 B runs code
- scripts/ha_get_entities.py 1.5 KB runs code
- scripts/ha_get_services.py 2.0 KB runs code
- scripts/ha_get_state.py 1.4 KB runs code
- scripts/ha_get_trace.py 4.4 KB runs code
- scripts/ha_list_traces.py 4.6 KB runs code
- scripts/ha_search_dashboards.py 4.0 KB runs code
- scripts/ha_search_similar_entities.py 2.3 KB runs code
- scripts/ha_trace_summary.py 5.9 KB runs code
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.
- 1mo ago Changed · +2 lines 40f5f1d29fb4
- 1mo ago First seen · 368 lines · 57 tokens per session scan A ba3e167ef12e
home-assistant is a skill published in the GitHub repository sammcj/agentic-coding (165 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 3,259 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
gap
Program robots with GaP (graph-as-policy) — compile natural-language tasks into typed, verified robot skill graphs and run them on simulators or real robots. Use when the user mentions GaP or graph-as-policy, robot manipulation, robot skills, robot tools or capabilities, skill registries, open-robot-skills, LIBERO or…
mactop
Retrieve real-time hardware metrics from Apple Silicon Macs using mactop. Provides CPU, RAM, GPU, power, thermal, network, disk I/O, and Thunderbolt bus information. Use when the user wants system stats, hardware monitoring, or performance metrics on Apple Silicon Macs.
agentproto-llm-endpoint
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public deployment — to route Claude Code / Claude SDK through custom providers (OpenRouter, Moonshot, Groq, ZAI) via an Anthropic-compatible gateway. Covers adapter-specific behaviors, auth patterns, proxy codenames, and common failure modes.
agentpush
Bridge an imported agentpush MCP server (Telegram, WhatsApp, etc.) with live agentproto sessions via the daemon's transmitter subsystem: transmitmessage sends outbound and binds the recipient to a session, inboundwatcherstart polls agentpush for new messages, and inboundendpointcreate/POST /inbound(/:slug) route…
bureau
Drive Bureau — the browser stack's installable capability server: a stealth Firefox (Camofox) + daemon that exposes browser tools as MCP-over-HTTP on :8830, plus a CLI for saved browser identities (sessions), social capture / search, adapter health probes, declarative workflows, and Guilde connection. Use when working…