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 znlgis/opengis-skills --skill home-assistantgit clone --depth 1 https://github.com/znlgis/opengis-skillsWrote 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/znlgis/opengis-skills/home-assistant)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/home-assistant"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/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/znlgis/opengis-skills/home-assistant"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/home-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00093 | $0.04887 |
| Opus 5.5 | $0.00037 | $0.01955 |
| Sonnet 5.5 | $0.00019 | $0.00977 |
| Haiku 4.5 | $0.00009 | $0.00489 |
Grade C, and why
home-assistant scanned grade C with 2 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 today.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s -H "Authorization: Bearer $TOKEN" "$HA_URL/api/states/sensor.balcony_illuminance" | python -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $TOKEN" http://localhost:8123/api/ How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目地址: https://github.com/home-assistant/core
官方文档: https://www.home-assistant.io/docs/
开发者文档: https://developers.home-assistant.io/
最新版本: 2026.10.4(GitHub Releases 与 Docker 镜像 tag 一致,截至 2026-10)
安装形态: Home Assistant OS / Supervised / Container / Core(pip)
许可证: Apache-2.0
概述
Home Assistant 是一个本地优先的开源家庭自动化平台。它把上千种设备与云服务统一成「实体(entity)」,再通过状态机、自动化规则、脚本与仪表盘把它们编排起来。数据与逻辑都跑在你自己的机器上,不依赖厂商云。
对脚本与自动化最关键的几层:
- 实体与状态:每个设备暴露为
domain.name(如light.study),状态 + 属性构成当前值 - 服务(service/action):
light.turn_on、climate.set_temperature这类可调用动作,是自动化与 API 的执行单位 - 自动化与脚本:YAML 或 UI 定义的
triggers/conditions/actions三段式规则 - REST API:
/api/*,用长期访问令牌鉴权,适合外部程序读写状态、触发服务 - WebSocket API:
/api/websocket,支持实时订阅事件、订阅触发器、批量取状态 - 模板(Jinja2):
{{ states('sensor.x') }}在自动化与/api/template中计算动态值
环境准备
方式一:Home Assistant OS(推荐给家庭用户)
在 Raspberry Pi / NUC / 虚拟机上刷写官方镜像,得到受管系统(含 Supervised、Add-ons、备份)。安装入口见 https://www.home-assistant.io/installation/。首次启动后浏览器访问 http://<ip>:8123 完成引导。
方式二:Docker Container
docker run -d \
--name homeassistant \
--restart=unless-stopped \
--privileged \
--network=host \
-e TZ=Asia/Shanghai \
-v /path/to/config:/config \
-v /run/dbus:/run/dbus:ro \
ghcr.io/home-assistant/home-assistant:stable
要点:
-v /path/to/config:/config必须持久化,否则升级即丢配置;--network=host让设备发现(mDNS/SSDP)正常工作,端口直接是 8123;- 需要直通 USB 设备(Zigbee/Z-Wave 棒)时加
--device /dev/ttyUSB0:/dev/ttyUSB0; - 关机给足时间:
docker run --stop-timeout 60,否则容易损坏数据库。
# compose.yaml
services:
homeassistant:
image: ghcr.io/home-assistant/home-assistant:stable
container_name: homeassistant
restart: unless-stopped
network_mode: host
privileged: true
stop_grace_period: 60s
environment:
TZ: Asia/Shanghai
volumes:
- ./config:/config
- /run/dbus:/run/dbus:ro
方式三:Core(pip,仅开发/调试)
python3 -m venv .venv
source .venv/bin/activate
pip install homeassistant==2026.10.4
hass --config ./config --debug
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.
- today First seen · 405 lines · 93 tokens per session scan C aad8c590d011
home-assistant is a skill published in the GitHub repository znlgis/opengis-skills (75 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 4,887 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-28.
Other skills, from other repositories
Home Assistant Automation
Automate smart home devices and create intelligent home automation workflows with Home Assistant.
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
iot-expert
Expert-level IoT systems, embedded devices, edge computing, and IoT protocols. Use when the user mentions embedded, edge computing, MQTT, sensors, or firmware, or when the task involves IoT Architecture, IoT Protocols, Embedded Systems, or Device Design.
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
unraid-management-agent
Monitor and control an Unraid server via the Unraid Management Agent's MCP server (125 tools, 5 resources, 6 diagnostic prompts) and REST API. Use when: connecting an AI client (Claude, ChatGPT, Cursor, Copilot, Gemini CLI) to Unraid; checking system, array, disk, Docker, VM, GPU, UPS, ZFS, or network status…
aether-iot-query
Use this skill when the user asks about a live AetherEdge runtime: channels, points, real-time values, history, alarms, rules, models, instances, routing, SHM health, service health, or system status. Use aether CLI commands to answer — do NOT inspect source code, local database files, or config YAMLs to answer…