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 agentmods add skills/ha-china/ha_claw/sourcenpx skills add ha-china/ha_claw --skill sourcegit clone --depth 1 https://github.com/ha-china/ha_clawWrote 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/ha-china/ha_claw/source)<a href="https://agentmods.dev/skills/ha-china/ha_claw/source"><img src="https://agentmods.dev/badge/skills/ha-china/ha_claw/source.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00172 |
| Opus 5 | $0.00008 | $0.00086 |
| Sonnet 5 | $0.00003 | $0.00034 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
homeassistant 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 4d 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.
What it actually says
Home Assistant Source Guide
This file is not the primary runtime guide.
Use runtime/*.md first.
Use this source layer only when you need:
- the original teaching shape behind the runtime guide
- deeper workflow notes
- safety reference material
- naming-context reference material
- source-level topics such as esphome, dashboards, or automation troubleshooting
Inside claw_assistant:
- do not require external setup
- do not require shell wrappers or terminal bootstrap
- translate all guidance back into internal tools and services
Reference entry points:
references/workflows.mdreferences/checklists.mdreferences/safety-policy.mdreferences/naming-context.md
What ships with it
5 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.
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.
- 4d ago First seen · 33 lines · 15 tokens per session scan A 3ea5dfdd92e2
homeassistant is a skill published in the GitHub repository ha-china/ha_claw (100 stars, last pushed 15d ago), licensed MIT. It adds 15 tokens to every session and 172 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
blueprint-import
Migrate an existing Home Assistant custom integration into the blueprint's structure and tooling without breaking the installations already running it. Use when asked to "import my integration", "migrate my existing integration into the blueprint", "adopt the blueprint in my repository", "move my custom component…
ha-service-action
Add, change, or remove a Home Assistant service action (also called a "service" or "action") in this custom integration. Use when asked to "add a service", "add an action", "expose X as a service call", "add a service that returns data", "make this callable from an automation", or when editing services.yaml, the…
ha-config-flow
Work on the Home Assistant config flow of this custom integration — the setup UI, options flow, reauthentication, reconfigure, discovery (zeroconf, dhcp, ssdp, bluetooth, usb, mqtt, homekit), subentries, unique IDs, and config entry version migration. Use when asked to "add a config option", "add a setting", "ask the…
ha-entity-platform
Add or change a Home Assistant entity platform or an individual entity in this custom integration — sensor, binarysensor, switch, button, number, select, fan, climate, cover, light, lock, and friends. Use when asked to "add a sensor", "add a new entity", "add a platform", "expose as an entity", "add an entity to the…
ha-planning
Plan a large change to this Home Assistant custom integration before writing code, or record an architectural decision. Use when asked to "create a plan", "plan this feature", "how should we approach", "propose an architecture", "write an ADR", "document this decision", "should we use library X or write our own…
blueprint-scaffold
Turn this freshly initialised blueprint into a working integration for one concrete device, service or computed source — decide the manifest classification, write the API client if there is one, shape the coordinator payload, keep or delete each example entity platform, and get the first end-to-end run green. Use when…