Home Assistant is open-source home automation software that lets people control devices and actions locally through a modular system. It is used by home-automation enthusiasts and DIY users, often on a Raspberry Pi or local server; the catalogue entries support operating or developing its integrations and codebase.
Borrowing it
Nothing to install: this file belongs to home-assistant/core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/home-assistant/core/dev/.claude/skills/ha-quality-scale-verify/SKILL.mdgit clone --depth 1 https://github.com/home-assistant/coreWrote 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/home-assistant/core/ha-quality-scale-verify)<a href="https://agentmods.dev/skills/home-assistant/core/ha-quality-scale-verify"><img src="https://agentmods.dev/badge/skills/home-assistant/core/ha-quality-scale-verify/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/home-assistant/core/ha-quality-scale-verify"><img src="https://agentmods.dev/badge/skills/home-assistant/core/ha-quality-scale-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00084 | $0.01627 |
| Opus 5.5 | $0.00034 | $0.00651 |
| Sonnet 5.5 | $0.00017 | $0.00325 |
| Haiku 4.5 | $0.00008 | $0.00163 |
Grade A, and why
ha-quality-scale-verify 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 19d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Quality Scale Rule
You are verifying whether a Home Assistant integration follows a quality scale rule. Verify one rule at a time; to check a full tier, verify each of that tier's rules (parallel subagents when possible).
Reading the code is not enough. Many rules have an objective threshold or a validator that CI enforces — run the tool and read its result instead of inferring from the source. Report the measured number or the tool's verdict; when a rule is a judgment from reading code, say so; when you could not check it, mark it unverified rather than implying a pass.
1. Understand the rule
Fetch the rule doc from https://raw.githubusercontent.com/home-assistant/developers.home-assistant/refs/heads/master/docs/core/integration-quality-scale/rules/{rule_name}.md and read the exact requirement — the wording matters (e.g. test-coverage is "Above 95% test coverage for all integration modules": per module, strictly above 95%). Note the tier the rule belongs to, its required patterns, and its exemption criteria.
2. Inspect the integration
Verify the code as it currently is (local working tree, or a checked-out PR head), not the base branch. In homeassistant/components/<domain>, read manifest.json (declared quality_scale tier), quality_scale.yaml (each rule's done/todo/exempt), and the modules and tests/components/<domain> relevant to the rule.
Other sources: the library on PyPI (https://pypi.org/pypi/<package>/json); and the integration docs, resolved in this order — the docs change under review, its linked docs PR, the next branch, then the current branch of home-assistant.io (.../home-assistant.io/refs/heads/<branch>/source/_integrations/<domain>.markdown). Docs for a tier bump usually land on next or a docs PR, so current alone is often stale.
3. Which rules to verify
- Tier bump (the
quality_scalevalue inmanifest.jsonchanges): verify every rule from Bronze up to the target tier, from scratch — do not trust the existingdone/exemptmarks. - Rule status changes, same tier (flips in
quality_scale.yaml, or a new scorecard): verify every rule whose status the diff changes, in any direction. A revert totodoat or below the declared tier breaks the tier claim. - Code change only (no
quality_scale.yamlor tier change): verify the changed code still satisfies the rules in force at the integration's current tier. Map the diff to the rules it implicates and check those — the bar is no regression. - A single requested rule: verify just that rule.
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.
- 19d ago Changed · -12 lines b4b86e877949
- 1mo ago First seen · 53 lines · 84 tokens per session scan A 20a02414096a
ha-quality-scale-verify is a skill published in the GitHub repository home-assistant/core (91,801 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 1,627 once invoked, about $0.0003 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.
Other skills, from other repositories
iot-skills
Use when developing IoT solutions — Raspberry Pi Pico (RP2040) GPIO/I2C/Wi-Fi/MQTT/sensors in MicroPython, building low-code data flows with Node-RED, running a local-first home automation platform with Home Assistant, or compiling ESP32/ESP8266 firmware from YAML with ESPHome. Index of 4 skills: KE3036 Keyes Pico…
iot-developer
Expert in IoT development, microcontrollers, sensors, and MQTT protocols.
edge-iot
Edge computing, IoT protocols, and embedded systems integration.
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, attach a workspace, defer capability…
implementing-mcp-tools
Guide for exposing PostHog product endpoints as MCP tools. Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML configs, or writing serializers with good descriptions. Covers the full pipeline from Django serializer to generated TypeScript tool handler.
adopting-generated-api-types
Use when migrating frontend code from manual API client calls (api.get, api.create, api.surveys.get, api.dashboards.list, new ApiRequest()) and handwritten TypeScript interfaces to generated API functions and types. Triggers on files importing from lib/api, files with api.get . , manual interface definitions that…