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 nolte/claude-home-assistant --skill ha-entity-description-mapgit clone --depth 1 https://github.com/nolte/claude-home-assistantWrote 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/nolte/claude-home-assistant/ha-entity-description-map)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-entity-description-map"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-entity-description-map/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/nolte/claude-home-assistant/ha-entity-description-map"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-entity-description-map.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 | $0.00111 | $0.01758 |
| Opus 5 | $0.00056 | $0.00879 |
| Sonnet 5 | $0.00022 | $0.00352 |
| Haiku 4.5 | $0.00011 | $0.00176 |
Grade A, and why
ha-entity-description-map 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA EntityDescription Mapper
Spec: spec/claude/ha-entity-description-map/en.md (EN canonical) / spec/claude/ha-entity-description-map/de.md (DE translation).
Why this is a skill, not an agent
- Per-datapoint operator decisions (decisive): mapping a datapoint table to EntityDescription tuples requires judgement calls (device class, unit, enabled-by-default) that are confirmed in the conversation, not fired off blind.
- Output flows back naturally: the generated tuple list and strings/icons entries are reviewed and iterated inline before they land.
- Counter-dimension considered: the generation step is mechanical and self-contained (agent bias), but a wrong device-class guess multiplied over a whole table is expensive — the confirm-as-you-go dialogue outweighs isolation.
When this skill activates
Use this skill when the user wants to add datapoints (sensors, binary sensors, buttons, numbers, selects, switches, calendars, todos) to an existing platform file in declarative EntityDescription form.
When NOT to activate
- greenfield scaffold →
ha-integration-scaffold - platform file missing → run scaffold first, then come back
- custom state-class definitions → manual code edit
- multi-platform generation in one call → call this skill once per platform
Hard rules
- Never overwrite existing entries. Conflict on
EntityDescription.keyaborts with the conflicting key quoted. - Never invent translations. Non-English translations land as
<TODO: translate '<EN value>'>unless the user supplies them. Skill output mentions these placeholders explicitly. - Never concretise the backend-field lookup. The skill produces the generic entity class with
entity_description.key-based access; mapping to actual coordinator data dict paths is the user's job. - Always validate
device_class/state_class/unitconsistency. Mismatches block the run with a verbose violation list. - Always update strings.json AND translations AND icons.json together. Half-augments where code is present but translations are missing are forbidden.
- Name keys and entities per
ha/naming-conventions.EntityDescription.keyandtranslation_keyaresnake_case; entity names come from thetranslation_keypath, never a hard-coded_attr_name; English display names only (seespec/ha/naming-conventions/en.md). - Emit
PARALLEL_UPDATES. The generated platform module declares a module-levelPARALLEL_UPDATESconstant (Silverparallel-updatesquality-scale rule); verify the appropriate value against the HAparallel-updatesrule page (0for coordinator-backed read-only platforms). A module without it is a quality-scale finding waiting to happen. - Validate
entity_category. A providedentity_categoryMUST be a member ofEntityCategory(CONFIG/DIAGNOSTIC); an invalid value aborts the run with the offending value quoted. - Verify HA internals against the official docs. Don't reproduce HA API signatures, lifecycle hooks, conventions, or schemas from memory — when uncertain, consult the official docs before generating or relying on it: Developer docs
developers.home-assistant, architecture/blueprint/YAML docshome-assistant.io(seespec/ha/upstream-docs-verification/en.md).
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.
- 9d ago First seen · 113 lines · 111 tokens per session scan A bd73720c84aa
ha-entity-description-map is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 1,758 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
ios-development
Comprehensive guide for building native Apple platform applications.
kotlin-multiplatform
KMP/CMP shared business logic, Compose Multiplatform, expect/actual, Ktor, SQLDelight, and platform-specific implementations. Use when building cross-platform Kotlin applications for Android, iOS, desktop, or web.
embedded-iot
Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.
migrate-to-shoehorn
Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.