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 denysdovhan/agents --skill home-assistant-cardgit clone --depth 1 https://github.com/denysdovhan/agentsWrote 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/denysdovhan/agents/home-assistant-card)<a href="https://agentmods.dev/skills/denysdovhan/agents/home-assistant-card"><img src="https://agentmods.dev/badge/skills/denysdovhan/agents/home-assistant-card/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/denysdovhan/agents/home-assistant-card"><img src="https://agentmods.dev/badge/skills/denysdovhan/agents/home-assistant-card.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 | $0.00078 | $0.00788 |
| Opus 5 | $0.00039 | $0.00394 |
| Sonnet 5 | $0.00016 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
home-assistant-card 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 12d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Assistant Card Skill
Use this skill for Home Assistant custom card development. Custom cards are Web Components; any framework that defines custom elements can work. Lit and helper libraries are optional unless the repo already uses them.
This is separate from Python integrations, automations, scripts, helpers, and ordinary dashboard YAML. Use those skills unless the work changes a custom card package, registration, editor, or card usage contract.
Start With Current Docs
Fetch current markdown from the Home Assistant developers docs repository before changing card APIs. All doc paths in this skill's references are relative to this base URL — prepend it when fetching:
https://raw.githubusercontent.com/home-assistant/developers.home-assistant/master/docs/
Use rendered pages on developers.home-assistant.io only as secondary reading. Fetch only relevant files, and do not copy Home Assistant docs into generated skill or repo files.
Use references/frontend-docs.md as the docs routing index. The most important source is frontend/custom-ui/custom-card.md.
Local Workflow
- Inspect local instructions first:
AGENTS.md, package scripts, README, HACS metadata, build config, source entrypoints, card/editor files, translations, and release notes. - Preserve the existing architecture and framework. Do not convert frameworks, add helper libraries, or add build tooling unless required.
- Read the relevant reference:
references/card-workflow.mdfor repo structure and validation,references/card-patterns.mdfor card API patterns,references/card-examples.mdfor card/editor examples, andreferences/frontend-docs.mdfor current docs. - Keep diffs surgical. Work with dirty worktrees; never revert unrelated edits.
- Prefer explicit config validation/defaulting in
setConfigor a local helper. AbuildConfighelper is a useful pattern, not a requirement. - Use Home Assistant frontend data and APIs deliberately:
hass.states,hass.localize,hass.callService, custom events, card sizing, editor APIs, and resource registration. - Handle unavailable or missing entities without crashing the whole dashboard.
- For card editors, dispatch
config-changedwith the full updated config and preserve existing editor UX. - Run repo-local validation, usually
npm test,npm run lint,npm run build, or equivalent scripts. For dependency changes in public repos, keep lockfiles and package-manager config free of private or machine-local registry URLs.
What ships with it
7 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.
- 12d ago First seen · 50 lines · 78 tokens per session scan A 242c6296cb16
home-assistant-card is a skill published in the GitHub repository denysdovhan/agents (17 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 788 once invoked, about $0.0004 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
slop-eval
Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…
astro-sites-manager
Comprehensive skill for building, migrating, and maintaining Astro v7 projects. Covers best practices from the official AGENTS.md, the v6→v7 migration path, validation of breaking/deprecated patterns, AI-enhanced dev server usage (background mode, JSON logging), advanced routing with src/fetch.ts, route caching…
lingui-best-practices
Implement internationalization with Lingui in React and JavaScript applications. Use when adding i18n, translating UI, working with Trans/useLingui/Plural, extracting messages, compiling catalogs, or when the user mentions Lingui, internationalization, i18n, translations, locales, message extraction, ICU…
migrate-i18next-to-lingui
Migrate i18next/react-i18next projects to Lingui. Use when the user wants to replace i18next, react-i18next, useTranslation, i18n.t(), Trans i18nKey, or i18next JSON catalogs with Lingui equivalents. Covers package installation, config setup, code transformation patterns, plural migration, namespace handling, and…
swc-plugin-compatibility
Diagnose and fix Lingui SWC plugin compatibility errors with Next.js, Vite, Rspack, or other SWC runtimes. Use when seeing errors like "failed to invoke plugin", "failed to run Wasm plugin transform", "Failed to deserialize program received from host", "Failed to execute SWC plugin", "out of bounds memory access", or…
lingui-framework-setup
Set up Lingui in a React framework. Use when adding Lingui to a Next.js App Router, Vite, React Router 7, Remix, or TanStack Start project, when wiring locale detection, locale-prefixed URLs, or SSR locale resolution, or when a working setup breaks after a framework or build-tool upgrade.