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-panel-authorgit 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-panel-author)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-panel-author"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-panel-author/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-panel-author"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-panel-author.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 | $0.00228 | $0.03027 |
| Opus 5 | $0.00114 | $0.01514 |
| Sonnet 5 | $0.00046 | $0.00605 |
| Haiku 4.5 | $0.00023 | $0.00303 |
Grade A, and why
ha-panel-author 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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Panel Author
Spec: spec/claude/ha-panel-author/en.md (EN canonical) / spec/claude/ha-panel-author/de.md (DE translation).
This skill is the senior panel-developer of the Lovelace/frontend family. Where ha-panel-add mechanically scaffolds one custom panel against a single spec, this skill develops a panel end-to-end to production grade: it picks the right delivery shape, wires the data channel, honours layout/responsive/performance/theming discipline, and holds the result to the whole relevant spec set — then reuses ha-panel-add for the base scaffold rather than reinventing it.
Why this is a skill, not an agent
- Human-visible senior surface — the user describes a need and reads back the delivery-shape decision, the build plan, the generated code, and a multi-spec conformance report; a skill keeps that judgement on the visible command surface, like the sibling
ha-lovelace-solution. - Mid-flow interactivity — the delivery-shape decision (custom panel vs. panel-mode view vs. custom view), the data-source/backend decision, and plan approval are per-run dialogues the user must see and approve before generation.
- Orchestrator-leaning — it dispatches
ha-panel-add(base scaffold) and, when a backend endpoint is needed,ha-websocket-command-add; the skill-orchestrates-skill default keeps the entry point in skill form. - Counter-dimension considered: the develop→validate→iterate loop could be an agent, but the shape decision, the backend call-out, and the report belong in the user's working context; skill wins.
When this skill activates
Use this skill when the user wants a complete, production-grade panel built with senior judgement — not just a bare scaffold: a full-page sidebar page, a single-card panel-mode view, or a custom-view layout container, developed with correct data access, layout/responsive discipline, and a spec-conformance report.
When NOT to activate
- just the minimal one-panel scaffold (bare custom element +
panel_customentry, no senior development) →ha-panel-add - a single custom card →
ha-lovelace-card-scaffold/ha/lovelace-card-patterns - a multi-artifact frontend solution across the whole Lovelace family (card + editor + feature + badge + …) →
ha-lovelace-solution(which MAY dispatch this skill for the panel part) - a programmatic dashboard/view strategy →
ha-strategy-add/ha/lovelace-strategies - the Python custom-integration backend (the WebSocket-command host, own protocol, config flow) →
ha-integration-scaffold - deploying/importing into a running HA instance → out of scope (generation only)
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.
- 10d ago First seen · 128 lines · 228 tokens per session scan A cb34148447e9
ha-panel-author is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 228 tokens to every session and 3,027 once invoked, about $0.0011 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
cache-components
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). PROACTIVE ACTIVATION: Use this skill automatically when working in Next.js projects that have cacheComponents: true in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best…
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
flutter-development
Cross-platform development with Flutter and Dart for iOS, Android, Web, Desktop, and embedded. Use when building Flutter apps, implementing Material/Cupertino design, or optimizing Dart code.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.
generic-react-ux-designer
Professional UI/UX design expertise for React applications. Covers design thinking, user psychology (Hick's/Fitts's/Jakob's Law), visual hierarchy, interaction patterns, accessibility, performance-driven design, and design critique. Use when designing features, improving UX, solving user problems, or conducting design…