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-badge-addgit 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-badge-add)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-badge-add"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-badge-add/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-badge-add"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-badge-add.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 | $0.00217 | $0.02189 |
| Opus 5 | $0.00109 | $0.01094 |
| Sonnet 5 | $0.00043 | $0.00438 |
| Haiku 4.5 | $0.00022 | $0.00219 |
Grade A, and why
ha-badge-add 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 11d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Badge Add
Spec: spec/claude/ha-badge-add/en.md (EN canonical) / spec/claude/ha-badge-add/de.md (DE translation).
Why this is a skill, not an agent
- Human-visible augmentation surface — the user describes a status display and reads back the badge element, the registration entry, and the conformance report; a skill keeps this on the visible command surface, like the sibling frontend skill
ha-lovelace-card-scaffold. - Mid-flow interactivity — the
badge_typetag-name decision and the "graphical editor yes/no" choice are per-run dialogues the user approves before generation. - Bounded, inline generation — one custom-element module plus its
window.customBadgespush and optional editor fit inline; no isolated agent context is needed. - Counter-dimension considered: the draft→validate loop could be an agent, but the tag-name and editor-depth decisions belong in the user's working context; skill wins.
When this skill activates
Use this skill to add one custom badge — the small status widget at the head of a Lovelace view — to an existing frontend module (an integration's www/ folder or a standalone Lovelace module).
When NOT to activate
- a custom card (the larger content building block) →
ha-lovelace-card-scaffold/ha/lovelace-card-patterns - a tile card feature →
ha/lovelace-card-features - a dashboard strategy →
ha/lovelace-strategies - the
config-changedgraphical-editor detail pattern →ha/lovelace-card-editor - deploying/importing into a running HA instance → out of scope
Hard rules
- One badge, one run. No multi-badge batches.
- Read
spec/ha/lovelace-badges/en.mdfirst. Do not generate from memory. - Custom element, no React. Define the badge as a subclass of
HTMLElement(orLitElement) and register it viacustomElements.define("<badge-type>", <BadgeClass>); the tag name becomes the badge typecustom:<badge-type>. Never use React as the rendering framework — custom elements and React are not compatible in HA badges. setConfigcontract. ImplementsetConfig(config); reject an invalid configuration withthrow new Error("...")— HA catches it and renders an error badge.hasssetter. Implement thehassproperty as a setter; the badge updates itself to the latest state on every set. Read the consumed entity fromhass.states[entityId]and render a sensible fallback (e.g.unavailable) when it is missing (seespec/ha/frontend-data-api/en.md).- Picker registration. Push an entry into
window.customBadges(window.customBadges = window.customBadges || []; window.customBadges.push({...})) with at least the requiredtypeandname;description/documentationURL/previeware optional (previewdefaults tofalse). - Graphical editor is optional. Add the static
getConfigElement()/getStubConfig()only when an editor is wanted; do not spell out theconfig-changedevent pattern here — that is governed byspec/ha/lovelace-card-editor/en.md. - Document the wiring. Reference the badge via
type: "custom:<badge-type>"in a view'sbadges:list and add amoduleresource with the badge module URL (typically/local/<badge-name>.js); note the HA restart needed after first creating thewwwfolder. - Name per
spec/ha/naming-conventions/en.mdand verify HA internals against the official docs (seespec/ha/upstream-docs-verification/en.md). - Honour the layout-antipattern catalogue (
spec/ha/lovelace-layout-antipatterns/en.md). Badges do not render inpanelorsidebarviews (A2) — when documenting the wiring, note the target view must support badges (Sections, Masonry), not panel/sidebar.
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.
- 11d ago First seen · 112 lines · 217 tokens per session scan A 03d4c3d6afc9
ha-badge-add is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 217 tokens to every session and 2,189 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-feature-developer
Guide feature development for React applications with architecture focus. Covers Zustand/Redux patterns, IndexedDB usage, component systems, lazy loading strategies, and seamless integration. Use when adding new features, refactoring existing code, or planning major changes.