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-card-editor-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-card-editor-add)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-card-editor-add"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-card-editor-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-card-editor-add"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-card-editor-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 | $0.00214 | $0.02106 |
| Opus 5 | $0.00107 | $0.01053 |
| Sonnet 5 | $0.00043 | $0.00421 |
| Haiku 4.5 | $0.00021 | $0.00211 |
Grade A, and why
ha-card-editor-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 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Card Editor Add
Spec: spec/claude/ha-card-editor-add/en.md (EN canonical) / spec/claude/ha-card-editor-add/de.md (DE translation).
Why this is a skill, not an agent
- Human-visible augmentation surface — the user names an existing card and reads back the editor element, the
ha-formschema, 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 editor field set, the selector choices, and the
computeHelper/assertConfigdecisions are a per-run dialogue the user approves before generation. - Bounded, inline generation — one editor element plus the two card hooks (
getConfigElement,getStubConfig) and thecustomElements.defineregistration fit inline; no isolated agent context is needed. - Counter-dimension considered: the draft→validate loop could be an agent, but the field/selector decisions belong in the user's working context; skill wins.
When this skill activates
Use this skill to add one ha-form-based visual configuration editor to an existing custom Lovelace card — the editor LitElement, the card's static getConfigElement() and static getStubConfig(), and the customElements.define registration.
When NOT to activate
- scaffolding the card itself (file layout,
set hass, render, registration) →ha-lovelace-card-scaffold - base card-level patterns and portfolio house style →
ha/lovelace-card-patterns - entity-selector filtering (domain / device-class / supported-features) →
ha/lovelace-card-entity-selector - deploying/importing into a running HA instance → out of scope
Hard rules
- One editor, one run. No multi-editor batches.
- Read
spec/ha/lovelace-card-editor/en.mdfirst. Do not generate from memory. - Existing card required. The card must already exist and be registered via
customElements.define. If it does not exist, point atha-lovelace-card-scaffoldand abort. If it already carries an editor hook (getConfigElementorgetConfigForm), abort rather than add a second. getConfigElementcontract.static getConfigElement()on the card returnsdocument.createElement("<domain>-<card>-editor"); that element is registered beforehand viacustomElements.define, in lowercase kebab-case with an integration-domain prefix.- Editor is a
LitElement. It implementssetConfig(config)and accepts thehassproperty as a setter. This skill's chosen surface isha-form-driven: arender()over<ha-form>with.hass,.data(the current config),.schema(a list, one entry per field withnameand preferablyselector), and.computeLabel. Note that<ha-form>inside agetConfigElementcustom element is this skill's implementation choice, not mandated byha/lovelace-card-editorfor thegetConfigElementpath (where the spec bindsha-formto the built-ingetConfigForm); verify against the official HA docs. config-changedis the sole return channel. The_valueChangedhandler dispatches aconfig-changedevent withbubbles: true,composed: true, anddetail: { config: newConfig }— never on an unchanged config, and never by mutating the config passed tosetConfig.getStubConfigwithouttype:.static getStubConfig()returns a default config without thetype:parameter; the card picker adds it itself.- Selectors preferred. Prefer selectors (
{ selector: { entity: {} } },{ selector: { text: {} } }, …) over native form types; addcomputeLabel, andcomputeHelper/assertConfigwhere the form needs them; verify selector options beyond the named ones againstha-form/types.ts. - Name per
spec/ha/naming-conventions/en.mdand verify HA internals against the official docs (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.
- 12d ago First seen · 106 lines · 214 tokens per session scan A 5e4d2f1c3df4
ha-card-editor-add is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 214 tokens to every session and 2,106 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.