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-lovelace-card-scaffoldgit 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-lovelace-card-scaffold)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-lovelace-card-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-lovelace-card-scaffold/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-lovelace-card-scaffold"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-lovelace-card-scaffold.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 | $0.00126 | $0.01625 |
| Opus 5 | $0.00063 | $0.00813 |
| Sonnet 5 | $0.00025 | $0.00325 |
| Haiku 4.5 | $0.00013 | $0.00162 |
Grade A, and why
ha-lovelace-card-scaffold 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Lovelace Card Scaffold
Spec: spec/claude/ha-lovelace-card-scaffold/en.md (EN canonical) / spec/claude/ha-lovelace-card-scaffold/de.md (DE translation).
Why this is a skill, not an agent
- Mid-flow interactivity (decisive): card name, target entities, and registration path are confirmed with the operator before scaffolding; corrections iterate in the same thread.
- Quick, targeted change: one new file under
www/plus registration — main-conversation territory per the change-scope dimension. - Counter-dimension considered: the lifecycle boilerplate is template-like and self-contained (agent bias), but the scaffold is the first step of card development the conversation continues, so a report boundary would only add friction.
When this skill activates
Use this skill when the user wants to add a custom Lovelace card to an existing HA Custom Integration — a vanilla-JS card living under custom_components/<domain>/www/, auto-registered through __init__.py.
When NOT to activate
- greenfield integration setup →
ha-integration-scaffold - TypeScript or Lit cards → separate spec planned
- card removal → manual code edit
- multi-card scaffold in one call → call once per card
Hard rules
- Never set hard-coded hex colours. Use HA CSS custom properties (
var(--primary-text-color)etc.) so the card respects the active theme. - Always set
cache_headers=Falsein the StaticPathConfig. Otherwise updated cards stay stale for cached browsers. - Always include
getCardSize,getGridOptions,setConfig, andgetStubConfig. Sections-layout and the card picker depend on them. - Always perform entity-change detection in
set hass. Re-rendering on every HA state tick burns CPU for nothing. - Never reference external CDN assets. Cards run offline-capable.
- Never ask the user to add Lovelace resources by hand. Auto-registration is the contract.
- Name the element, class, and file per
ha/naming-conventions. The custom-element tag iskebab-casewith at least one hyphen, namespaced by the integrationdomain(<domain>-card); if a config editor element is provided, its tag is<tag>-editor; the class isPascalCaseending inCard/CardEditor; the source file iskebab-case; the cardname/descriptionare English (seespec/ha/naming-conventions/en.md). - 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). - Honour the layout-antipattern catalogue. Conform to
spec/ha/lovelace-layout-antipatterns/en.md: defaultgrid_options.columnsto a multiple of 3 (3/6/9/12; B3); never hardcode a fixed outer pixel width or absolutely position the card to force its grid footprint (fixed inner-content heights are fine —rows: "auto"measures them; B4); setcolumns: "full"only when the card truly spans the section (B4); never use React as the render layer (B5).
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 · 105 lines · 126 tokens per session scan A 2602dec2d98c
ha-lovelace-card-scaffold is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 1,625 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
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.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…