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 tonylofgren/aurora-smart-home --skill ha-dashboard-designgit clone --depth 1 https://github.com/tonylofgren/aurora-smart-homeWrote 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/tonylofgren/aurora-smart-home/ha-dashboard-design)<a href="https://agentmods.dev/skills/tonylofgren/aurora-smart-home/ha-dashboard-design"><img src="https://agentmods.dev/badge/skills/tonylofgren/aurora-smart-home/ha-dashboard-design/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/tonylofgren/aurora-smart-home/ha-dashboard-design"><img src="https://agentmods.dev/badge/skills/tonylofgren/aurora-smart-home/ha-dashboard-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00141 | $0.01669 |
| Opus 5.5 | $0.00056 | $0.00668 |
| Sonnet 5.5 | $0.00028 | $0.00334 |
| Haiku 4.5 | $0.00014 | $0.00167 |
Grade A, and why
HA Dashboard Design 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 4d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Dashboard Design
Create a dashboard around the user's visual direction. Home Assistant supplies entities and actions; its default card appearance is optional. The nine styles below are references, not a menu the user must choose from.
Choose the design approach
For an original theme, a reference screenshot, a wall panel, or a request that should not look like Home Assistant, read Custom dashboards. Start with the intended screen, the information hierarchy, and the user's aesthetic. Reuse supplied preferences; ask only for missing details that change the design.
- Theme only: preserve familiar cards and change colors, typography and surfaces.
- Custom composition: reshape the whole view with CSS Grid, button-card templates and original navigation. This is the usual choice for an app-like dashboard.
- Custom card or panel: use a maintained web component when the interaction cannot be expressed by existing cards. Do not force an independent frontend on a theme request.
Working starter: Editorial dashboard, with separate theme and dashboard files, responsive layouts and replaceable entity placeholders.
Optional building blocks (install only those used)
- card-mod - CSS styling for supported cards, with shadow-DOM limits
- button-card - fully customizable button cards
- mini-graph-card - beautiful graphs (optional)
- mushroom - modern card suite (optional, used in some styles)
- layout-card - explicit responsive CSS Grid layouts (used by the editorial starter)
Available Styles
| Style | Feel | Best for |
|---|---|---|
glassmorphism |
Frosted glass, depth, blur | Dark wallpaper backgrounds |
dark-minimal |
Pure black, clean typography | Focus, productivity |
material-you |
Google Material 3, dynamic color | Modern, familiar |
nordic |
Light, airy, Scandinavian | Bright rooms, day use |
neon-cyberpunk |
Glow effects, vivid neon | Night mode, wow factor |
warm-home |
Amber/orange, cozy | Living rooms, evening |
soft-pastel |
Soft pinks, lilac, mint | Friendly, family homes |
luxury-gold |
Deep navy + gold accents | Premium, sophisticated |
retro-terminal |
Green phosphor, monospace | Geek aesthetic |
What ships with it
14 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.
- assets/custom-editorial/dashboard.yaml 5.5 KB
- assets/custom-editorial/README.md 3.6 KB
- assets/custom-editorial/theme.yaml 666 B
- references/custom-dashboards.md 5.3 KB
- references/dark-minimal.md 9.8 KB
- references/glassmorphism.md 12 KB
- references/image-prompts.md 7.3 KB
- references/luxury-gold.md 7.2 KB
- references/material-you.md 8.7 KB
- references/neon-cyberpunk.md 13 KB
- references/nordic.md 9.0 KB
- references/retro-terminal.md 9.1 KB
- references/soft-pastel.md 6.3 KB
- references/warm-home.md 5.6 KB
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.
- 4d ago Changed · +33 lines · +16 tokens per session ac10f126335c
- 1mo ago First seen · 131 lines · 125 tokens per session scan A 6d87c5ceb399
HA Dashboard Design is a skill published in the GitHub repository tonylofgren/aurora-smart-home (109 stars, last pushed 5d ago), licensed MIT. It adds 141 tokens to every session and 1,669 once invoked, about $0.0006 per session on Opus 5.5. 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
bat-story-eval
Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.
contrib-pr-review
Review a contribution PR for safety, quality, and readiness. Checks for security concerns, test coverage, size appropriateness, and intent alignment. Use when reviewing external contributions.
bat-adhoc
Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs.
contributors-update
Find merged PR authors missing from README and update the contributors list after approval.
issue-to-pr-resolver
Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean. Use when you need to fully implement a GitHub issue from start to merge-ready. Triggers on "implement issue", "resolve…
my-pr-checker
Manage your own GitHub pull requests — check CI status, inline review comments, PR-level comments, resolve review threads, fix issues, and iterate until all checks pass and threads are resolved. Use for managing your own PRs (not external contributions). Triggers on "check my PR", "check PR", "/my-pr-checker ".