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 magnusoverli/opencode --skill home-assistant-dashboard-uigit clone --depth 1 https://github.com/magnusoverli/opencodeWrote 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/magnusoverli/opencode/home-assistant-dashboard-ui)<a href="https://agentmods.dev/skills/magnusoverli/opencode/home-assistant-dashboard-ui"><img src="https://agentmods.dev/badge/skills/magnusoverli/opencode/home-assistant-dashboard-ui.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 59 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00085 | $0.00941 |
| Opus 5 | $0.00043 | $0.00470 |
| Sonnet 5 | $0.00017 | $0.00188 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
home-assistant-dashboard-ui 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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboards and UI
Which mechanism this installation uses
Find out before proposing anything — the two are not interchangeable.
- Storage mode (default): dashboards live in
.storage/, which is off-limits to direct editing. Usehab dashboard:hab dashboard list,hab dashboard get <url_path>,hab dashboard create,hab dashboard view create. This is the primary path for most installations. - YAML mode:
lovelace:inconfiguration.yamlnames a dashboard file. Then it is ordinary YAML — the configuration skill's style guide andwrite_config_safeapply.
hab dashboard list tells you which dashboards exist and how they are managed.
hab dashboard get <url_path> --json gives you the current structure to modify;
read it before writing, exactly as with any config file.
Building a view
Start from what the home actually has: get_home_context for the area and its
entities, or get_areas when laying out an area-per-view dashboard. Do not
invent entity IDs — every card you write should reference an entity you have
confirmed exists.
Standard cards worth knowing: entities, tile, button, light, thermostat,
media-control, weather-forecast, history-graph, statistics-graph,
gauge, picture-elements, map, markdown, todo-list, area, and the
layout cards grid, vertical-stack, horizontal-stack, sections.
conditionalshows a card only while a condition holds — the usual way to hide something that is irrelevant most of the time.custom:cards come from HACS. Check the resource is actually installed (hab dashboard resources list, or thewww/folder) before writing one in; a missing custom card renders as an error box for the user.- card-mod styling is a custom-card feature too, and equally dependent on the resource being present.
Views take title, path, icon, type (sections, panel, masonry,
sidebar), badges, and cards. Sections view type is the current default for
new dashboards and behaves differently from masonry — check which one the
existing dashboard uses before adding cards to it.
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.
- 8d ago First seen · 85 lines · 85 tokens per session scan A add749c00b27
home-assistant-dashboard-ui is a skill published in the GitHub repository magnusoverli/opencode (380 stars, last pushed 6d ago), licensed Unlicense. It adds 85 tokens to every session and 941 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
codegen-react
Scaffold and iterate on Vite + React applications.
pdf-press
Teaches agents how to generate Markdown, HTML (with embedded SVG), and Mermaid content that renders beautifully to multi-page PDF via writepdf, with proper page breaks, compact professional layouts, brand and domain-adaptive color schemes, multi-column support for scientific papers, magazine-style editorial documents…
go-bulma
Scaffold the Bulma CSS framework into a Go web app with embedded assets for zero-dependency binaries. Use when building an HTML UI with a classes-based CSS framework and no Node toolchain.
legacy-circuit-mockups
Breadboard circuit mockups via HTML5 Canvas. Use when creating circuit layouts, visualizing 6502/retro electronics components, drawing breadboard diagrams, or designing vintage computer schematics with discrete parts.
web-app-creator
Build webapps that integrate with Meta Aria Gen2 (Nebula) smart glasses, usable by any agent that supports skills (Manus, Claude Code, etc.). macOS only — the backend launcher and auto-open browser hooks are written for macOS; Windows and Linux are not supported. Covers the full Web App Creator stack: real-time sensor…
s3d-apps
S3D Apps Builder — build custom embedded mini-apps (client-side JS/HTML) that run inside the SkyCiv Structural 3D (S3D) web application, reading/writing the live model and interacting with the 3D viewport and element selection.