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 agentmods add skills/pinebasedev/svelteflare/ui-and-themenpx skills add pinebasedev/svelteflare --skill ui-and-themegit clone --depth 1 https://github.com/pinebasedev/svelteflareWrote 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/pinebasedev/svelteflare/ui-and-theme)<a href="https://agentmods.dev/skills/pinebasedev/svelteflare/ui-and-theme"><img src="https://agentmods.dev/badge/skills/pinebasedev/svelteflare/ui-and-theme.svg" alt="Measured on agentmods" 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 | $0.00159 | $0.03790 |
| Opus 5 | $0.00079 | $0.01895 |
| Sonnet 5 | $0.00032 | $0.00758 |
| Haiku 4.5 | $0.00016 | $0.00379 |
Grade A, and why
ui-and-theme 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 3d 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI and Theme
Build all UI from shadcn-svelte components and the shared theme system. The theme includes semantic CSS variables in packages/ui/src/global.css and the visual implementations in packages/ui/src/components/**/*.svelte. Never use raw hex/rgb colors, Tailwind palette classes, or arbitrary color values — the app has a founder-approved theme, and every screen must look like it belongs to it.
Allowed vs forbidden styling
| ❌ Never | ✅ Instead |
|---|---|
bg-blue-500, text-green-500, bg-zinc-900, bg-white, text-black |
bg-primary, text-primary, bg-card, bg-background, text-foreground |
bg-[#1e40af], text-[oklch(0.6 0.2 30)], border-[rgb(30,40,50)] |
a semantic token utility: bg-secondary, border-border, … |
style="color: #333", color: red in <style> blocks |
token utilities, or var(--muted-foreground) etc. in CSS |
text-green / bg-amber (token doesn't exist) |
check packages/ui/src/global.css for real tokens first |
| success/warning states via palette colors | text-primary, text-destructive, text-muted-foreground, bg-primary/10 |
Non-color arbitrary values (w-[420px], grid-cols-[1fr_2fr]) are fine. Lint enforces the color rules (theme/no-hardcoded-colors) and fails just check — if lint flags a color, replace it with a token; never suppress the error.
Stack at a glance
| Layer | Detail |
|---|---|
| Component library | shadcn-svelte (style: vega), built on bits-ui primitives |
| CSS framework | Tailwind CSS v4 (no tailwind.config.js — all config lives in CSS) |
| Token system | CSS custom properties in packages/ui/src/global.css, bridged via @theme inline |
| Dark mode | Class-based (.dark on <html>), managed by mode-watcher |
| Icons | unplugin-icons — import as ~icons/lucide/<name> |
| Fonts | Inter Variable (sans), Geist Mono (mono) |
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.
- 3d ago First seen · 356 lines · 159 tokens per session scan A 591e205bedbd
ui-and-theme is a skill published in the GitHub repository pinebasedev/svelteflare (47 stars, last pushed 1mo ago), licensed MIT. It adds 159 tokens to every session and 3,790 once invoked, about $0.0008 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
diceui
Build complex, accessible UI components using DiceUI — combobox, tags-input, sortable, kanban, data-table, file-upload, color-picker, and 40+ more. Use when the user wants to add any DiceUI component, mentions @diceui packages, asks for complex interactive components like combobox, sortable lists, kanban boards…
ui-ux-design-best-practices
UI/UX polish, component design, animation decisions, and Tailwind v4 patterns for making interfaces feel right. Use when reviewing, writing, or refactoring UI code involving animations, transitions, CSS transforms, gestures, Tailwind utility classes, or interactive component behavior. Triggers on tasks involving…
review-tailwind
Tailwind CSS v4 review (CSS-first config, Vite plugin integration, better-tailwindcss lint rules) against current official Tailwind best practices. USE WHEN: user runs /review-tailwind or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or implementing features.
changelog-writer
This skill should be used when the user asks to "add a changelog entry", "write changelog", "audit changelog", "review changelog", "check changelog entries", or is editing docs-mintlify/changelog.mdx. Enforces a consistent, reader-facing voice and cuts implementation trivia.
add-media
This skill should be used when the user asks to "add a movie", "add a vinyl", "add to my collection", "add physical media", "add a Blu-ray", "add a CD", or "bought these records". It handles both movies (via TMDb/Trakt) and music (via Discogs).
media-search
This skill should be used when the user asks to "search for a movie", "find a record on Discogs", "look up a film", "search TMDb", "search Discogs", "what's the TMDb ID for", "what's the Discogs ID for", or wants to look up media metadata before adding it to the collection.