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 makifbaysal/tasktrooper --skill vite-tailwind-radixgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/vite-tailwind-radix)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/vite-tailwind-radix"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/vite-tailwind-radix/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/makifbaysal/tasktrooper/vite-tailwind-radix"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/vite-tailwind-radix.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 | $0.00044 | $0.01597 |
| Opus 5.5 | $0.00018 | $0.00639 |
| Sonnet 5.5 | $0.00009 | $0.00319 |
| Haiku 4.5 | $0.00004 | $0.00160 |
Grade A, and why
vite-tailwind-radix 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tailwind, Radix, No Custom CSS
Overview
Styling is Tailwind-first with a shared token system, on top of Radix/shadcn primitives. Custom CSS and hand-rolled interactive widgets are what this skill exists to prevent — they fragment the design and re-introduce accessibility bugs the primitives already solved.
Core principle: Avoid custom CSS. Style with Tailwind utilities and the design tokens; reach for the existing shadcn primitive before building an interactive widget, and its built-in variant before a custom class.
Rules
- Tailwind v4 by default. New Vite projects use
@tailwindcss/viteand@import "tailwindcss", with tokens defined in@theme/:rootin the main CSS file. A repo already on Tailwind v3 keepstailwind.config— checkpackage.jsonand follow what the repo already uses, don't migrate it mid-task. - Tailwind utilities, not custom CSS. No new
.cssfiles, no<style>blocks, no bespoke class names. Compose utilities; usecn()for conditional variants. An inlinestyle={{}}object is allowed ONLY for a genuinely dynamic, computed value (a measured width, a transform) — tag it// ui-guard-allow: <reason>if the project runs ui-guard. - Built-in variants before custom styles.
<Button variant="outline">,size="sm"— notclassName="border border-input bg-transparent hover:bg-accent". - Semantic tokens, not raw values.
bg-primary,text-muted-foreground,border-border— neverbg-blue-500,text-gray-600, or a hex code. No arbitrary pixel values (w-[327px]) — use the scale. classNameis for layout, not restyling.w-full,max-w-md,self-end,col-span-2are fine (spacing between siblings comes from the parent'sgap, not margins on the child); overriding a component's own colour or typography throughclassNameis not — change the variant or the token instead.gap-*overspace-x-*/space-y-*.flex flex-col gap-4, notspace-y-4.size-*for square elements.size-10, notw-10 h-10.- No manual
dark:colour overrides — the semantic tokens already carry both themes. - No manual z-index on overlay primitives.
Dialog,Sheet,Drawer,Popover,DropdownMenu,Tooltipmanage their own stacking; never addz-50/z-[999]to them. The fixed z-scale —z-10raised content,z-20sticky header,z-30dropdown/popover,z-40overlay,z-50modal/toast — is for your own layered content, never arbitraryz-[…]. - Build on the primitives. Dialog, Dropdown, Tooltip, Popover, Tabs, etc. come from the Radix primitives wrapped in
components/ui— never hand-roll one that exists (you'll lose focus trapping, keyboard nav, and ARIA).Dialog/Sheet/Draweralways render aTitle(visually hidden withsr-onlyif the design doesn't show one). - Forms use the Field pattern.
Field/FieldGroup(or the project's ownFormFieldmolecule) — not a rawdivwithspace-y-*. Validation state isdata-invalidon theField,aria-invalidon the control. - Use the component for the job, not a styled div.
Emptyfor empty states,Skeletonfor loading (no customanimate-pulsediv),AlertDialogfor destructive confirmation,Spinnercomposed intoButtonfor a pending submit. - Match neighbors. Before styling a new screen, look at an adjacent one and reuse its patterns and token classes.
npm run buildmust stay green — a TypeScript error or failed build is a broken task, not a warning.
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 · 82 lines · 44 tokens per session scan A 6aed64a002b9
vite-tailwind-radix is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,597 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.
webgl-liquid-metal
A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…
webgl-particle-galaxy
A real-time particle galaxy — tens of thousands of additive-blended GPU points spiraling around a bright core, their orbits solved entirely in the vertex shader (from glVertexID), so the whole cloud draws in one call. Rendered as a single self-contained index.html. Use when the brief asks for a "particle field"…
webgl-horizontal-parallax
A horizontal-scroll WebGL gallery (Three.js): frames glide sideways with lerp smoothing and each image parallaxes its texture (UV shift) by its position in the viewport.