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 rules/virtuslab-open-source/astro-strapi-starter/tailwind-shadcngit clone --depth 1 https://github.com/VirtusLab-Open-Source/astro-strapi-starterWrote 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/rules/virtuslab-open-source/astro-strapi-starter/tailwind-shadcn)<a href="https://agentmods.dev/rules/virtuslab-open-source/astro-strapi-starter/tailwind-shadcn"><img src="https://agentmods.dev/badge/rules/virtuslab-open-source/astro-strapi-starter/tailwind-shadcn.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 | $0.00000 | $0.00368 |
| Opus 5 | $0.00000 | $0.00184 |
| Sonnet 5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
tailwind-shadcn 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 5d 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.
What it actually says
Tailwind CSS 4 and shadcn-style components (this starter)
-
Tailwind v4 is applied via
@tailwindcss/viteinastro.config.mjs. Global entry:src/styles/global.csswith@import 'tailwindcss',@theme, and shadcn theme imports. Prefer utilities and existing CSS variables from that file; extend tokens in@themewhen adding project-wide design changes. -
Shadcn-style React components live in
src/components/ui/and are generated from shadcn/ui usingcomponents.json(New York style,src/styles/global.css). Use the shadcn CLI to add or update components; do not hand-copy unrelated project snippets. -
Class merging for React: use
cn()from@/lib/utils(clsx + tailwind-merge). For Astro, use regularclassstrings orclsxwhere the starter already does. -
Astro + Tailwind showcase components and React shadcn elements coexist; keep spacing, color, and radius consistent with the design tokens in
global.cssso the UI looks unified. -
This repo does not include proprietary Tailwind Insiders “agent rules.” Follow public Tailwind v4 documentation and the patterns already in the codebase.
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.
- 5d ago First seen · 18 lines · 0 tokens per session scan A 52bbd8a896c2
tailwind-shadcn is a cursor rule published in the GitHub repository VirtusLab-Open-Source/astro-strapi-starter (21 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 368 tokens. 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 cursor rules, from other repositories
nuxt-overlay-slot
Overlay 元件（USlideover/UModal/UDrawer）body 必用 #body slot、寬度必用 :ui prop 覆寫.
hatch3r-design-system-detection
Mandatory detection of existing design tokens, theme primitives, and component library before AI agents author new UI components.
nuxt-ui-mcp
Nuxt UI v3/v4 component / composable / theming / icon 必走 nuxt-ui-remote MCP；ban prescriptive synthesis.
nuxt-review-bans
🔒 LOCKED — managed by clade Source: rules/modules/framework/nuxt/nuxt-review-bans.md Edit at: $CLADEHOME Local edits will be reverted by the next sync. -->.
nuxt-ui-conventions
實作 Nuxt UI component 前強制 grep 既有同語義用法、複製多數 props 組合；慣例一致性在實作時對齊，不等 review 才抓.
nuxt-error-localization
UI 錯誤訊息必須本地化（繁體中文），禁止直接顯示原始英文 error code 或 message.