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.
git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-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/yudefine/nuxt-supabase-starter/nuxt-ui-mcp)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/nuxt-ui-mcp"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/nuxt-ui-mcp.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 5.1 | $0.00000 | $0.02610 |
| Opus 5 | $0.00000 | $0.01305 |
| Sonnet 5 | $0.00000 | $0.00522 |
| Haiku 4.5 | $0.00000 | $0.00261 |
Grade A, and why
nuxt-ui-mcp 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 today.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nuxt UI MCP（強制走 nuxt-ui-remote）
核心命題：Nuxt UI 是 fast-moving 套件（v2 → v3 重寫、ui-pro 持續迭代、components / composables / icons 隨版本演變）。模型訓練資料對 component prop / slot / theming API 的記憶幾乎一定過時或錯誤，硬寫出來的 code 看起來合理但 runtime 會壞。nuxt-ui-remote MCP 是 Nuxt UI 官方最新 docs 的唯一可信來源。
此規則優先於個別 skill 說明與其他規則。
範圍
以下全部屬於本規則「Nuxt UI 實做」範圍，MUST 走 MCP：
@nuxt/uiv3 / v4（現行主線）— components、composables、icons、theming、app.config.ts的ui.*區塊@nuxt/uiv2（legacy，少數舊專案）@nuxt/ui-pro（Pro 版高階 component 與 template）- Nuxt UI 官方 templates（starter / dashboard / saas 等結構與配置）
判斷標準：任何會寫進 .vue / .ts / app.config.ts / nuxt.config.ts 且觸及 U* component、use* composable（Nuxt UI 自家）、ui.* theming key、@nuxt/ui* import 的內容，都算 Nuxt UI 實做。
設計階段同樣在範圍內
path scope 含 specs/plans/**/{spec,plan,design-review}.md，不是只有實作檔。因為這條規則要擋的有兩層，而它們發生在不同階段：
| 層 | 問的問題 | 發生階段 | 寫錯的代價 |
|---|---|---|---|
| API surface | 這個 prop / slot 存在嗎、叫什麼 | 寫 .vue 時 |
改幾行 |
| 元件選擇 | 這個場景該用哪些元件、怎麼組 | 寫 proposal / design 時 | 整段重寫 |
只在實作階段載入這條規則，等於只擋住便宜的那一層。元件選擇在設計文件寫下「用 USlideover 400px」的當下就定了，到實作階段才想起要查 MCP，能修的只剩 prop 名稱——架構已經不能動。
設計階段的具體要求（候選 ≥2、寫明淘汰理由）見 design skill § Step 1.9 Component Candidates。
Hard rule — API surface 層
MUST：
- 寫任何 Nuxt UI component / composable / theming / config 之前，先呼叫對應 nuxt-ui-remote MCP tool 取得當前版本的真實 API：
search-components/get-component/get-component-metadata— component prop / slot / emitsearch-composables— composable signaturesearch-icons— icon name 對照get-example/list-examples— 官方推薦寫法get-template/list-templates— template 結構get-documentation-page/search-documentation— 一般 docs / theming / configget-migration-guide— v2 → v3 / 跨版本 BC
- 取得 MCP 回傳後才寫 code；引用的 prop / slot / API 必須能對應到 MCP 回傳內容。
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.
- today Changed · +1 lines 41bfa7787eaa
- 4d ago First seen · 141 lines · 0 tokens per session scan A cb26331aa45f
nuxt-ui-mcp is a cursor rule published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,610 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 2026-09-03.
Other cursor rules, from other repositories
tailwind-shadcn
Tailwind CSS 4 + shadcn-style UI — global.css, components.json, cn(), Astro + React.
shadcn-tailwind-guide
A guide to building new components with shadcn/ui and Tailwind CSS, a utility-based system for styling interfaces.
quasar_fixes
A Quasar interface rule requiring extra SCSS fixes when using q-scroll-area or q-tooltip, including a fix for iOS scaling.
nextjs-app-router
Next.js 14+ App Router Standards.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.