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-review-bans)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/nuxt-review-bans"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/nuxt-review-bans/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/rules/yudefine/nuxt-supabase-starter/nuxt-review-bans"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/nuxt-review-bans.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 | $0.00000 | $0.02428 |
| Opus 5 | $0.00000 | $0.01214 |
| Sonnet 5 | $0.00000 | $0.00486 |
| Haiku 4.5 | $0.00000 | $0.00243 |
Grade A, and why
nuxt-review-bans 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 2d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nuxt Review Bans（實作階段強制）
核心命題：vendor/review-rules/patterns.json 定義了跨 consumer 統一的機械可檢 ban 規則，由 pre-commit hook + code-review agent 消費。但這些規則過去只在 review 階段可見（plugins/hub-core/agents/references/clade-review-rules.md），實作階段的 Claude 完全看不到 → 反覆寫出違規 → 事後才被抓。
本 rule 把 patterns.json 的 ban 清單提升到 path-scoped implementation rule，由當前 runtime 的 scoped delivery 送達全文；agent 在首次修改符合範圍的 .vue / app.config.ts 之前讀取並套用。
SoT 是
vendor/review-rules/patterns.json；本檔是它的實作階段投影。patterns.json 新增 / 修改 entry 時，本檔 MUST 同步更新。
Ban 清單
寫任何 .vue 或 app.config.ts 之前，MUST 逐條自查以下 ban：
1. UBadge size ban（ubadge-size-ban，severity: error）
禁止：<UBadge size="xs"> / <UBadge size="sm">
也禁止動態元件形式（ubadge-size-ban-dynamic）：<component :is="UBadge" size="xs"> — tag name 不是 UBadge 但 runtime 等效。
也禁止：在 app.config.ts 的 badge.defaultVariants 設 size: 'xs' 或 size: 'sm' — 效果等同 inline prop 但繞過 .vue 掃描。
理由：xs / sm 在密集表格字級過小、可讀性不足。
正解：移除 size prop（吃預設 md），或顯式寫 size="md" / "lg" / "xl"。
1b. 字級下限（text-size-floor，severity: error，layer: ratchet）
禁止：text-xs，以及任意 text-[Npx] 其中 N < 14。
理由：字級下限是 text-sm（14px）。這些畫面主要在手機上讀，而 14px 也是 iOS 不觸發輸入框 auto-zoom 的下限。
正解：改用 text-sm 或更大。真的需要次要層級就用 text-muted / font-normal 降對比，NEVER 用縮字級表達層級。
1c. 可點擊元件尺寸下限（interactive-size-floor，severity: error，layer: ratchet）
禁止：<UButton size="xs"> / <UInput size="xs"> / <USelect size="xs"> 等可點擊元件的 size="xs"（完整清單見 patterns.json 的 pattern）。
理由：比 UBadge 那條更強——UBadge 的 xs 只是讀不清楚，可點擊元件的 xs 是觸控目標過小，屬可用性缺陷。
正解：移除 size prop（吃預設）或顯式寫 sm / md / lg。密集版面要省空間就調 padding 與間距，NEVER 縮點擊目標。
這兩條是
layer: ratchet：導入時全 repo 已有存量違規，baseline（review-rules-baseline.json）凍結現況、只擋新增。NEVER 因為 ratchet 通過就以為存量已清——那是兩件事。
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.
- 2d ago Changed · +1 lines 7dd4ee41ccf8
- 6d ago First seen · 136 lines · 0 tokens per session scan A 2510ea22f161
nuxt-review-bans 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 2,428 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.
csg-design-reviewer
Audits React/CSS code against the CSG Design System. Activate when reviewing UI code, checking design compliance, or before merging frontend PRs.
development-workflow-solidjs-short
Essential linting and quality checks for SolidJS + Vite development.
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.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.