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/proactive-skills.design-checkpoint)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/proactive-skills.design-checkpoint"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/proactive-skills.design-checkpoint/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/proactive-skills.design-checkpoint"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/proactive-skills.design-checkpoint.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 | $0.03990 |
| Opus 5 | $0.00000 | $0.01995 |
| Sonnet 5 | $0.00000 | $0.00798 |
| Haiku 4.5 | $0.00000 | $0.00399 |
Grade A, and why
proactive-skills.design-checkpoint 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 yesterday.
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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proactive Skills — Design Checkpoint
Reference 檔。核心規約見
proactive-skills.md。本檔聚焦動 UI 檔（pages / components / layouts /.vue/.ts）或寫design.md/spec.md時主動觸發的 design skill orchestrator、Design Review task block 模板、Design Gate 阻擋條件、跨 work item 整體性審查與非 UI exception。
Design Skill 自主觸發
觸發條件
任何 /implement task 碰到 UI 工作（建立/修改 .vue 檔案、pages、components、layouts）時，自動進入 Design Checkpoint。每一個這樣的 task 都適用，不是只有整包工作的最後一個。
Design Checkpoint 流程
Task 涉及 UI？
│
├─ 否 → 正常完成 task
│
└─ 是 → Design Checkpoint：
│
├─ 1. 檢查 PRODUCT.md（必要）+ DESIGN.md（建議）
│ PRODUCT.md 存在？→ 繼續（DESIGN.md 缺則建議跑 /impeccable document）
│ PRODUCT.md 不存在？→ 先跑 /impeccable init
│
├─ 2. 跑 /design improve [affected pages/components]
│ → 取得診斷報告 + Design Fidelity Report
│
├─ 2.5 修復所有 DRIFT 項目（fidelity check loop，max 2 輪）
│ Fidelity Score = 8/8？→ 繼續
│ 有 DRIFT/MISSING？→ 修復 → 重新檢查（max 2 輪）
│
├─ 3. 按 canonical order 執行計劃中的 design skill
│ （結構 → 視覺 → 體驗 → 韌性 → polish）
│
├─ 4. 跑 /impeccable audit [affected pages]
│ Critical > 0？→ 修復後重跑
│ Critical = 0？→ 繼續
│
└─ 5. 標記 task 完成
Design Skill 選擇指南（診斷驅動）
根據 /design improve 的診斷結果選擇，不要盲目全跑：
| UI 類型 | 常見需要的 skill | 通常不需要 |
|---|---|---|
| 表單密集（CRUD、輸入） | /impeccable layout, /impeccable clarify, /impeccable harden | /impeccable overdrive, /impeccable bolder |
| 資料表格（列表、搜尋） | /impeccable layout, /impeccable typeset, /impeccable adapt | /impeccable delight, /impeccable animate |
| 儀表板/圖表 | /impeccable colorize, /impeccable layout, /impeccable typeset | /impeccable quieter, /impeccable harden |
| 首次體驗/空狀態 | /impeccable harden, /impeccable clarify, /impeccable delight | /impeccable optimize |
| 複雜互動流程 | /impeccable animate, /impeccable clarify, /impeccable harden | /impeccable bolder |
| 登入/認證頁 | /impeccable typeset, /impeccable colorize | /impeccable extract, /impeccable distill |
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.
- yesterday Changed · +10 lines 097cf1b3e1dd
- 5d ago First seen · 236 lines · 0 tokens per session scan A 3bea16ee7040
proactive-skills.design-checkpoint 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 3,990 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
design-system
UI Best Practices.
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.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.