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 YuDefine/nuxt-supabase-starter --skill ui-plangit 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/skills/yudefine/nuxt-supabase-starter/ui-plan)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/ui-plan"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/ui-plan/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/yudefine/nuxt-supabase-starter/ui-plan"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/ui-plan.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 | $0.00083 | $0.00779 |
| Opus 5 | $0.00042 | $0.00390 |
| Sonnet 5 | $0.00017 | $0.00156 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
ui-plan 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.
What it actually says
UI Plan
ui-plan 只產出本次迭代的 UI plan 與靜態雛形。UI artifact 留在 plan package，作為實作參考與評審材料，不是系統 truth。
SOP
Phase 1 -- 對齊 plan、truth-delta 與 UI 範圍
- READ 讀取使用者需求、呼叫者 handoff、plan package 的
spec.md、research.md、plan.md、truth-delta.md、既有ui/**，以及與 UI 有關的specs/truth/contracts/**、specs/truth/features/**。 - READ 讀取
templates/ui-plan.md、templates/ui-plan.example.md、templates/prototype-entry.html、templates/prototype-entry.example.html、templates/prototype-screen.html、templates/prototype-screen.example.html、rules/高保真靜態頁面切分與Flow覆蓋判準.md與rules/靜態網站雛形與實作計畫邊界判準.md，確認 plan-side UI artifact 與靜態雛形的完成樣貌。 - DELEGATE 若缺口會改變使用者可見流程、畫面責任、互動入口、錯誤狀態或與 truth 的對齊方式，呼叫
/clarify；未收斂前停止。
Phase 2 -- 產出 UI plan 與靜態雛形
- THINK 依需求、truth-delta 與現有 truth 收斂畫面範圍、狀態、主要 flow、可見回饋、錯誤處理、accessibility 與 responsive 行為。
- WRITE 將 UI 規劃寫入
specs/plans/NNN-<slug>/ui/ui-plan.md。 - WRITE 依 UI plan 產出或更新
specs/plans/NNN-<slug>/ui/*.html與必要靜態資源；不得寫入specs/truth/**。 - READ 回頭檢查 UI plan 與靜態雛形是否對齊 spec、truth-delta 與相關 truth；若不符合，立即修正。
Phase 3 -- 交付後續 handoff
- WRITE 向使用者回報 UI plan、靜態雛形路徑、引用的 truth 變更、剩餘風險，以及是否可進入
/dsl-refine、/tasks或實作。
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- rules/靜態網站雛形與實作計畫邊界判準.md 2.5 KB
- rules/高保真靜態頁面切分與Flow覆蓋判準.md 3.0 KB
- templates/prototype-entry.example.html 3.9 KB
- templates/prototype-entry.html 3.9 KB
- templates/prototype-screen.example.html 4.5 KB
- templates/prototype-screen.html 4.6 KB
- templates/ui-plan.example.md 5.9 KB
- templates/ui-plan.md 3.1 KB
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 First seen · 37 lines · 83 tokens per session scan A 594ef7ec4dbc
ui-plan is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 779 once invoked, about $0.0004 per session on Opus 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 2026-09-10.
Other skills, from other repositories
create-wot-ui-theme
A workflow for creating one SCSS file that defines and mounts a custom Wot UI theme. SCSS is a CSS format with extra features for organizing styles.
using-design-system
Ensures consistent use of X-components design system instead of Material3 when working on feature UI code. Automatically activates for Composable functions in feature modules or when user mentions UI/screens/components.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
tailwind-v4-shadcn
Production-tested setup for Tailwind CSS v4 with shadcn/ui, Vite, and React. Use when: initializing React projects with Tailwind v4, setting up shadcn/ui, implementing dark mode, debugging CSS variable issues, fixing theme switching, migrating from Tailwind v3, or encountering color/theming problems. Covers: @theme…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
anti-ui-slop
Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.