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 skills/f0d010c/stark/apple-designnpx skills add f0d010c/stark --skill apple-designgit clone --depth 1 https://github.com/f0d010c/starkWrote 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/f0d010c/stark/apple-design)<a href="https://agentmods.dev/skills/f0d010c/stark/apple-design"><img src="https://agentmods.dev/badge/skills/f0d010c/stark/apple-design.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 | $0.00149 | $0.03128 |
| Opus 5 | $0.00075 | $0.01564 |
| Sonnet 5 | $0.00030 | $0.00626 |
| Haiku 4.5 | $0.00015 | $0.00313 |
Grade A, and why
apple-design 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 4d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apple-design — pick the track first
Apple platforms have multiple stacks with different visual ceilings and cost. Ask the user which one before any code.
What This Skill Can Do
- Choose the right Apple track: strict SwiftUI, branded SwiftUI, React Native, Flutter Cupertino, or Electron/Tauri for macOS.
- Design iPhone task flows, iPad/macOS productivity surfaces, menu-bar utilities, document apps, settings, inspectors, media apps, and desktop-class workbenches.
- Preserve UX briefs, state coverage, action hierarchy, keyboard flow, Dynamic Type, focus, accessibility, and safe areas.
- Apply HIG, Liquid Glass, SF Symbols, SF typography, NavigationSplitView, DocumentGroup, inspectors, sheets, toolbars, and platform-specific motion.
- Add originality through composition, content, and state treatment without replacing native controls with web-style chrome.
Step 0 (MANDATORY) — Ask the user which track
Which track for this app?
1. System-like native (SwiftUI strict + Liquid Glass + HIG) — feels like Settings, Notes, Reminders, Mail. Best for: utilities, productivity. Visual ceiling: medium. Stays App Store-friendly. Examples: Things 3, NetNewsWire, Soulver.
2. Branded native (SwiftUI + HIG + custom identity) — native chrome (Liquid Glass, SF Symbols, Dynamic Type) but bespoke content surface (custom typography, hero atmospheres, magazine layouts). Best for: consumer/media/creative apps that want fit-in and identity. Visual ceiling: high. Examples: Ivory, Reeder, Mela, Craft, CARROT Weather.
3. React Native (New Architecture + Fabric + Hermes) — real UIKit views, decent native feel, JavaScript codebase, cross-platform with Android. Liquid Glass partial via
expo-glass-effect. Best for: cross-platform apps with web-team velocity. Examples: Discord mobile, Coinbase, Microsoft Office mobile.4. Flutter Cupertino — Skia-painted UIKit-look. Always one OS behind, no Liquid Glass. Cross-platform. Best for: utility apps where pixel control beats native feel. Visual ceiling: high if you bring your own design language; low if you try to mimic iOS.
5. Electron / Tauri 2 (macOS only — no iOS) — web stack desktop apps. Tauri 2 (~5MB, WKWebView) or Electron (~150MB, bundled Chromium). Same React/Tailwind/Motion code as web. Best for: cross-platform desktop with brand-first identity. Examples: Spotify, Discord, VSCode, Slack, Figma desktop, Linear.
Which? Or describe priorities (App Store, brand vs HIG fit, cross-platform reach) and I'll pick.
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.
- 4d ago First seen · 173 lines · 149 tokens per session scan A 5f0525a73e46
apple-design is a skill published in the GitHub repository f0d010c/stark (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 149 tokens to every session and 3,128 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
frontend-design-writer
阶段 1-7 持续维护的 design.md 主写手——把调研（六维试吃）+ 双轮深度采访 + 视觉锚定三件套 + 动效实现 prompt 集全部压缩为 Agent 可执行的设计契约。kun 版 15 段三轮写作顺序（原 12 段 + 新增 §12 Moodboard Prompt / §13 Page Mockup Prompt / §14 Motion Prompts 三段视觉锚定引用）。同时维护 DESIGN-LANGUAGE.md（低频）+ design.md（高频）+ MOTION-SPEC.md（中频）三份。不用于调研本身（那是 frontend-design-research）、不用于从零搭 knowledge/…
frontend-design-research
阶段 2 试吃——对 4-5 个该领域设计优秀的真实网站跑六维机械拆解（形 / 色 / 字 / 构 / 质 / 动），综合成本项目 design.md 初稿。六维是上位骨架，DOM 量化工作流 + 动效采访 5 类是落地肌肉。每次一站，保护上下文。不做前轮/后轮深度采访（那是 frontend-interview-dualround）、不做视觉锚定三件套（那是 frontend-visual-reference）、不写最终交付的 design.md（那是 frontend-design-writer）、不做组件库 / 动效资产库选型（那部分由 frontend-design-writer 的 §11 Resources 段 +…
frontend-design-review
代码已经跑起来后（阶段 7 迭代微调）的设计评审横切——用户看到具体页面涌现审美反馈时使用：三段式追问（定位→对标→量化）把"感觉不对"翻译成可执行改动项，"选择题化"让用户做选择题而不是填空题，参数外显 Tweaks 让不确定的参数暴露成可调旋钮，所有修正反写回 design.md。覆盖 design-review（视觉对标）、design-content（文案与信息层级）、design-harden（边缘状态加固）三种子模式。仅用于代码已生成后——代码前的"感觉"引导走 frontend-interview-dualround 的后轮采访；纯调研走 frontend-design-research；写 design.md 走…
frontend-iteration-planner
前端项目二开 / 增量改进的入口路由器——已定稿 design.md 的项目要加新页面 / 新 section / 微改 token 时，先读老资产（design.md + visual-anchors/ + motion-prompts/），按三档 tier 判定（T1 新页面 / T2 新 section / T3 微改）输出本轮最小流程路径，阻止模型"假装新项目"把已定风格冲掉。本 skill 只做路由和前置防呆，不自己执行具体阶段——执行仍委给 dualround / visual-reference / design-writer / design-review 等原 skill。触发：用户说"加个新页面""在首页加一个…
frontend-visual-reference
阶段 4 视觉锚定三件套的主 skill——在写第一行代码前，用 Moodboard（A） + 完整网页示意图（B） + 动效帧序列（C） 三种图像级锚点把视觉方向钉死。探索前移在 Moodboard 阶段（A）以 2-3 张让用户选的方式执行，B/C 是单线生成。资产生成走双路径：主路径 baoyu-imagine skill 自动出图，兜底路径打开 prompt 文件让用户复制到网页端。产出写入 knowledge/design-docs/visual-anchors/ 目录，并在 design.md §12/§13/§14 回填引用。触发：design.md 初稿完成、后轮采访定稿后、用户说"出几张方向图让我选""做…
frontend-interview-dualround
产品设计师视角的双轮深度采访横切——前轮（阶段 1 需求后）建产品边界 + 主语言收敛，后轮（阶段 3 Moodboard 选定后）拔架构 + section + 文案调性 + 交互路径。五类引导式提问：前轮是定位/用户/反向/资源/时间；后轮是架构/section/文案调性/交互路径/反向细节。角色显式从"前端设计师"切到"产品设计师"，选择题优先+开放题兜底，一次问 3-5 个不批量甩 20 个。产出反写回 design.md。触发：新项目启动 brief 模糊、六维调研完成但未定稿、用户说"帮我问清楚这个产品""我脑子里有个想法但说不清"。不用于代码后纠偏（那是 frontend-design-review…