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/android-designnpx skills add f0d010c/stark --skill android-designgit clone --depth 1 https://github.com/f0d010c/starkWhat 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 | $0.00128 | $0.02417 |
| Opus 5 | $0.00064 | $0.01208 |
| Sonnet 5 | $0.00026 | $0.00483 |
| Haiku 4.5 | $0.00013 | $0.00242 |
Grade A, and why
android-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 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
android-design — pick the track first
Android has multiple stacks with different visual ceilings. Ask the user which one before any code.
What This Skill Can Do
- Choose the right Android track: strict Compose/Material, branded Compose, React Native, Flutter, or Compose Multiplatform.
- Design mobile task flows, onboarding, forms, settings, dashboards, media/product surfaces, foldables, tablets, and adaptive layouts.
- Preserve UX briefs, state coverage, navigation hierarchy, gesture/back behavior, loading/error/permission states, and accessibility.
- Apply Material 3 Expressive, dynamic color, edge-to-edge, predictive back, motion schemes, shape, typography, and responsive window-size classes.
- Add branded originality through content surfaces, composition, typography, and state treatment without breaking Android idioms.
Step 0 (MANDATORY) — Ask the user which track
Which track for this app?
1. System-like native (Jetpack Compose + Material 3 Expressive strict) — feels like Pixel Launcher, Google Calendar, Settings. Best for: utilities, system tools, productivity. Spring physics, shape morphing, wavy progress, dynamic color (Material You). Examples: Read You, Androidify sample, Files by Google.
2. Branded native (Compose + custom Material theme) — native chrome (M3E motion, predictive back, edge-to-edge) but bespoke content surface (custom typography, hero atmospheres, magazine layouts). Visual ceiling: high. Examples: Fitbit redesign, Google Calendar's editorial moments, Niantic apps.
3. React Native (New Architecture + Fabric + Hermes) — real Android views, decent native feel, JavaScript codebase, cross-platform with iOS. Material themable but won't get spring physics or shape morphing without manual work. Examples: Discord mobile, Coinbase, Microsoft Office.
4. Flutter — Skia-painted custom rendering. Cross-platform single codebase. Lags Material updates (no M3 Expressive parity, no real dynamic color). Visual ceiling: high if you ship your own design language; weak if mimicking Material. Examples: Google Pay, BMW My BMW, Toyota.
5. Compose Multiplatform (1.8+) — same Compose code, runs Android + iOS + Desktop + Web (Wasm experimental). Native on Android, Material-look on iOS (you must Cupertino-skin or accept). Best for: Kotlin shop wanting cross-platform from one codebase.
Which? Or describe priorities (Play Store launch, cross-platform reach, brand vs Material fit) 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.
- 2d ago First seen · 163 lines · 128 tokens per session scan A 8b5fca080ea6
android-design is a skill published in the GitHub repository f0d010c/stark (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 128 tokens to every session and 2,417 once invoked, about $0.0006 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
mobile-app
像素级 iPhone 15 Pro 边框, 一屏 app 截图.
mobile-onboarding
三个手机框并排: splash / value-prop / sign-in.
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-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-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…