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 sutchan/Agent-Skills-Hub --skill prototype-design-exploregit clone --depth 1 https://github.com/sutchan/Agent-Skills-HubWrote 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/sutchan/agent-skills-hub/prototype-design-explore)<a href="https://agentmods.dev/skills/sutchan/agent-skills-hub/prototype-design-explore"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/prototype-design-explore.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 5.1 | $0.00042 | $0.00719 |
| Opus 5 | $0.00021 | $0.00360 |
| Sonnet 5 | $0.00008 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
prototype-design-explore 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 3d 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.
What it actually says
Prototype
Prototype 是用来回答一个问题的 throwaway code。问题决定形状。
Pick a branch
先识别正在回答哪个问题：来自用户 prompt、周围代码，或在用户在线时直接询问：
- "Does this logic / state model feel right?" → LOGIC.md。构建一个单一、可分享的 HTML 文件——free-play buttons 加 tabbed guided walkthroughs——推动 state machine 跑过纸面上难以推理的 cases，而且非开发人员也能驱动它。
- "What should this look like?" → UI.md。在单一路由上生成几种差异很大的 UI variations，并通过 URL search param 和浮动底栏切换。
这两个分支会产出非常不同的 artifacts；选错会浪费整个 prototype。如果问题确实模糊且用户不可达，默认选择更匹配周围代码的分支（backend module → logic；page 或 component → UI），并在 prototype 顶部说明假设。
Rules that apply to both
- 从第一天就是 throwaway，并明确标记。 Prototype code 要靠近它实际会被使用的位置（放在被 prototype 的 module 或 page 旁边），这样上下文清楚；但命名要让随手读代码的人看出它是 prototype，不是 production。对 throwaway UI routes，遵守项目现有 routing convention；不要发明新的顶层结构。
- 运行毫无负担。 UI prototype 从项目 task runner 中的一条命令启动——
pnpm <name>、python <path>、bun <path>等。Logic demo 则是用户双击即可打开的单个 HTML 文件。无论哪种，启动都不需要动脑。 - 默认不持久化。 State 保存在内存中。Persistence 是 prototype 要_检查_的东西，不该成为依赖。如果问题明确涉及 database，就用 scratch DB 或带有清晰 “PROTOTYPE — wipe me” 名称的本地文件。
- 跳过 polish。 不写 tests，不做超过“能跑起来”所需的 error handling，不做 abstractions。重点是快速学到东西。
- 暴露 state。 每次 action（logic）或每次 variant switch（UI）后，打印或渲染完整相关 state，让用户看到发生了什么变化。
- 完成后 capture。 把验证过的 decision 折进真实 code，然后把 prototype 本身作为 primary source 保存：commit 到 main 之外的 throwaway branch，并在 implementation issue 上留下指向该 branch 的 context pointer。同时在 issue 或 commit 中 capture answer，也就是 verdict 与它解决的问题。Main branch 只保留验证过的 decision。
What ships with it
3 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.
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.
- 3d ago First seen · 31 lines · 42 tokens per session scan A 34ce0c3348e5
prototype-design-explore is a skill published in the GitHub repository sutchan/Agent-Skills-Hub (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 719 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
design-system-architect
Expert guide for designing, building, and maintaining scalable UI design systems with design tokens, headless primitives, Material Design 3 (M3), Tailwind v4 @theme, and WCAG 2.2 accessibility.
ui-ux-pro-max
Comprehensive design guide & BM25 search engine for web and mobile applications across 11 tech stacks / Panduan desain komprehensif & mesin pencari BM25 untuk aplikasi web dan mobile di 11 tech stack.
hig
Applies Human Interface Guidelines (HIG) principles — Hierarchy, Harmony, and Consistency — to UI/UX designs to ensure intuitive and cohesive interfaces / Menerapkan prinsip Human Interface Guidelines (HIG) — Hierarchy, Harmony, dan Consistency — pada desain UI/UX untuk memastikan antarmuka yang intuitif dan kohesif.
website-design-cloner
Analyzes and reverse-engineers website designs directly from a target URL, extracting layout structures, design tokens (colors, typography, spacing), component hierarchies, visual assets, and responsive behaviors to enable full 1:1 duplication into modern code (Tailwind CSS v4, React/Next.js, HTML/CSS). / Mempelajari…
data-visualization-expert
Expert guide for data visualization, charts, and dashboards using D3.js, Recharts, Chart.js, Nivo, and Tremor / Panduan ahli visualisasi data, chart, dan dashboard menggunakan D3.js, Recharts, Chart.js, Nivo, dan Tremor.
svg-animation-motion-expert
Expert guide for web animations: SVG manipulation, Framer Motion 12+, GSAP 3, CSS Scroll-Driven Animations, and View Transitions API / Panduan ahli animasi web.