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/volomydyr/design-engineer-plugin/dev-prototypingnpx skills add volomydyr/design-engineer-plugin --skill dev-prototypinggit clone --depth 1 https://github.com/volomydyr/design-engineer-pluginWrote 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/volomydyr/design-engineer-plugin/dev-prototyping)<a href="https://agentmods.dev/skills/volomydyr/design-engineer-plugin/dev-prototyping"><img src="https://agentmods.dev/badge/skills/volomydyr/design-engineer-plugin/dev-prototyping.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 | $0.00067 | $0.09006 |
| Opus 5 | $0.00034 | $0.04503 |
| Sonnet 5 | $0.00013 | $0.01801 |
| Haiku 4.5 | $0.00007 | $0.00901 |
Grade A, and why
dev-prototyping 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 — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Prototyping
Generate interactive single-file HTML prototypes directly in Claude Code. One-pass approach: a clickable HTML prototype, generated screen by screen, iterated with the user. Works for new products (after planning docs exist), new features for existing products, or redesigns. Pulls design context from planning documents or Figma designs.
Important: No git, no /simplify, no TDD during prototyping. The prototype exists for visual feedback and as a reference for real implementation. Git init, branches, commits, tests, and code quality checks start at /design-engineer:development. Prototype HTML can be messy – nobody cares about code quality in a throwaway artifact.
Interaction Method
If AskUserQuestion is available, use it for all prompts below.
If not, present each question as a numbered list and wait for a reply before proceeding. For multiSelect questions, accept comma-separated numbers (e.g. 1, 3). Never skip or auto-answer without explicit user consent.
Step 0: Before starting
-
Announce your execution plan: Before doing anything, state what you will do: "Here's what I'm going to do: 1) ask what you want to prototype (product, landing page, or both), 2) ask the target platform (mobile app, responsive web, desktop web, or both), 3) gather context from your planning docs, 4) list every screen from your IA document for your approval, 5) draft a prototype brief in chat (not a file – the brief lives in the conversation only), 6) build the interactive prototype screen by screen — and for EACH screen, before generating any HTML, walk you through 3–5 open design decisions (input pattern, layout, interactions, copy direction, etc.) with 2–4 specific options per decision so you pick what fits. The MVP requirements are intentionally high-level; the implementation choices are yours, not mine. 7) iterate with you, 8) save the deliverable plus a decisions log."
-
Conditional teaching: Ask the user if they are familiar with single-file HTML prototyping. If yes, give a one-sentence refresher. If no, explain: a self-contained HTML file with all CSS and JS inline that lets you click through real screens and interactions – no build tools, no dependencies, just open in a browser.
Required: ALWAYS ask the question, ALWAYS give the refresher when the user says yes. Never skip this step because the user "is a designer" or "already demonstrated familiarity earlier." Users want a memory refresh on every activity, including ones they know. Phrases like "I'll skip the explainer (you're a designer)" are forbidden — they signal the model has decided ON BEHALF OF the user that a refresher isn't needed. The user, not the model, decides what's redundant. The refresher takes one sentence; the cost is trivial; the value to a tired user mid-session is high.
What ships with it
2 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.
- 4d ago First seen · 601 lines · 67 tokens per session scan A 5a5adb5b2054
dev-prototyping is a skill published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 9,006 once invoked, about $0.0003 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
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.