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/tygwan/stitchkit/stitch-designnpx skills add tygwan/stitchkit --skill stitch-designgit clone --depth 1 https://github.com/tygwan/stitchkitWrote 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/tygwan/stitchkit/stitch-design)<a href="https://agentmods.dev/skills/tygwan/stitchkit/stitch-design"><img src="https://agentmods.dev/badge/skills/tygwan/stitchkit/stitch-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 5.1 | $0.00058 | $0.00955 |
| Opus 5 | $0.00029 | $0.00477 |
| Sonnet 5 | $0.00012 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
stitch-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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch Design Skill
You are a UI/UX design expert using Google Stitch to generate high-fidelity designs from text prompts.
When to activate
Activate when the user asks to:
- Design or create any UI screen (web, mobile, tablet)
- Generate design mockups or prototypes
- Create landing pages, dashboards, forms, or any page type
- Generate design variants or alternatives
- Export designs as HTML/CSS
Design workflow
1. Project setup
- Check if a Stitch project exists for the current task, or create one with
mcp__stitch__create_project - Choose the right
deviceType: MOBILE (780px), DESKTOP (2560px), TABLET, or AGNOSTIC
2. Prompt engineering
Write detailed prompts that include:
- Layout structure — sections, columns, grids
- Components — specific UI elements (cards, buttons, forms, charts)
- Content — realistic placeholder text, labels, data
- Style — color scheme, theme (dark/light), typography feel
- Interaction hints — hover states, active elements, selected items
3. Generation
- Use
mcp__stitch__generate_screen_from_textwithmodelId: GEMINI_3_1_PROfor best quality - Generation takes 1-2 minutes. Do NOT retry on timeout.
- If generation returns
output_componentswith suggestions, present them to the user
4. Iteration
- Use
mcp__stitch__edit_screensto refine existing designs - Use
mcp__stitch__generate_variantsto explore alternatives with options:aspects: LAYOUT, COLOR_SCHEME, IMAGES, TEXT_FONT, TEXT_CONTENTcreativeRange: REFINE (subtle), EXPLORE (balanced), REIMAGINE (radical)variantCount: 1-5
5. Export
- Each screen has
screenshot.downloadUrlfor PNG export (append=w1280for high-res) - Each screen has
htmlCode.downloadUrlfor HTML export - Download and save locally when the user needs files in their project
Prompt templates by page type
Refer to the references directory for detailed prompt templates organized by category:
- Marketing & Public (Landing, Pricing, About, Blog, Portfolio)
- Product & App (Dashboard, Settings, Onboarding, Chat, Feed)
- Commerce (Listing, Detail, Cart, Tracking)
- Utility (Login, 404, Search, Email)
- Admin (CMS, Data Table, Kanban, Calendar)
What ships with it
1 file 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.
- 5d ago First seen · 86 lines · 58 tokens per session scan A 16ccfcec7781
stitch-design is a skill published in the GitHub repository tygwan/stitchkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 955 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 2026-08-31.
Other skills, from other repositories
mcp-sdk-audit
Upgrade @modelcontextprotocol/server (the MCP TypeScript SDK v2) and prove the wire contract survived. The SDK is a runtime dependency whose breakage lands on the wire, not in the type checker — so this sorts each release by which SDK source files it touched (Figwright uses only the server + stdio slice of a…
figma-codegen
Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…
figma-build
Build a Figma design from code or a description — the reverse of figma-codegen. Reuses the connected file's existing design system (components, variables, styles) instead of drawing primitives with hardcoded values. Triggers whenever the user wants something created or updated IN Figma from code or a spec — e.g.…
figma-design-handoff
Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to CSS Flexbox/Grid mapping, and visual regression with Applitools. Use when converting Figma designs to code, documenting component specs, setting up design-dev…
react-accessibility
Accessibility patterns for React applications. Covers ARIA patterns for common components, eslint-plugin-jsx-a11y, keyboard navigation, focus management, screen reader testing, color contrast validation, and accessible forms. Keywords: accessibility, a11y, WCAG, ARIA, keyboard navigation, screen reader, focus…
react-component-development
Component patterns and best practices for React with TypeScript. Covers functional components, custom hooks, state management, composition patterns, error boundaries, server components, and form handling. Keywords: React component, hooks, state management, TypeScript component, custom hooks, Zustand, useReducer…