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 S3YED/appie-kit --skill web-design-pipelinegit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/web-design-pipeline)<a href="https://agentmods.dev/skills/s3yed/appie-kit/web-design-pipeline"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/web-design-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/s3yed/appie-kit/web-design-pipeline"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/web-design-pipeline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.01028 |
| Opus 5 | $0.00028 | $0.00514 |
| Sonnet 5 | $0.00011 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
web-design-pipeline 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 9d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Design Pipeline (premium sites, fast, with rigor)
The repeatable way to ship awwwards-tier sites without vibe-coding. Design tokens first, components second, motion last. Never one loose HTML file for flagship work.
0. Principle
Separate DESIGN (brand system) from STRUCTURE (layout) from MOTION (animation). Decide each deliberately. Padding/spacing always come from a scale, never by feel. See companion skills: design-mastery, 21st-dev, ui-ux-pro-max, design-system, motion.
1. Design system FIRST
Build one coherent brand before any page:
- Tokens as one source: color, type scale, spacing on a 4/8pt grid, radii, shadows, motion curves. Light + dark.
- Max 2 typefaces (one display, one text). Single accent colour used sparingly. Tabular numbers for figures.
- Options to generate/seed a system:
- A locked internal brand-token set for the target property.
- Claude.ai → Design tab → create a Design System (reusable across pages, decks, motion).
- getdesign.md — free brand kits for 68 major brands (colors, type, icons, buttons, dark mode). Paste a brand's
design.mdinto Claude Design "additional notes" to generate a reusable system in ~5 min. Use for inspiration/structure, never to copy a competitor's identity.
2. Structure from a reference
Pick a proven layout skeleton, then reskin with your design system:
- durable.com (or 21st.dev / awwwards) → screenshot a layout (e.g. "marketing agency website").
- Tell the model: use the design system for branding, use the screenshot only for structure. Same skeleton, your brand's look.
3. Prototype
Claude Design → high fidelity (not wireframe) + select your design system. Generate the multi-page set (home / services / about / case studies / contact). Edit visually: comment+select an element, edit for color/font/size, draw/circle a region to change specifics.
4. Hand off to Claude Code and one-shot
Export → "Handoff to Claude Code". In an empty folder, paste the command + append:
Build this with Next.js, use GSAP for animations wherever appropriate — staggered scroll reveals, count-up numbers, parallax, moving logo strip — stunning but never cheesy. Read
claude.mdand build it in one go.
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.
- 9d ago First seen · 57 lines · 56 tokens per session scan A 251e2c87a1d5
web-design-pipeline is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 17d ago), licensed MIT. It adds 56 tokens to every session and 1,028 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 2026-09-03.
Other skills, from other repositories
animation-patterns
Framer Motion patterns, page transitions, skeleton loading, scroll-linked animations, and gesture-based interactions for React.
accessibility-patterns
WCAG 2.2 AA compliance, ARIA patterns, keyboard navigation, screen reader optimization.
component-library-patterns
Design system token management, component API design, Storybook, and visual regression testing patterns.
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…
color-palette
Generate complete, accessible colour palettes from a single brand hex. Produces 11-shade scale (50-950), semantic tokens, dark mode variants, Tailwind v4 CSS output, WCAG contrast checks. Use whenever the user supplies a brand hex and asks for a palette, mentions setting up a design system, wants Tailwind theme…
tailwind-theme-builder
Set up Tailwind v4 + shadcn/ui themed UI with dark mode. Install deps, configure CSS variables via @theme inline, wire dark mode toggle, verify. Use whenever the user mentions Tailwind v4, setting up Tailwind theming, shadcn/ui colours, dark mode, or troubleshooting colours not working, tw-animate-css errors, @theme…