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 jezweb/claude-skills --skill design-loopgit clone --depth 1 https://github.com/jezweb/claude-skillsWrote 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/jezweb/claude-skills/design-loop)<a href="https://agentmods.dev/skills/jezweb/claude-skills/design-loop"><img src="https://agentmods.dev/badge/skills/jezweb/claude-skills/design-loop.svg" alt="Measured on agentmods" height="20"></a>- Socket warn
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 236 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00130 | $0.05243 |
| Opus 5 | $0.00065 | $0.02622 |
| Sonnet 5 | $0.00026 | $0.01049 |
| Haiku 4.5 | $0.00013 | $0.00524 |
Grade A, and why
design-loop 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 — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Loop — Autonomous Site Builder
Build complete multi-page websites through an autonomous loop. Each iteration reads a task, generates a page, integrates it, verifies it visually, then writes the next task to keep going.
Overview
The Design Loop uses a "baton" pattern — a file (.design/next-prompt.md) acts as a relay baton between iterations. Each cycle:
- Reads the current task from the baton
- Generates the page (via Claude or Google Stitch)
- Integrates into the site structure (navigation, links)
- Verifies visually via browser automation (if available)
- Updates site documentation
- Writes the NEXT task to the baton — keeping the loop alive
This is orchestration-agnostic. The loop can be driven by:
- Human-in-loop: User reviews each page, then says "next" or "keep going"
- Fully autonomous: Claude runs continuously until the site is complete
- CI/CD: Triggered on
.design/next-prompt.mdchanges
Generation Backends
| Backend | Setup | Quality | Speed | Best for |
|---|---|---|---|---|
| Claude (default) | Zero dependencies | Great — production-ready HTML/Tailwind | Fast | Most projects, full code control |
| Google Stitch | npm install @google/stitch-sdk + API key |
Higher fidelity AI designs | ~10-20s/screen | Design-heavy projects, visual polish |
Detecting Stitch
At the start of each loop, check if Stitch is available:
- Check if
@google/stitch-sdkis installed:ls node_modules/@google/stitch-sdk 2>/dev/null - Check if
STITCH_API_KEYis set in.dev.varsor environment - Check if
.design/metadata.jsonexists (contains Stitch project ID)
If all three are present, use Stitch. Otherwise, fall back to Claude generation.
Stitch SDK Reference
Install: npm install @google/stitch-sdk. Set STITCH_API_KEY in environment or .dev.vars.
import { stitch } from "@google/stitch-sdk";
// Create a project
const result = await stitch.callTool("create_project", { title: "My Site" });
// Reference an existing project
const project = stitch.project("4044680601076201931");
// Generate a screen
const screen = await project.generate("A modern landing page with hero section", "DESKTOP");
// Get assets
const htmlUrl = await screen.getHtml(); // Download URL for HTML
const imageUrl = await screen.getImage(); // Download URL for screenshot
// Edit an existing screen (prefer this for refinements)
const edited = await screen.edit("Make the background dark and enlarge the CTA button");
// Generate variants
const variants = await screen.variants("Try different colour schemes", {
variantCount: 3,
creativeRange: "EXPLORE", // "REFINE" | "EXPLORE" | "REIMAGINE"
aspects: ["COLOR_SCHEME"], // "LAYOUT" | "COLOR_SCHEME" | "IMAGES" | "TEXT_FONT" | "TEXT_CONTENT"
});
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 · 528 lines · 130 tokens per session scan A a62ac4c8a36b
design-loop is a skill published in the GitHub repository jezweb/claude-skills (995 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 5,243 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 2026-09-03.
Other skills, from other repositories
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
animation-patterns
Framer Motion patterns, page transitions, skeleton loading, scroll-linked animations, and gesture-based interactions for React.
suede-design
Suede Labs AI design skill for making an interface feel intentional instead of templated: design tokens, color strategy, OKLCH ramps, type scale, fluid type, visual hierarchy, dark mode, spacing, component laws, motion, and source-to-implementation visual QA. Use when asked to design, restyle, polish, or audit a…
frontend-design-review
Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.
component-library-patterns
Design system token management, component API design, Storybook, and visual regression testing patterns.