Cloudflare VibeSDK is an open-source platform for building and deploying full-stack applications through an AI coding agent. Users describe an application, review the agent's questions and edits, inspect previews and errors, and iterate through deployment on Cloudflare. The catalogue entries provide skills and instructions for working with the platform.
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 cloudflare/vibesdk --skill frontend-design-saasgit clone --depth 1 https://github.com/cloudflare/vibesdkWrote 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/cloudflare/vibesdk/frontend-design-saas)<a href="https://agentmods.dev/skills/cloudflare/vibesdk/frontend-design-saas"><img src="https://agentmods.dev/badge/skills/cloudflare/vibesdk/frontend-design-saas/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/cloudflare/vibesdk/frontend-design-saas"><img src="https://agentmods.dev/badge/skills/cloudflare/vibesdk/frontend-design-saas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.35420 |
| Opus 5.5 | $0.00042 | $0.14168 |
| Sonnet 5.5 | $0.00021 | $0.07084 |
| Haiku 4.5 | $0.00011 | $0.03542 |
Grade A, and why
frontend-design-saas 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 1mo 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 — 3,440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SaaS Design System (Stripe / Linear / Vercel lineage)
AI-Optimized Design Reference for building S-tier SaaS dashboards, admin consoles, billing pages, settings UIs, data-dense application shells, and product surfaces.
Tonal anchors:
stripe.com/dashboard,linear.app,vercel.com/dashboard,notion.so/teamspace,clerk.com,planetscale.com/console.
Quick Reference (TL;DR)
Brand Accent: #5E6AD2 (indigo) - replace with product brand
Neutrals: #FFFFFF → #F8FAFC → #F1F5F9 → #E2E8F0 → #94A3B8 → #475569 → #0F172A
Text: #0F172A (primary) / #475569 (muted) / #94A3B8 (subtle)
Border: #E2E8F0 (default) / #CBD5E1 (strong)
Font Sans: "Inter", "Geist", system-ui (NOT Arial, NOT Roboto)
Font Mono: "JetBrains Mono", "Geist Mono", ui-monospace
Base Spacing: 4px (scale: 4, 8, 12, 16, 20, 24, 32, 40, 48, 64)
Border Radius: Buttons/inputs = 6-8px (NOT pill), Cards = 8-12px, Modals = 12-16px
Shadow: Tight, low-spread, single-direction (NOT diffuse marketing shadows)
Density: Compact-to-comfortable; row heights 36-44px, button heights 32-36px
The fastest way to get this wrong: use marketing-page aesthetics (huge type, generous whitespace, pill buttons, gradient hero shadows) in a product surface. SaaS UIs are dense, neutral, fast, and quiet. The brand color appears in <5% of the pixels and earns its weight by marking only what's interactive or active.
1. Brand Foundation
Design Philosophy
| Principle | Description |
|---|---|
| Users First | Workflows, keyboard navigation, and information density beat decoration. |
| Quiet by Default | Neutrals dominate; the brand color is reserved for primary action, active state, and focus. |
| Speed & Density | Snappy transitions (≤200ms), compact row heights, no entrance animations on every page load. |
| Opinionated Defaults | Single canonical pattern per surface (one button hierarchy, one date picker, one empty state). |
| Meticulous Craft | 1px borders aligned to pixel grid, focus rings 2px offset 2px, motion uses ease-out not linear. |
| Accessible (WCAG AA+) | 4.5:1 text contrast, 3:1 UI element contrast, every interactive surface keyboard-reachable. |
| Predictable | Same component looks/behaves identically on every page; no marketing-grade variants. |
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.
- 1mo ago First seen · 3,440 lines · 105 tokens per session scan A e0283287a2bf
frontend-design-saas is a skill published in the GitHub repository cloudflare/vibesdk (5,419 stars, last pushed 29d ago), licensed MIT. It adds 105 tokens to every session and 35,420 once invoked, about $0.0004 per session on Opus 5.5. 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
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
visual-acceptance
A visual final-review method for user-interface changes. It checks the rendered result with repeatable screenshots, pixel values, computed styles, and CSS layering checks across themes.
drawio-diagram
A tool for creating editable Draw.io diagrams, a file format used for flowcharts, system diagrams, and model illustrations.
gpui-mockup
Explore visual directions for a herdr-gpui UI element as real GPUI code. Write 3–4 variants in one Rust file, show them side by side in a native mockup window in the user's own theme and fonts, capture the window to check your work, and iterate on the picks and notes the user sends back. Use instead of the HTML mockup…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…