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-landing-pagegit 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-landing-page)<a href="https://agentmods.dev/skills/cloudflare/vibesdk/frontend-design-landing-page"><img src="https://agentmods.dev/badge/skills/cloudflare/vibesdk/frontend-design-landing-page/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-landing-page"><img src="https://agentmods.dev/badge/skills/cloudflare/vibesdk/frontend-design-landing-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Prompt Injection · line 1059 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 1908 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 2041 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 2925 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00106 | $0.32848 |
| Opus 5 | $0.00053 | $0.16424 |
| Sonnet 5 | $0.00021 | $0.06570 |
| Haiku 4.5 | $0.00011 | $0.03285 |
Grade A, and why
frontend-design-landing-page 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 10d 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 — 3,279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Landing Page Design System
AI-Optimized Design Reference for building warm, professional, conversion-focused marketing landing pages, product pages, feature pages, and pricing pages.
This skill captures a specific landing-page register: warm cream backgrounds (NOT pure white), brown text (NOT pure black), a single bold accent for CTAs, pill-rounded buttons, and signature corner-bracket card decorations. It's tuned for developer-adjacent / B2B products — the aesthetic feels human and crafted without being playful or consumer-y. Pin the accent color to your brand; the rest of the system is reusable as-is.
When to use this vs.
frontend-design-saas: Landing-page surfaces (homepage, /features, /pricing, /about, blog) → this skill. Product UI behind the login (dashboards, settings, tables) →frontend-design-saas.
Quick Reference (TL;DR)
Brand Accent: #FF4801 (replace with your brand) / #FF7038 (hover)
Background: #FFFBF5 (warm cream) / #121212 (dark mode)
Text: #521000 (warm brown) / #F0E3DE (dark mode)
Border: #EBD5C1 (cream-tinted)
Font Sans: "Inter" / "Geist" / "Manrope" / any modern grotesk
Font Mono: "JetBrains Mono" / "IBM Plex Mono" / "Geist Mono"
Base Spacing: 4px (multiples: 8, 12, 16, 24, 32, 48, 64)
Border Radius: Buttons = pill (9999px), Cards = 12-16px, Inputs = 8px, Hero = 16-20px
Signature: Corner brackets on cards (8px decorative squares at corners)
This is a landing-page register, not a product-UI register. Buttons are pills (consumer/marketing read), backgrounds are warm cream (inviting, not sterile), and decorative idioms like corner brackets are welcome. For product surfaces behind auth, use the SaaS skill instead.
1. Brand Foundation
Design Philosophy
| Principle | Description |
|---|---|
| Warm but Technical | Cream tones soften technical content |
| Professional yet Approachable | Modern typography, generous whitespace |
| Developer-Focused | Monospace for code, terminal aesthetics |
| Performance-Oriented | Smooth animations convey speed |
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.
- 10d ago First seen · 3,279 lines · 106 tokens per session scan A bb620c71dd67
frontend-design-landing-page is a skill published in the GitHub repository cloudflare/vibesdk (5,352 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 32,848 once invoked, about $0.0005 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
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-shell.
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
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…
create-openbitfun-skin
Inspect the current OpenBitFun Appearance contract and author, repair, package, or validate sparse .openbitfun-appearance skins. Use when Codex needs to discover registered scenes/components/parts/states/facets, check Style IR properties or renderer tokens, initialize or inspect a package, diagnose import failures…
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.
drawio-diagram
A tool for creating editable Draw.io diagrams, a file format used for flowcharts, system diagrams, and model illustrations.