Kumo is Cloudflare's component library for building web application interfaces with accessible, design-system-compliant UI elements. Developers use it to add components with built-in keyboard navigation, focus management, and ARIA attributes, while advanced users can access re-exported Base UI primitives. Catalogue add-ons support the library's development workflow.
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/kumo --skill kumo-designgit clone --depth 1 https://github.com/cloudflare/kumoWrote 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/kumo/kumo-design)<a href="https://agentmods.dev/skills/cloudflare/kumo/kumo-design"><img src="https://agentmods.dev/badge/skills/cloudflare/kumo/kumo-design/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/kumo/kumo-design"><img src="https://agentmods.dev/badge/skills/cloudflare/kumo/kumo-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00036 | $0.01679 |
| Opus 5.5 | $0.00014 | $0.00672 |
| Sonnet 5.5 | $0.00007 | $0.00336 |
| Haiku 4.5 | $0.00004 | $0.00168 |
Grade A, and why
kumo-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 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Design
Apply these rules when designing, implementing, or reviewing Cloudflare product interfaces. Follow recommended examples and avoid patterns marked as examples to avoid.
Rules
content-text-size Use 14px for content text
All content text—body, buttons, data, other interactables—must be 14px in size. 16px and above are restricted to headings and subheadings.
Good
<Text>Content text</Text>
Avoid
<Text size="lg">Content text</Text>
heading-case Always sentence case headings
Never capitalize or uppercase headings. Product names must be title-cased.
Good
<Text as="h2">Recent requests</Text>
Avoid
<Text as="h2">Recent Requests</Text>
<Text as="h2" DANGEROUS_className="uppercase">
Recent requests
</Text>
font-tracking Never change the font's tracking
Do not use the tracking-* classes to change the spacing between characters.
Good
<span className="text-lg">Worker Metrics</span>
Avoid
<span className="text-lg tracking-tight">Worker Metrics</span>
font-weight Never use font-bold
Use font-semibold for headings and font-medium for bold inline text.
Good
<Text as="h3" variant="heading3">Account settings</Text>
<Text as="strong" bold>required</Text>
Avoid
<Text as="h3" DANGEROUS_className="font-bold">Account settings</Text>
<Text as="strong" DANGEROUS_className="font-bold">required</Text>
related-text-spacing Put related text closer together
Related text should have smaller spacing around it than the content it belongs to.
Good
<div className="grid gap-6">
<div className="grid gap-1.5">
<Text as="h3">Web Analytics</Text>
<Text>Measure site traffic without changing your code.</Text>
</div>
<Button>Configure</Button>
</div>
Avoid
<div className="grid gap-4">
<Text as="h3">Web Analytics</Text>
<Text>Measure site traffic without changing your code.</Text>
<Button>Configure</Button>
</div>
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 · 316 lines · 36 tokens per session scan A fa6b13f4a766
kumo-design is a skill published in the GitHub repository cloudflare/kumo (4,136 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,679 once invoked, about $0.0001 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
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
open-design-setup
Prepare or repair a project's prototyping environment so open-design can build prototypes with the project's own component library and render them through the project's toolchain. Use when the library target is needed and docs/design/prototyping.md is missing, stale, or failing; excludes HTML-only design work and…
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…