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 decocms/studio --skill decocms-uigit clone --depth 1 https://github.com/decocms/studioWrote 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/decocms/studio/decocms-ui)<a href="https://agentmods.dev/skills/decocms/studio/decocms-ui"><img src="https://agentmods.dev/badge/skills/decocms/studio/decocms-ui/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/decocms/studio/decocms-ui"><img src="https://agentmods.dev/badge/skills/decocms/studio/decocms-ui.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 | $0.00091 | $0.01141 |
| Opus 5.5 | $0.00036 | $0.00456 |
| Sonnet 5.5 | $0.00018 | $0.00228 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
decocms-ui 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
decocms product design system (@decocms/ui)
React 19 components built on Radix primitives, styled with Tailwind CSS v4 semantic tokens. Light and dark themes work out of the box. Browse every component and token at https://designsystem.decocms.com/
Install (new project)
bun add @decocms/ui react react-dom
Requirements: React 19 and Tailwind CSS v4 (bun add -d tailwindcss @tailwindcss/vite
plus the tailwindcss() plugin in vite.config.ts).
Make the design-system stylesheet the FIRST import of the app's CSS entry point —
it pulls in Tailwind itself, all tokens, and the bundled fonts (Inter + Commit Mono).
Do NOT also @import "tailwindcss" yourself:
@import "@decocms/ui/styles/global.css";
Tailwind only scans app source by default; if the app's classes come exclusively
from @decocms/ui components this already works — the package declares its own
@source.
Peers: install react-hook-form if you use the form component, and sonner
if you use toasts (sonner component). They are peers so the app and the design
system share one instance — never bundle a second copy.
Imports
No barrel export. Import each component from its subpath, extensionless:
import { Button } from "@decocms/ui/components/button";
import { Dialog, DialogContent, DialogTrigger } from "@decocms/ui/components/dialog";
import { cn } from "@decocms/ui/lib/utils";
import { useIsMobile } from "@decocms/ui/hooks/use-mobile";
Exception — inside the decocms/studio monorepo, workspace imports keep the
source extension: @decocms/ui/components/button.tsx.
Rules
- Semantic tokens only, never raw palette.
bg-primary,text-muted-foreground,bg-destructive,border-border— neverbg-red-500ortext-zinc-400. Available color roles:background,foreground,card,popover,primary,secondary,muted,accent,destructive,success,warning,special(AI/highlight moments),brand,border,input,ring,sidebar-*(sidebar surfaces),chart-1..5(data viz). Most roles pair with a*-foregroundtext token. - Dark mode is automatic via the
.darkclass on a root element — never hardcode colors or writedark:overrides that bypass tokens. - Compose, don't fork. Extend components with
className+cn(); add variants through the component'scvaconfig rather than wrapping with custom styles. font-boldrenders at weight 650 (custom scale); body text is 450. Radius scale derives from--radius(default 0.375rem).- User-facing copy comes from the app, passed as props — components ship only overridable English defaults.
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 · 101 lines · 91 tokens per session scan A 9968072c4307
decocms-ui is a skill published in the GitHub repository decocms/studio (410 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 1,141 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
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
multi-surface-render
Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output…
ai-ui-generation
AI-assisted UI generation patterns for json-render, v0.app, Google Stitch, Bolt Cloud, and Cursor workflows. Covers prompt engineering for component and full-stack app generation, review checklists for AI-generated code, design token injection, refactoring for design system conformance, and CI gates for quality…
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…
component-search
Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…