Guidance for shadcn/ui, a toolkit that adds UI component source code directly to a web project. It covers finding, adding, composing, styling, and debugging components, including chat interfaces.

Searching component registries, adding components with the project's package manager, composing pages from existing parts, applying built-in variants, and using semantic colors.

It helps developers reuse existing components and keep interfaces consistent with the project's design system instead of writing every control from scratch.

shadcn — Skill by shadcn-ui

Install

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.

agentmods

npx agentmods add skills/shadcn-ui/ui/shadcn

Any agent

npx skills add shadcn-ui/ui --skill shadcn

Clone the repo

git clone --depth 1 https://github.com/shadcn-ui/ui

Made for: Claude Code, Codex.

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,866 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00094	$0.04866
Opus 5	$0.00047	$0.02433
Sonnet 5	$0.00019	$0.00973
Haiku 4.5	$0.00009	$0.00487

Measured yesterday against content hash deba6c5152d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shadcn 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 yesterday.

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.

Origin

Copies of this mod

8 near-identical copies found in the catalogue:

shadcn — 100% identical, 0 lines differ
shadcn — 100% identical, 0 lines differ
shadcn — 100% identical, 0 lines differ
shadcn — 100% identical, 40 lines differ
shadcn — 95% identical, 47 lines differ
shadcn — 95% identical, 47 lines differ
shadcn — 95% identical, 47 lines differ
shadcn — 95% identical, 47 lines differ

skills/shadcn/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shadcn/ui

A framework for building ui, components and design systems. Components are added as source code to the user's project via the CLI.

IMPORTANT: Run all CLI commands using the project's package runner: npx shadcn@latest, pnpm dlx shadcn@latest, or bunx --bun shadcn@latest — based on the project's packageManager. Examples below use npx shadcn@latest but substitute the correct runner for the project.

Current Project Context

!`npx shadcn@latest info --json`

The JSON above contains the project config and installed components. Use npx shadcn@latest docs <component> to get documentation and example URLs for any component.

Principles

Use existing components first. Use npx shadcn@latest search to check registries before writing custom UI. Check community registries too.
Compose, don't reinvent. Settings page = Tabs + Card + form controls. Dashboard = Sidebar + Card + Chart + Table.
Use built-in variants before custom styles. variant="outline", size="sm", etc.
Use semantic colors. bg-primary, text-muted-foreground — never raw values like bg-blue-500.

Critical Rules

These rules are always enforced. Each links to a file with Incorrect/Correct code pairs.

Styling & Tailwind → styling.md

className for layout, not styling. Never override component colors or typography.
No space-x-* or space-y-*. Use flex with gap-*. For vertical stacks, flex flex-col gap-*.
Use size-* when width and height are equal. size-10 not w-10 h-10.
Use truncate shorthand. Not overflow-hidden text-ellipsis whitespace-nowrap.
No manual dark: color overrides. Use semantic tokens (bg-background, text-muted-foreground).
Use cn() for conditional classes. Don't write manual template literal ternaries.
No manual z-index on overlay components. Dialog, Sheet, Popover, etc. handle their own stacking.

Forms & Inputs → forms.md

Read the full file on GitHub · 278 lines

Files

What ships with it

14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

yesterday First seen · 278 lines · 94 tokens per session scan A deba6c5152d9

Subscribe to this mod's changes

shadcn is a skill published in the GitHub repository shadcn-ui/ui (122,642 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 4,866 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.

Debugging Frontend ReAct Writing and docs base-ui components laravel nextjs radix-ui

magic-ui

Use this skill when users want to add, customize, or troubleshoot Magic UI components in React/Next.js projects. It covers component selection, shadcn registry installation (@magicui/), integration patterns, and practical quality checks for accessibility and maintainability.

magicuidesign/magicui · 56 tokens

coss-particles

Index of all COSS UI particle examples. Use when implementing UI features to find copy-paste-ready component patterns built on coss primitives. Each particle has a description and a JSON URL for easy installation.

cosscom/coss · 46 tokens

coss

Helps implement coss UI components correctly. Use when building UIs with coss primitives and patterns (buttons, dialogs, selects, forms, menus, tabs, segmented controls, inputs, toasts, etc.), migrating from shadcn/Radix to coss/Base UI, composing trigger-based overlays, or troubleshooting coss component behavior.…

cosscom/coss · 85 tokens

primeng-v19-patterns

PrimeNG v19 component patterns, Design Tokens, and Tailwind conventions.

robiparvez/claude-code-guidelines · 22 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens