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 Cratis/AI --skill shadcngit clone --depth 1 https://github.com/Cratis/AIWrote 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/cratis/ai/shadcn)<a href="https://agentmods.dev/skills/cratis/ai/shadcn"><img src="https://agentmods.dev/badge/skills/cratis/ai/shadcn/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/cratis/ai/shadcn"><img src="https://agentmods.dev/badge/skills/cratis/ai/shadcn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00080 | $0.01803 |
| Opus 5.5 | $0.00032 | $0.00721 |
| Sonnet 5.5 | $0.00016 | $0.00361 |
| Haiku 4.5 | $0.00008 | $0.00180 |
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 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.
This is a copy
92% identical to shadcn — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shadcn/ui Community Best Practices
Comprehensive best practices guide for shadcn/ui applications, maintained by the shadcn/ui community. Contains 42 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.
When to Apply
Reference these guidelines when:
- Writing new shadcn/ui components or composing primitives
- Implementing forms with React Hook Form and Zod validation
- Building data tables or handling large dataset displays
- Customizing themes or adding dark mode support
- Reviewing code for accessibility compliance
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Component Architecture | CRITICAL | arch- |
| 2 | Accessibility Preservation | CRITICAL | ally- |
| 3 | Styling & Theming | HIGH | style- |
| 4 | Form Patterns | HIGH | form- |
| 5 | Data Display | MEDIUM-HIGH | data- |
| 6 | Component Composition | MEDIUM | comp- |
| 7 | Performance Optimization | MEDIUM | perf- |
| 8 | State Management | LOW-MEDIUM | state- |
Quick Reference
1. Component Architecture (CRITICAL)
arch-use-asChild-for-custom-triggers- Use asChild prop for custom trigger elementsarch-preserve-radix-primitive-structure- Maintain Radix compound component hierarchyarch-extend-variants-with-cva- Use Class Variance Authority for type-safe variantsarch-use-cn-for-class-merging- Use cn() utility for safe Tailwind class mergingarch-forward-refs-for-composable-components- Forward refs for form and focus integrationarch-isolate-component-variants- Separate base styles from variant-specific styles
2. Accessibility Preservation (CRITICAL)
What ships with it
43 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.
- AGENTS.md 9.2 KB
- references/ally-ensure-color-contrast.md 1.7 KB
- references/ally-maintain-focus-management.md 2.0 KB
- references/ally-preserve-aria-attributes.md 2.2 KB
- references/ally-preserve-keyboard-navigation.md 2.0 KB
- references/ally-provide-sr-only-labels.md 1.8 KB
- references/arch-extend-variants-with-cva.md 1.9 KB
- references/arch-forward-refs-for-composable-components.md 2.0 KB
- references/arch-isolate-component-variants.md 2.2 KB
- references/arch-preserve-radix-primitive-structure.md 1.6 KB
- references/arch-use-asChild-for-custom-triggers.md 1.8 KB
- references/arch-use-cn-for-class-merging.md 1.7 KB
- references/comp-combine-command-with-popover.md 3.1 KB
- references/comp-compose-with-compound-components.md 3.0 KB
- references/comp-create-reusable-form-fields.md 3.8 KB
- references/comp-nest-dialogs-correctly.md 3.1 KB
- references/comp-use-drawer-for-mobile-modals.md 3.3 KB
- references/comp-use-slot-pattern-for-flexibility.md 3.2 KB
- references/data-empty-states-with-guidance.md 2.9 KB
- references/data-paginate-server-side.md 2.8 KB
- references/data-use-skeleton-loading-states.md 2.6 KB
- references/data-use-tanstack-table-for-complex-tables.md 3.1 KB
- references/data-virtualize-large-lists.md 2.4 KB
- references/form-handle-async-validation.md 2.7 KB
- references/form-reset-form-state-correctly.md 2.3 KB
- references/form-show-validation-errors-correctly.md 1.7 KB
- references/form-use-react-hook-form-integration.md 2.9 KB
- references/form-use-zod-for-schema-validation.md 2.5 KB
- references/perf-avoid-unnecessary-rerenders-in-forms.md 2.6 KB
- references/perf-debounce-search-inputs.md 2.2 KB
- references/perf-lazy-load-heavy-components.md 2.5 KB
- references/perf-memoize-expensive-renders.md 2.4 KB
- references/perf-optimize-icon-imports.md 1.9 KB
- references/state-colocate-state-with-components.md 2.7 KB
- references/state-lift-state-to-appropriate-level.md 2.6 KB
- references/state-prefer-uncontrolled-for-simple-inputs.md 2.5 KB
- references/state-use-controlled-dialog-state.md 3.3 KB
- references/style-avoid-important-overrides.md 1.7 KB
- references/style-consistent-spacing-scale.md 1.9 KB
- references/style-dark-mode-support.md 2.2 KB
- references/style-responsive-design-patterns.md 2.5 KB
- references/style-use-css-variables-for-theming.md 1.7 KB
- references/style-use-tailwind-theme-extend.md 1.9 KB
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 · 119 lines · 80 tokens per session scan A 2afd14757e68
shadcn is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,803 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to shadcn, differing in 32 lines, and is treated as a copy.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…