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 PyModel/react-frontend-skills --skill shadcngit clone --depth 1 https://github.com/PyModel/react-frontend-skillsWrote 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/pymodel/react-frontend-skills/shadcn)<a href="https://agentmods.dev/skills/pymodel/react-frontend-skills/shadcn"><img src="https://agentmods.dev/badge/skills/pymodel/react-frontend-skills/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/pymodel/react-frontend-skills/shadcn"><img src="https://agentmods.dev/badge/skills/pymodel/react-frontend-skills/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 | $0.00016 | $0.01747 |
| Opus 5.5 | $0.00006 | $0.00699 |
| Sonnet 5.5 | $0.00003 | $0.00349 |
| Haiku 4.5 | $0.00002 | $0.00175 |
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 23d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- shadcn — 92% identical, 32 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shadcn/ui Community Best Practices
Current best-practices guide for shadcn/ui applications. Before applying primitive-specific guidance, inspect whether the checked-in components use Radix UI or Base UI; current shadcn supports both (Base UI is the default for new projects) and their composition APIs differ. Component installs and upgrades go through the current CLI (v4), which resolves namespaced registries.
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 the generated primitive's composition APIarch-current-cli-registry- Use the current CLI for component lifecycle (v4, registries, MCP)arch-unified-radix-package- Import primitives from the unified radix-ui packagearch-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
What ships with it
44 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.
- 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-current-cli-registry.md 2.2 KB
- references/arch-extend-variants-with-cva.md 1.9 KB
- references/arch-forward-refs-for-composable-components.md 2.3 KB
- references/arch-isolate-component-variants.md 2.2 KB
- references/arch-preserve-radix-primitive-structure.md 1.6 KB
- references/arch-unified-radix-package.md 1.7 KB
- references/arch-use-asChild-for-custom-triggers.md 1.5 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 3.1 KB
- references/data-use-skeleton-loading-states.md 2.7 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 3.1 KB
- references/form-use-zod-for-schema-validation.md 2.6 KB
- references/perf-avoid-unnecessary-rerenders-in-forms.md 2.6 KB
- references/perf-debounce-search-inputs.md 2.4 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 2.8 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 1.8 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.
- 23d ago Changed · -4 lines · -47 tokens per session 5124d3bede90
- 1mo ago Changed · +2 lines d98dc0b47d39
- 1mo ago First seen · 113 lines · 63 tokens per session scan A ce72dfa4a963
shadcn is a skill published in the GitHub repository PyModel/react-frontend-skills (38 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 1,747 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 2026-08-31.
Other skills, from other repositories
lov-kill-emoji
A UI cleanup tool that replaces unsuitable emoji in visible interface elements with matching icons or short text. It checks the surrounding meaning before changing anything.
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
cometchat-react-v7-customization
Theme and brand the React v7 UI Kit — light/dark mode, CSS custom-property design tokens, per-component style overrides. Triggers: 'change chat colors', 'dark mode chat', 'match my brand', 'customize cometchat theme', 'override message list styles'.
lov-maintain-partners
Maintain the Skill Publisher website's partners section AND align partner logo rows on event posters / hero strips: reuse lov-find-logo for brand logo discovery, normalize collected logos to a 240px-tall content canvas (retina-ready), rasterize SVGs via rsvg-convert before normalizing (so SVG viewBox padding gets…
lov-oh-my-landingpage
A landing-page creation and redesign skill that derives a product’s positioning, story, and visual direction from its actual product and brand facts. It then implements the page responsively and checks the result against the intended product message.
lov-frontend-design
A frontend design guide for turning requirements, existing screens, and real media into usable pages and components. It covers visual design, navigation, interaction details, animation, images, audio, and video.