Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/marcusgoll/Spec-Flownpx agentmods add skills/marcusgoll/spec-flow/shadcn-integrationWrote 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/marcusgoll/spec-flow/shadcn-integration)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/shadcn-integration"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/shadcn-integration/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/marcusgoll/spec-flow/shadcn-integration"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/shadcn-integration.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 | $0.00053 | $0.02604 |
| Opus 5.5 | $0.00021 | $0.01042 |
| Sonnet 5.5 | $0.00011 | $0.00521 |
| Haiku 4.5 | $0.00005 | $0.00260 |
Grade A, and why
shadcn-integration 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Key Principle: OKLCH tokens remain the source of truth. shadcn CSS variables are aliases that reference OKLCH tokens, not hardcoded values.
This skill is auto-invoked when:
- User runs
/init --tokens --shadcn - User asks to add shadcn components to a project
- Customizing shadcn theme colors or styles
- Setting up Next.js with shadcn/ui
Benefits:
- WCAG-compliant colors via OKLCH with perceptual uniformity
- Full shadcn component library compatibility
- 8 customization options without manual CSS editing
- Automatic dark mode support
- Menu-specific theming with variants
<quick_start> <trigger_pattern> Auto-invoke when:
/init --tokens --shadcncommand is run- User asks to "add shadcn" or "setup shadcn"
- User wants to customize theme colors
- Setting up new Next.js project with components </trigger_pattern>
<basic_workflow> Step 1: Run the questionnaire (8 questions)
/init --tokens --shadcn
Step 2: Review generated files
design/systems/shadcn-variables.css- CSS variablescomponents.json- shadcn CLI configcomponents/ui/menu-variants.ts- Menu styling
Step 3: Import in globals.css
@import '../design/systems/shadcn-variables.css';
Step 4: Add components
npx shadcn@latest add button card dropdown-menu
</basic_workflow>
<immediate_value> Before:
- Manual theme.css editing with hardcoded HSL values
- Inconsistent color contrast
- No systematic menu theming
- Dark mode requires manual CSS duplication
After:
- 8 questions → complete theme system
- OKLCH ensures WCAG-compliant contrast
- Menu variants via tailwind-variants
- Automatic dark mode via CSS variables </immediate_value> </quick_start>
Use AskUserQuestion tool with these questions in sequence:
- Style Preset → Determines shadcn style + density
- Base Color → Generates OKLCH primary scale (11 shades)
- Theme Mode → Configures light/dark/system preference
- Icon Library → Sets package and components.json config
- Font Family → Configures next/font
- Border Radius → Sets --radius CSS variable
- Menu Color → Generates menu background tokens
- Menu Accent → Generates menu active state tokens
Run the token generation script:
node .spec-flow/scripts/node/generate-shadcn-tokens.js --config answers.json
Generated files:
design/systems/shadcn-variables.css- shadcn CSS variable aliasesdesign/systems/tokens.json- Full token definitionscomponents.json- shadcn CLI configurationcomponents/ui/menu-variants.ts- Menu styling with tailwind-variants
Based on questionnaire answers:
# Icon library (based on choice)
pnpm add lucide-react # or @heroicons/react or @phosphor-icons/react
# shadcn dependencies
pnpm add tailwindcss-animate class-variance-authority clsx tailwind-merge
# For menu variants
pnpm add tailwind-variants
Update app/layout.tsx with font configuration:
import { Inter } from 'next/font/google'
const fontSans = Inter({
subsets: ['latin'],
variable: '--font-sans',
})
export default function RootLayout({ children }) {
return (
<html lang="en" className={fontSans.variable}>
<body>{children}</body>
</html>
)
}
Now users can add components that automatically use the generated theme:
npx shadcn@latest add button
npx shadcn@latest add card
npx shadcn@latest add dropdown-menu
npx shadcn@latest add dialog
Components will use CSS variables from shadcn-variables.css.
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 · 344 lines · 53 tokens per session scan A 3b783459279c
shadcn-integration is a skill published in the GitHub repository marcusgoll/Spec-Flow (96 stars, last pushed 29d ago), licensed MIT. It adds 53 tokens to every session and 2,604 once invoked, about $0.0002 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 2026-09-03.
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.
antigravity-design-expert
Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.
team-ui
Orchestrate the UI team through the UX pipeline — authoring, visual design, implementation, review, polish. Uses /ux-design, /ux-review, studio templates.
design-shiny-ui
Design Shiny application UIs using bslib for theming, layoutcolumns for responsive grids, value boxes, cards, and custom CSS/SCSS. Covers page layouts, accessibility, and brand consistency. Use when building a new Shiny app UI from scratch, modernizing an existing app from fluidPage to bslib, applying brand theming…
token-architecture
Design and govern a three-tier CSS custom property token system (primitive → semantic → component), including semantic alias layers, light/dark theming, and DTCG-compatible source generation. Triggers on "design a three-tier token system for our web app", "audit our CSS tokens for hardcoded value drift", "add a…
interaction-design
Use when someone asks how one screen or component should respond to actions, validate input, transition, recover, or feel in use. Produces behavioral and state specifications for the interaction. Use information-architecture for hierarchy, user-flow for cross-screen routes, and creative-direction for visual mood…