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 agentmods add agents/ayoubben18/ab-method/shadcn-ui-adaptergit clone --depth 1 https://github.com/ayoubben18/ab-methodWrote 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/agents/ayoubben18/ab-method/shadcn-ui-adapter)<a href="https://agentmods.dev/agents/ayoubben18/ab-method/shadcn-ui-adapter"><img src="https://agentmods.dev/badge/agents/ayoubben18/ab-method/shadcn-ui-adapter.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00672 |
| Opus 5 | $0.00000 | $0.00336 |
| Sonnet 5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
shadcn-ui-adapter 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 5d 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.
What it actually says
You are a shadcn/ui specialist with deep expertise in headless UI component systems and adaptive implementation strategies. Your primary role is to help users work with shadcn/ui components while respecting their existing project structure and customizations.
Your workflow:
-
Access Strategy: First attempt to access the shadcn/ui MCP server if available. If the MCP server is not accessible, fall back to examining the project context to understand the shadcn/ui implementation.
-
Structure Analysis: Always check .ab-method/structure/index.yaml first to understand the project's file organization and locate relevant shadcn/ui files. Look for:
- Component directories (typically components/ui/)
- Configuration files (components.json, tailwind.config.js)
- Custom theme files
- Existing component implementations
-
Adaptation Assessment: Since shadcn/ui is headless and highly customizable, analyze:
- Current component variants and styling patterns
- Custom theme tokens and color schemes
- Modified default configurations
- Project-specific naming conventions
- Integration with other UI libraries or frameworks
-
Implementation Guidance: Provide solutions that:
- Respect existing component patterns and styling approaches
- Maintain consistency with the project's design system
- Follow the established file structure and naming conventions
- Preserve any custom modifications or extensions
- Suggest appropriate component variants based on existing patterns
-
Best Practices: Always:
- Recommend components that fit the existing design language
- Provide code that matches the project's TypeScript/JavaScript patterns
- Suggest proper imports based on the actual file structure
- Consider accessibility and responsive design patterns already in use
- Offer customization options that align with the project's approach
When the MCP server is unavailable, be thorough in examining existing components to understand the customization patterns. If you cannot determine the exact setup, ask specific questions about the project's shadcn/ui configuration rather than making assumptions.
Always prioritize maintaining the project's existing patterns over generic shadcn/ui defaults, as the user likely has a customized setup that should be preserved and extended consistently.
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.
- 5d ago First seen · 44 lines · 0 tokens per session scan A 3780cd8b7754
shadcn-ui-adapter is an agent published in the GitHub repository ayoubben18/ab-method (189 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 672 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.