shadcn/lint is an open-source, agent-first linter for Tailwind design systems from the shadcn team that enforces your own rules so AI coding agents produce on-brand components instead of off-spec markup. Announced on September 15, 2026, it targets the exact pain of letting agents scaffold UI: generated code that technically runs but quietly breaks your design system.
Core Features
- Enforces your own design rules rather than generic style opinions, keeping generated components inside the system.
- Gives agents specific error explanations and suggested fixes derived from your existing components, variants, and themes.
- Reduces violation counts and rework rounds during AI-assisted development by catching issues before merge.
- Integrates with agent workflows used in Claude, Cursor, and similar coding tools, and ships free on GitHub.
Use Cases
- Teams that let agents write Tailwind and need consistency across dozens of generated screens.
- Maintaining a single source of truth for spacing, color, and variant conventions in generated code.
- Catching off-brand utility classes and missing theme tokens automatically in CI.
Pricing
shadcn/lint is free and open-source, distributed through the shadcn GitHub repository with no license fee or usage cap.
Pros and Cons
- Pros: Turns your design rules into agent-checkable lint; free and open-source; cuts rework loops.
- Cons: Tailwind and shadcn only; not a replacement for a general-purpose linter.
Our Take: Best for shops that already lean on agents to build Tailwind UI and want guardrails without manual review; the trade-off is that it is purpose-built for the Tailwind and shadcn ecosystem, not a general-purpose linter for other frameworks. Find complementary tooling in our AI Coding category.
