Modular rulebook for AI coding agents on Next.js, Supabase, shadcn/ui, and Zustand.
vibe-stack-rules is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo clone imfaisii/vibe-stack-rulesOpen or clone the template repository.
Move the relevant AGENTS.md content into your project root.
Update project-specific commands, environment rules, and sensitive areas.
This repository provides a set of modular, focused rule files for AI coding agents (like Claude Code, Cursor) when building with the vibe stack: Next.js, Supabase, shadcn/ui, and Zustand. Instead of a single large CLAUDE.md, it splits rules into small files by concern, making agents more reliable and context-aware. Drop the template into your project root and your agent will follow best practices automatically.
vibe-stack-rules is a curated collection of engineering rules designed for AI-powered coding agents working with the modern web stack: Next.js (App Router), Supabase, shadcn/ui, and Zustand. The project addresses a common pain point: monolithic CLAUDE.md files that cause context pollution, degrade adherence, and mix project-specific instructions with generic stack rules. The solution is a lean CLAUDE.md at the project root that describes the specific application, plus a stack/ folder containing focused rule files (~150-250 lines each) covering foundations, server-side rendering, Supabase client management, client-side state with Zustand, and discipline/anti-patterns. These files are imported via @path syntax and loaded automatically by Claude Code. Additionally, the repo includes a Claude Design-to-Next.js skill that converts Claude Design bundles into Next.js + TSX + Tailwind + shadcn components. The skill is available both as a plugin for /plugin install and bundled in the template for degit installs. The target stack: Next.js ≥15, Supabase JS v2, shadcn/ui, Zustand v5, TypeScript strict mode, Tailwind CSS v4, and React 19. The rules enforce best practices like async page.tsx, proper Supabase client scoping, Zustand store factories, and avoiding common pitfalls.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 98 days ago.
1 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
Set up a new Next.js project with AI agent rules for consistent code generation.
Prevent common bugs in vibe-coded apps like async page issues, Supabase client leaks, and Zustand state leaks.
Standardize team coding practices across multiple projects using the same stack.
Quickly onboard AI agents to a project's specific stack conventions without manual prompting.
Convert Claude Design mockups into production-ready Next.js components with proper structure.
Agent instruction templates should be reviewed before use because they can change coding-agent behavior across an entire repository.
Avoid copying rules that grant broad filesystem, shell, network, or secret access without adapting them to your project.
1
Stars
0
Forks
0
Issues
MIT
License
A drop-in AGENTS.md file that makes coding agents behave like senior engineers, eliminating sycophancy and forcing verification.
Convert and sync AI coding-agent rule files between formats with zero dependencies.
Generate AGENTS.md from your codebase in one command. Free, instant, no API key.
Modular rulebook for AI coding agents on Next.js, Supabase, shadcn/ui, and Zustand.
Vibe coders who use AI agents to build full-stack Next.js applications., Developers tired of fixing the same bugs repeatedly in AI-generated code., Teams wanting to enforce consistent patterns across AI-assisted projects.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Agent instruction templates should be reviewed before use because they can change coding-agent behavior across an entire repository. Avoid copying rules that grant broad filesystem, shell, network, or secret access without adapting them to your project.
Similar or complementary options to evaluate include agents-md, agentsync, agentseed.
Jun 7, 2026
2 security/trust notes recorded.
Setup difficulty is 1/5.