Skip to content
STACK IT FAST
Share
AI coding agent rules and skills

Cursor rules, AGENTS.md & agent skills.

Stop rewriting system prompts. Copy battle-tested AGENTS.md, Cursor rules, CLAUDE.md and Claude Code skills (SKILL.md), each configured for a real production architecture.

Not sure which file your tool reads? AGENTS.md vs CLAUDE.md vs .cursorrules, with data from 113 repos

Rule and skill sets
32
Technologies covered
76
Free, copy-paste ready
100%

Matching rule sets

Showing 8 of 32

astro-static-content/AGENTS.md · 72 linesAstro Static Site + Content Collections + TailwindRules for a fully static Astro 7 site: content collections with Zod schemas, zero-JS pages with rare islands, build-time sitemap and OG images, and static hosting on Cloudflare. starter AstroTailwind CSSTypeScriptMDXexpo-sqlite-local-first/AGENTS.md · 71 linesExpo + SQLite + Drizzle (Local-First Mobile App)Rules for an offline-first Expo SDK 57 app: expo-sqlite with Drizzle migrations bundled in the app, no backend by default, sync as an optional module, EAS Build and Update. starter ExpoReact NativeExpo RouterSQLitehono-jsx-internal-tools/AGENTS.md · 69 linesHono JSX + Bun + SQLite (Server-Rendered Internal Tools)Rules for internal tools rendered on the server with Hono JSX on Bun: forms over fetch, htmx where needed, an OAuth allow-list, Drizzle over SQLite or a read replica, and cron in the same process. starter HonoBunSQLiteDrizzlenextjs-drizzle-supabase/AGENTS.md · 91 linesNext.js 16 + Drizzle ORM + SupabaseProduction guidelines for Next.js App Router, Drizzle ORM with postgres-js, Supabase Transaction Pooler (prepare: false), and RLS security. starter Next.jsDrizzleSupabaseTypeScriptnextjs-prisma-postgres/AGENTS.md · 89 linesNext.js 16 + Prisma ORM + PostgreSQLProduction guidelines for Next.js App Router, Server Actions, Prisma connection pooling, PgBouncer/Neon tuning, and Zod schema validation. starter Next.jsPrismaPostgreSQLTypeScriptnuxt-vue-postgres/AGENTS.md · 69 linesNuxt 4 + Vue + PostgreSQLProduction guidelines for Nuxt 4 server routes and universal rendering, Vue 3 Composition API, and PostgreSQL via a typed query layer. starter NuxtVuePostgreSQLSupabasesveltekit-postgres-drizzle/AGENTS.md · 78 linesSvelteKit + PostgreSQL + Drizzle ORMProduction guidelines for SvelteKit form actions and load functions, Drizzle ORM over PostgreSQL, and Svelte 5 runes-based reactivity. starter SvelteKitSveltePostgreSQLSupabasevite-react-hono-edge/AGENTS.md · 66 linesVite + React SPA + Hono (Edge API)Architecture guidelines for zero-server-lag single-page apps built with Vite and React, backed by a Hono API on Cloudflare Workers. starter ViteReactHonoTypeScript

Questions about rules and skills

Setting up AGENTS.md, CLAUDE.md, Cursor .mdc, SKILL.md and context boundaries.

What is the purpose of AGENTS.md and CLAUDE.md files?

AGENTS.md and CLAUDE.md are specialized system prompt guideline files placed in repository roots. They supply AI coding assistants (like Cursor, Claude Code, Windsurf, and AGY) with non-negotiable architectural boundaries, connection pooling rules, framework idioms, and forbidden anti-patterns to prevent hallucinations and maintain codebase consistency.

How do I use these rules in my local development environment?

Copy the generated AGENTS.md into your project root, or drop the .mdc file into .cursor/rules/ for Cursor — both are automatically indexed. Claude Code directly reads CLAUDE.md for project conventions and CLI commands.

What's the difference between AGENTS.md, CLAUDE.md, and the .mdc file?

AGENTS.md is the open, cross-tool standard read by 30+ agents (Codex, Cursor, Copilot, Jules, and more). CLAUDE.md adds Claude Code-specific CLI commands and conventions. The .mdc file is the modern Cursor Rules format with YAML frontmatter (description, globs, alwaysApply) that replaces the legacy single .cursorrules file.

What is the difference between a rule and an agent skill (SKILL.md)?

Rules (AGENTS.md, CLAUDE.md, .mdc) are always-on project instructions loaded from the repository root. An agent skill is a SKILL.md file with YAML frontmatter (name, description) that agents like Claude Code, Codex, and Cursor load on demand when a task matches its description. Every stack on this page ships in both forms, so you can pin the guidelines globally or let the agent pull them in only when it touches that stack.

How do I install one of these as a Claude Code skill?

Open any rule set and copy the SKILL.md cURL command, or run: curl -s --create-dirs -o .claude/skills/<slug>/SKILL.md https://stackitfast.com/rules/<slug>/SKILL.md. Claude Code discovers project skills under .claude/skills/ automatically; the same file works in any Agent Skills-compatible tool.

Why are stack-specific rules necessary over generic prompts?

Generic system prompts fail on crucial framework-specific edge cases—such as disabling prepared statements in Supabase transaction poolers (prepare: false), configuring Redis noeviction policies for BullMQ, or enforcing asyncpg pool pre-ping in FastAPI. Stack-specific rules provide verified, battle-tested solutions to real integration gotchas.

Are these rules based on real open-source architectures?

Yes. Every rule set in STACK IT FAST is derived directly from verified production repositories benchmarked in our directory, including Cal.com, PostHog, Supabase Studio, Sentry, Grafana, and Dub.

Need rules for your own constraints?

Take the two-minute survey for a stack matched to real architectures and a scaffolding prompt to start from.

Start the survey Not sure yet? Pick a roadmap