agentmods.dev

vibe-stack AGENTS.md

A project guide that tells AI coding agents how to work in a Next.js and Supabase application. It describes the project’s tools, folder layout, and rules for writing code.

In plain words
What is it for?
Use it to guide AI agents working on authentication, databases, payments, email, validation, styling, and other parts of this application.
Why use it?
It gives an agent the context it needs before changing the code, reducing guesses and inconsistent implementations.

Instructions file for CodexOpenCode

7 2d ago A scan 1,353 tokens original MIT
View the source file vibestackdev/vibe-stack
Install

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.

agentmods
npx agentmods add instructions/vibestackdev/vibe-stack/agents-md
Clone the repo
git clone --depth 1 https://github.com/vibestackdev/vibe-stack

Made for: Codex, OpenCode.

Per session 1,353 This file is loaded in full into every session.
When invoked 1,353 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01353 $0.01353
Opus 5 $0.00677 $0.00677
Sonnet 5 $0.00271 $0.00271
Haiku 4.5 $0.00135 $0.00135

Measured 2d ago against content hash 207692b7d110, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibe-stack AGENTS.md 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 2d 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.

AGENTS.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — AI Coding Agent Instructions

This file provides project context and instructions for AI coding agents (Cursor, Claude, Copilot, Windsurf, Cline) working within this codebase.

Project Overview

Vibe Stack is a production-ready Next.js 15 + Supabase boilerplate designed for AI-assisted development. It includes 22 .mdc architecture rule files that constrain AI models to generate secure, modern, production-grade code.

Tech Stack

  • Framework: Next.js 15 (App Router, Server Components, Server Actions)
  • Runtime: React 19
  • Database & Auth: Supabase (PostgreSQL, Auth with SSR, Row Level Security)
  • Payments: Stripe (Checkout Sessions, Webhooks, Customer Portal)
  • Email: Resend (transactional email with HTML templates)
  • Validation: Zod (runtime validation at every boundary)
  • Styling: Tailwind CSS + shadcn/ui
  • Language: TypeScript (strict mode, no any)

Architecture Principles

  1. Server Components by default — Only use 'use client' when hooks or event handlers are required
  2. getUser() over getSession() — Server-side auth MUST use getUser() for JWT verification
  3. @supabase/ssr only — Never import from the deprecated @supabase/auth-helpers-nextjs
  4. Zod at every boundary — All user input validated before processing
  5. RLS on every table — Row Level Security is mandatory, never optional

Directory Structure

src/
├── app/                    # Next.js App Router pages and layouts
│   ├── (auth)/             # Auth route group (login, signup)
│   │   ├── actions.ts      # Auth server actions with Zod validation
│   │   ├── login/page.tsx  # Login page (Server Component)
│   │   └── signup/page.tsx # Signup page (Server Component)
│   ├── auth/confirm/       # PKCE email verification callback
│   ├── dashboard/          # Protected pages (requires auth)
│   ├── api/webhooks/       # External webhook handlers (Stripe)
│   ├── layout.tsx          # Root layout (fonts, metadata, dark mode)
│   ├── page.tsx            # Landing page
│   ├── loading.tsx         # Global loading state
│   ├── error.tsx           # Global error boundary
│   └── not-found.tsx       # Custom 404
├── lib/                    # Business logic & integrations
│   ├── supabase/           # Server + Client factories + middleware helper
│   ├── stripe/             # Checkout session + customer portal helpers
│   ├── email/              # Resend email templates (welcome, password reset)
│   ├── env.ts              # Type-safe environment variable access
│   └── utils.ts            # cn() helper and general utilities
├── types/                  # Shared TypeScript types
│   └── index.ts            # ActionResponse<T>, UserProfile, PaginatedResponse
└── middleware.ts            # Session refresh entry point

.cursor/
├── rules/                  # 22 .mdc architecture rules (auto-loaded by Cursor)
└── mcp.json                # 4 MCP server configurations

docs/
├── VIBE-CODING.md          # The 3-stage agentic loop framework
├── ARCHITECTURE.md         # 8 Architecture Decision Records
└── MCP-SETUP.md            # MCP server setup guide

n8n-workflows/              # 3 importable n8n automation templates

Read the full file on GitHub · 132 lines

Changes

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.

  1. 2d ago First seen · 132 lines · 1,353 tokens per session scan A 207692b7d110

Subscribe to this mod's changes

vibe-stack AGENTS.md is an instructions file published in the GitHub repository vibestackdev/vibe-stack (7 stars, last pushed 2d ago), licensed MIT. It adds 1,353 tokens to every session, about $0.0068 per session on Opus 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 2026-08-31.

DatabasesFrontendReActWriting and docsaiboilerplatecursormcpnextjs
Related

Other instructions, from other repositories

codeguide-starter-fullstack CLAUDE.md

Claude Code instructions for CodeGuide-dev/codeguide-starter-fullstack, covering claude code task management guide, documentation available, mandatory task management workflow, step 1: discover tasks (mandatory) and step 2: start each task (mandatory).

CodeGuide-dev/codeguide-starter-fullstack · 621 tokens

magicui AGENTS.md

Instructions for magicuidesign/magicui, covering project context, key principles, before writing code, rules and accessibility (a11y).

magicuidesign/magicui · 3,445 tokens

core CLAUDE.md

Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.

module-federation/core · 3,933 tokens

web-interface-guidelines AGENTS.md

Instructions for vercel-labs/web-interface-guidelines, covering interactions, keyboard, targets & input, forms and state & navigation.

vercel-labs/web-interface-guidelines · 1,887 tokens

ssgoi AGENTS.md

Instructions for meursyphus/ssgoi, covering ssgoi and releasing.

meursyphus/ssgoi · 147 tokens

coss AGENTS.md

AGENTS.md instructions for cosscom/coss, covering agents.md and main documentation.

cosscom/coss · 48 tokens