What is vibe-stack CLAUDE.md?

A project-memory file containing Vibestack's stack, setup commands, workflow, and development rules for Claude Code. It describes the main technologies and how optional services behave.

It helps an agent start the app, understand its framework and services, follow the repository workflow, and know which tools are used for testing, styling, deployment, authentication, billing, and storage.

It gives an AI coding assistant the background needed to work consistently in the repository. It also records the commands and constraints that prevent common setup and maintenance mistakes.

vibe-stack CLAUDE.md — Instructions file for coding agents by f-amine: A project-memory file containing Vibestack's stack, setup commands, w

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/f-amine/vibe-stack/claude-md

Clone the repo

git clone --depth 1 https://github.com/f-amine/vibe-stack

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/f-amine/vibe-stack/claude-md.svg)](https://agentmods.dev/instructions/f-amine/vibe-stack/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/f-amine/vibe-stack/claude-md"><img src="https://agentmods.dev/badge/instructions/f-amine/vibe-stack/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,669 This file is loaded in full into every session.

When invoked 1,669 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.

Model	Per session	Once invoked
Fable 5	$0.01669	$0.01669
Opus 5	$0.00834	$0.00834
Sonnet 5	$0.00334	$0.00334
Haiku 4.5	$0.00167	$0.00167

Measured yesterday against content hash 77eb4b5546f2, 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 CLAUDE.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 yesterday.

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.

CLAUDE.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project memory for Claude Code

Pre-load this file when working in this repo. This is vibestack — an opinionated, AI-first SaaS starter. Stack pre-wired, every Claude Code skill vendored in .claude/skills/. See CONTEXT.md for positioning and ADR-0004.

Stack

Turborepo + pnpm; Next.js 16 + React 19; Tailwind v4 + shadcn; Better Auth 1.6 (email/pw, magic-link, Google, passkeys, 2FA, org plugin, admin plugin, rate-limit); Drizzle 0.45 + Postgres; tRPC v11; Zod v4; Polar.sh billing; Resend + React Email; Cloudflare R2; PostHog + GA4; Sentry; next-intl (EN + FR); Biome v2; Vitest + Playwright; Dokploy + docker-compose; nightly pg_dump → R2.

Workflow

Skills are vendored in .claude/skills/. No install step.

Clone-to-running-app: npx create-vibestack my-saas (interactive wizard: rename, feature toggles, optional keys, .env) or pnpm init:app in an existing clone; /setup is the conversational version inside Claude Code. Zero-key boot: the app boots with only DATABASE_URL + BETTER_AUTH_SECRET (+ URL vars) — third-party features degrade or hide until their keys exist (auth emails print to the dev console, billing UI hides without Polar, storage errors only when used without R2, /api/health reports them as disabled). See ADR-0009.
Product design: /grill-with-docs → /to-prd → /to-issues
Frontend / UI design: /impeccable is mandatory. Any task touching UI, components, pages, theming, typography, motion, layout, or visual polish must invoke /impeccable first — even if the user did not name the skill. Includes new pages, redesigns, "make this look better", color/spacing tweaks, empty states, error states, copy.
Instagram Reels / short-form video / TikTok-shaped content: route to /video-writer. Any request to "make a reel", "generate a video", "produce a short video about X", or any Instagram / TikTok / Shorts content intent spawns the swarm (researcher → script writer → [voice + SFX + music]parallel → motion designer → renderer → publisher). Reels are pure typographic / UI-mockup composition (packages/video/src/compositions/Reel.tsx) — no AI-generated stills on this surface; they read as generic and undercut the editorial register. Default output: 60s 9:16 MP4 at apps/marketing/public/reels/<slug>.mp4. Requires GOOGLE_AI_API_KEY (script) and ELEVENLABS_API_KEY (voice + SFX). Music = curated local library under packages/video/assets/music/<mood>/. See ADR-0008.
Long-form blog posts / journal articles / content marketing: route to /blog-writer. Any request to "write a blog post", "generate an article", "fill the journal", or content of a deep-dive shape spawns the swarm (researcher → writer → SEO editor + image producer in parallel → publisher). Output is a 15-20 minute read (3500-5000 words) with multiple Gemini-generated inline images, full frontmatter, JSON-LD ready, dropped as a draft into apps/marketing/content/blog/. Topics may be product-adjacent (domain deep-dives count); the post stays a draft until a human flips draft: false. See ADR-0007.
SEO / GEO / Search Console / organic traffic: route to toprank. Any task about search rankings, organic traffic, Google Search Console, indexing, keyword research, content gaps, meta tags, schema markup, Core Web Vitals, sitemap, robots, AI-search visibility (ChatGPT, Perplexity, Gemini), or Generative Engine Optimization runs through the toprank plugin (/toprank:seo-analysis, /toprank:keyword-research, /toprank:content-writer, /toprank:geo-optimizer, /toprank:meta-tags-optimizer, /toprank:schema-markup-generator, /toprank:broken-link-checker, /toprank:seo-page). Toprank uses live GSC + PageSpeed Insights data, so install it during /setup and let it OAuth on first run. See ADR-0006.
Google Ads / Meta Ads / paid acquisition: also toprank (/toprank:google-ads-audit, /toprank:google-ads-manage, /toprank:meta-ads-audit, /toprank:meta-ads-manage). Connects via the NotFair-GoogleAds and NotFair-MetaAds HTTP MCPs configured in .mcp.json.
Build: /tdd → /review
Bug: /diagnose → /tdd
Refactor: /improve-codebase-architecture → ADR draft → /to-issues
Spike: /prototype (throwaway, then commit to real implementation)
Inbox: /triage (sort incoming issues into a state machine)

Read the full file on GitHub · 65 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.

yesterday First seen · 65 lines · 1,669 tokens per session scan A 77eb4b5546f2

Subscribe to this mod's changes

vibe-stack CLAUDE.md is an instructions file published in the GitHub repository f-amine/vibe-stack (21 stars, last pushed 2mo ago), licensed MIT. It adds 1,669 tokens to every session, about $0.0083 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 2026-09-03.

Building agents Planning ai better-auth claude claude-code drizzle-orm nextjs

openmonetis AGENTS.md

AGENTS.md instructions for felipegcoutinho/openmonetis, covering agents.md - openmonetis, related projects, critical rules, architecture and feature-first.

felipegcoutinho/openmonetis · 4,004 tokens

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

vibe-stack CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Project memory for Claude Code

Stack

Workflow

What this file has done since we first saw it

Other instructions, from other repositories

openmonetis AGENTS.md

codeguide-starter-fullstack CLAUDE.md

create-better-t-stack AGENTS.md

kan AGENTS.md

flarestarter AGENTS.md

flarestarter CLAUDE.md