Borrowing it
Nothing to install: this file belongs to f-amine/vibe-stack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/f-amine/vibe-stack/master/AGENTS.mdgit clone --depth 1 https://github.com/f-amine/vibe-stackWrote 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.
[](https://agentmods.dev/instructions/f-amine/vibe-stack/agents-md)<a href="https://agentmods.dev/instructions/f-amine/vibe-stack/agents-md"><img src="https://agentmods.dev/badge/instructions/f-amine/vibe-stack/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/f-amine/vibe-stack/agents-md"><img src="https://agentmods.dev/badge/instructions/f-amine/vibe-stack/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.01173 | $0.01173 |
| Opus 5.5 | $0.00469 | $0.00469 |
| Sonnet 5.5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade C, and why
vibe-stack AGENTS.md scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- No `rm -rf` outside scratch directories. How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents guide
vibestack is designed to be operated by AI agents in addition to humans. The skill workflow under .claude/skills/ is the canonical way to do non-trivial work.
First-time setup
If .env does not exist, run pnpm init:app (interactive wizard: product name rename, feature toggles, optional API keys, .env with a generated BETTER_AUTH_SECRET) or /setup in Claude Code for the conversational version — never read or print existing .env values. pnpm rename <name> does just the rename (lockfile-safe; run pnpm install after).
Zero-key boot: the app boots without any third-party keys — only DATABASE_URL + BETTER_AUTH_SECRET (+ URL vars) are required. Missing keys degrade or hide their feature: auth emails print to the dev console, billing doesn't mount without Polar, storage errors only when used without R2, /api/health reports them as disabled. See ADR-0009.
Already running? Skip to the workflow.
Workflow
Before doing anything non-trivial:
- Read
CLAUDE.md,CONTEXT.md, and the relevantdocs/adr/*.md. - Pick the entry skill based on the kind of work:
- New feature or capability —
/grill-with-docs→/to-prd→/to-issues→/tdd→/review - Any frontend / UI change —
/impeccableis mandatory before writing or editing component / page / styling code. Covers redesigns, new screens, "make this look better", spacing, colour, motion, copy, empty states. Holds even when the user did not name the skill. See ADR-0005. - Instagram Reels / short-form video / TikTok / YouTube Shorts —
/video-writer. Swarm: researcher → script writer → [voice + SFX + music] parallel → motion designer → renderer → publisher. Reels are pure typographic / UI-mockup composition — no AI-generated stills on this surface. Output: 30-90s 9:16 MP4 + all assets underapps/marketing/public/reels/<slug>/. Remotion composition lives atpackages/video/src/compositions/Reel.tsx. See ADR-0008. - Long-form blog posts / journal / content marketing —
/blog-writer. Swarm: researcher → writer → (SEO editor + image producer in parallel) → publisher. 15-20 min read, multiple Gemini inline images, draft MDX inapps/marketing/content/blog/. See ADR-0007. - SEO / GEO / Search Console / organic traffic / keyword research / meta tags / schema / broken links / Core Web Vitals — route to
toprank. Skills:/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. Uses live Google Search Console + PageSpeed Insights via OAuth. See ADR-0006. - Google Ads / Meta Ads / paid acquisition — also
toprank. Skills:/toprank:google-ads-audit,/toprank:google-ads-manage,/toprank:google-ads-copy,/toprank:google-ads-landing,/toprank:meta-ads-audit,/toprank:meta-ads-manage. Connects via the NotFair-GoogleAds and NotFair-MetaAds HTTP MCPs in.mcp.json. - Bug report —
/diagnose→/tdd - Refactor itch —
/improve-codebase-architecture(requires maintainer approval; propose an ADR before changing structure) - Spike / design exploration —
/prototype(throwaway, then formalise) - Triage —
/triagefor incoming issues
- New feature or capability —
- Do not push code without an issue.
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.
- 1mo ago First seen · 48 lines · 1,173 tokens per session scan C 6bb1a18155c2
vibe-stack AGENTS.md is an instructions file published in the GitHub repository f-amine/vibe-stack (21 stars, last pushed 3mo ago), licensed MIT. It adds 1,173 tokens to every session, about $0.0047 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.