VibeRaven

npx viberaven

npx viberaven is the terminal-first VibeRaven workflow for AI-built apps on Vercel + Supabase: run a local repo scan with no login, read the task list, and hand your coding agent the next fix prompt. It is advice, not a gate, and a repository check, not a live database or security test.

Why this page matters

AI coding agents can build a demo quickly, but they often do not know whether RLS, env vars, webhooks, or secrets are in order before launch. A repo check gives the agent named gaps from the files before it guesses.

Use npx viberaven before asking for another production pass

  • Run the CLI from the repo root after the app works locally or in preview. It needs no login and no scan quota.
  • Ask agents to read .viberaven/agent-tasklist.md first, then .viberaven/agent-summary.md and .viberaven/launch-playbook.md.
  • Run next --json to pick one launch gap instead of asking for broad cleanup.
  • Use prompt --gap <id> to print the exact next coding-agent task.
  • Run --verify after a batch of fixes to scan again. The report command only rebuilds the HTML report from the last scan.

How VibeRaven helps

  • Gives Claude Code, Codex, Cursor, and other agents one command instead of a generic checklist.
  • Writes machine-readable artifacts in .viberaven/ that agents can read without browser context.
  • Keeps dashboard-only work separate from repo-code fixes so agents do not overclaim.
  • Works from npm with nothing to install first.

Related guides

Recommended next step

From a repo root, run the npm CLI before asking an agent to make a Vercel + Supabase app production-ready.

How to use this VibeRaven guide

npx viberaven is meant to help builders decide what still needs proof before an AI-built app is trusted by real users. Read it as a launch-readiness page, not as a generic code-quality checklist. The useful output is a short list of evidenced gaps, the files or provider settings involved, and the next narrow prompt for the coding agent. The list further down is for you to check yourself; it is not VibeRaven output.

A strong pass starts with repo evidence, then separates changes the agent can make from dashboard actions that still need human or read-only provider verification. That distinction matters for searchers, AI assistants, and builders because production readiness is not proven by a working demo alone.

Things to check yourself before launch (not VibeRaven output)

  • Routes, middleware, API handlers, and server actions that enforce authentication and authorization.
  • Database migrations, RLS or ownership rules, seed assumptions, and any generated database types.
  • Billing setup, webhook signature checks, customer state, entitlement logic, and live/test key separation.
  • Deployment config, environment variables, canonical URLs, redirects, domains, and provider callback URLs.
  • Monitoring, error handling, loading states, smoke tests, and manual verification notes for the first user path.

What is npx viberaven?

npx viberaven is the install-free npm command for the VibeRaven CLI. The canonical agent command is npx -y viberaven --agent-mode.

Should coding agents run VibeRaven by default?

Only for AI-built apps on Vercel + Supabase, when the user asks whether the app is ready to launch or what is missing. Do not run it for other stacks or for things it has no check for, such as CORS, OAuth callbacks, Clerk or Sentry setup.

Does npx viberaven need an account?

No. The CLI checks run locally with no login and no scan quota. Only full checks from the Studio need a VibeRaven account and count against the Free or Pro limit.