By ohad6k
Audit AI-built apps for production readiness with a ship/no-ship verdict, enforce architecture-first planning for AI coding agents, push to GitHub and Vercel for deployment, maintain production context, and detect regressions by comparing releases via git tags and diffs.
Use VibeRaven when working on an AI-built app that must ship to real users; when the user asks to ship, deploy, go to production, connect auth, database, payments, RLS, env vars, webhooks, or monitoring; when production-only errors appear; or when the agent needs product context (versions, providers, launch risks) before patching. Fully local — no login, no API key.
Use when an AI coding agent starts real app work, product feature design, provider work, migrations, auth, billing, storage, webhooks, deploys, or any task where unclear architecture could cause broad or unsafe changes.
Use when VibeRaven architecture questions have been answered, a feature/fix has unclear boundaries, or an agent needs to turn product answers plus repo evidence into a workstream architecture plan before editing.
Use when a user wants an AI-built local project pushed to GitHub and deployed live on Vercel with the least friction, while keeping git, secrets, provider setup, and live proof explicit.
Use when changing, reviewing, debugging, deploying, or documenting production-sensitive work involving providers, releases, migrations, auth, billing, webhooks, env vars, incidents, rollback notes, fragile customer paths, or architecture boundaries.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
VibeRaven is an open-source local cockpit for AI-built apps. Run npx -y viberaven in your repo and it connects your coding agent (Claude Code, Cursor, Codex) to the context it patches blind without, your architecture, providers, and releases, then shows what is actually safe to ship to production, auth, RLS, webhooks, deploy, before real users hit it. Local-first, no login.
npx -y viberaven
VibeRaven deals your providers as a hand — each one graded, each one a card you play into your agent's next move. Supabase, Vercel, GitHub, Stripe, Sentry, Resend, Clerk, Upstash, and more.
The Studio opens in your browser and works entirely on your machine: it detects your stack, finds your providers, puts your git releases on a timeline, and gives you a "can I ship?" verdict from offline checks. No login, no API key, no telemetry.
Run it. npx -y viberaven in your project folder. The Studio opens in your browser and scans your repo offline.
Read your verdict. The gate chip and Launch Signals show exactly what blocks launch, ranked. Click any signal, then click Fix to hand it to your agent.
Connect your coding agent. Pick Codex, Claude Code, or Gemini CLI in the chat panel, hit Test connection, and choose how much access it gets (ask, approve, or full).
Open the Architecture map. Pages, API, data, modules, and providers as a live draggable map. Weak boundaries glow red. Click one and press a plain-English action like "Protect user data (RLS)" or "Fix slow queries".
Open the Worktree. Your branches as a real tree. Uncommitted mess? One tap: Commit with agent. Branch ready? Review explains it in plain language and Merge does it safely.
Give your agent the skills. Install the six-skill pack and the plugin so Codex, Claude Code, and Gemini follow the same senior-engineer loop everywhere:
npx -y skills add ohad6k/VibeRaven --skill viberaven # skills.sh pack
npx -y viberaven init --agents all # agent rules in-repo
npx claudepluginhub ohad6k/viberavenEnhances Claude Code from producing raw code into delivering production-ready systems. 14 specialized agents handle architecture, tested code, security audit, CI/CD, and documentation. Use for building apps/websites/services, adding features, hardening, deployment, testing, review, or architecture design.
Use this agent when evaluating new development tools, frameworks, or services for the studio. This agent specializes in rapid tool assessment, comparative analysis, and making recommendations that align with the 6-day development cycle philosophy. Examples:\n\n<example>\nContext: Considering a new framework or library
Claude Code skill pack for Vercel (30 skills)
A caring skill pack for vibe coders. Encodes engineering discipline — refactor verification, minimal security audit, repo rot detection, AI-friendly docs, CI/CD basics, secrets lifecycle, project conventions, repo bloat diagnosis, and design-system unification — as a set of portable agent skills.
Complete PR workflow from commit to production with validation
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.