Vibes Plug
Universal Skill AI Agent Swarm Architecture for Antigravity, Claude Code, Cursor, and Windsurf. Vibe Coding 2.0 with Zero Tech Debt
Install
npx vibes-plug initclaude mcp add vibes-plug -- npx vibes-plug init{
"mcpServers": {
"vibes-plug": {
"command": "npx",
"args": [
"vibes-plug",
"init"
]
}
}
}Install command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →⚡ VibesPlug Pro v4.2: 147-Skill AI Agent Swarm Architecture
Turn any IDE into an autonomous 147-agent software development studio.
Zero AI Slop • Sovereign Anti-Slop Directive • Zero Tech Debt • Pure Production Velocity
⭐ Star this repo to support the project & help it trend!
🇬🇧 English | 🇮🇩 Bahasa Indonesia | 🇨🇳 中文 (Mandarin) | 🇩🇪 Deutsch (German) | 🇯🇵 日本語 (Japanese) | 📈 Star History
🎬 Swarm Director in Action
# ⚡ Instant 1-Command Scaffold (No Config Needed)
npx vibes-plug init
💥 Why VibesPlug? (The Paradigm Shift)
| Metric / Capability | Vanilla Vibe Coding (Prompts) | Static IDE Rules (.cursorrules) | ⚡ VibesPlug Pro (Swarm) |
|---|---|---|---|
| Agent Coordination | ❌ 1 confused LLM doing everything | ⚠️ Static rules without orchestration | Swarm Director & 147 Specialists |
| Full-Stack Lifecycle | ❌ Fragmented & prone to regressions | ⚠️ Ad-hoc guidance | Autonomous 9-Phase Zero-To-Prod |
| Tech Stack | ⚠️ Often outputs legacy 2022 patterns | ⚠️ Stale prompts | React 19, Next 15, Tailwind v4, Bun 1.2+ |
| Code Gardening & QA | ❌ Hallucinated dead code & slop | ❌ No automated debt check | 🧹 Zero-Tech-Debt Auditor & Red Teaming |
| Sovereign Anti-Slop | ❌ Lazy stubs, // TODO, & chat fluff |
⚠️ Untested static prompts | 🛡️ Zero-Tolerance Anti-Slop Engine & Scanner |
| Payment & Micro-Economy | ❌ Incomplete integrations | ⚠️ Basic docs | DOKU SNAP, Stripe, M2M Agent Wallets |
| IDE Portability | ❌ Locked to one interface | ⚠️ Cursor only | Antigravity, Cursor, Claude Code, Windsurf, Trae, VSCode |
🧩 The 147-Skill Arsenal (Category Breakdown)
VibesPlug is powered by 147 specialized AI subagents. Here is a high-level grouping of the engine's core capabilities:
| 🎨 Frontend & UI/UX | ⚙️ Backend & Architecture |
|---|---|
senior-frontend app-promo-media-expert ephemeral-generative-ui-architect tailwind-expert modern-css-native-expert ui-ux-pro-max micro-frontend-architect |
js-backend-expert go-programming-expert rust-programming-expert api-design-expert database-orm-expert domain-driven-design-expert |
| 🤖 Frontier AI & LLM | 💸 FinOps & Micro-Economy |
|---|---|
affective-computing-emotion-ai gemini-agent-booster vercel-ai-sdk-expert mcp-server-architect pydantic-ai-expert |
agentic-micro-economy-architect saas-billing doku-payment-gateway payment-gateway-expert ecommerce-expert |
| 🛡️ DevOps, QA & Orchestration | 🌐 Web Ecosystem & Platforms |
|---|---|
zero-to-prod-orchestrator anti-slop (v4.0) zero-tech-debt-auditor (Phase 9) autonomous-red-teamer ci-cd-devops-architect brainstorming |
chrome-extensions mobile-expo-expert desktop-electron-expert pwa-offline-first-expert blockchain-web3-expert |
🇬🇧 English Version
Welcome to VibesPlug Pro. Unlike generic prompt libraries, VibesPlug acts as a Swarm Director, orchestrating 147 specialized AI subagents. It is strictly engineered to extract maximum reasoning capabilities from ALL Frontier Models (Gemini 4 Pro, Claude 5, GPT-5.6/O3, OpenAI Codex, and DeepSeek).
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…