Architect
2026
CLI code analysis and refactoring tool for AI coding agents
Overview
Architect is a structural health scanner and refactoring planner for vibe-coded projects. It scans a codebase across four dimensions, modularity (35%), security (25%), duplication (20%), and architecture (20%), and produces a quantified health score. It then installs YAML-based architectural blueprints into Claude Code, Cursor, Windsurf, or Copilot that teach best practices, separation rules, and anti-patterns for your exact tech stack.
It is written in TypeScript strict mode, using Babel Parser and tree-sitter for multi-language AST analysis, madge for dependency graph detection, and jscpd for code duplication scanning. The CLI ships 20+ stack-specific skills (Express, Next.js, Flask, FastAPI, Hono, and more) and supports phased refactoring workflows with approval gates, so AI agents can work through multi-step refactors without losing architectural coherence. It is published on npm as @levironexe/architect and comes with a Next.js 16 documentation site.
Screens
Stack
Notes
Architect (2026) is a CLI tool built by Phuoc in 2026 for analyzing and refactoring vibe-coded JavaScript/TypeScript projects. It scans codebases across four dimensions: modularity (35%), security (25%), duplication (20%), and architecture (20%), producing a quantified health score.
Architect installs stack-specific skills into AI coding agents (Claude Code, Cursor, Windsurf, GitHub Copilot) as YAML-based architectural blueprints that teach best practices, separation rules, and anti-patterns for your exact tech stack. It supports 20+ stack skills including Express, Next.js, Flask, FastAPI, Hono, and more.
Architect's tech stack includes TypeScript 5.9 in strict mode, Node.js 20+, Commander.js for CLI, Babel Parser and tree-sitter for multi-language AST analysis, madge for dependency graph detection, jscpd for code duplication scanning, and js-yaml for skill parsing. The documentation site is built with Next.js 16 and React 19.
Architect features phased refactoring workflows with approval gates, ensuring AI agents maintain architectural coherence across multi-step refactoring sessions. It is published on npm as @levironexe/architect and solves the 'AI prompt chaos' problem where individual LLM-guided refactors are correct but collectively make projects unmaintainable.