🏗️ Claude Agent Builder

Turn any idea into production-ready AI agents in Claude Code

Stop writing agent files from scratch. Describe your problem → get researched, architected, production-ready agents, skills, hooks, and commands — automatically.

Quick Start · How It Works · Examples · Patterns · Contributing

---

The Problem

Building agents in Claude Code means juggling 7 different primitives (subagents, skills, hooks, commands, MCP servers, CLAUDE.md, Agent SDK), reading scattered docs, and starting from blank Markdown files every time.

Claude Agent Builder fixes this. It's a skill that acts as your personal agent architect — it interviews you, researches what already exists, designs the optimal system, and generates every file you need.

⚡ Quick Start

macOS / Linux

git clone https://github.com/keysersoose/claude-agent-builder.git && cp -r claude-agent-builder/agent-builder ~/.claude/skills/

Windows (PowerShell)

git clone https://github.com/keysersoose/claude-agent-builder.git; Copy-Item -Recurse claude-agent-builder\agent-builder "$env:USERPROFILE\.claude\skills\agent-builder"

Windows (CMD)

git clone https://github.com/keysersoose/claude-agent-builder.git && xcopy /E /I claude-agent-builder\agent-builder "%USERPROFILE%\.claude\skills\agent-builder"

Other install methods

# macOS/Linux — install script
git clone https://github.com/keysersoose/claude-agent-builder.git
cd claude-agent-builder && ./install.sh

# macOS/Linux — project-level only
./install.sh --project

# Windows — install script (PowerShell)
git clone https://github.com/keysersoose/claude-agent-builder.git
cd claude-agent-builder; .\install.ps1

# Windows — project-level only
.\install.ps1 -Project

# Any platform — project-level manual
git clone https://github.com/keysersoose/claude-agent-builder.git
cp -r claude-agent-builder/agent-builder .claude/skills/

Open Claude Code and say:

Build me an agent that reviews my PRs for security issues and posts comments on GitHub

The skill triggers automatically. That's it.

🧠 How It Works

Agent Builder operates in 6 phases, adapting to how much context you provide:

  🔍 CONTEXT SCAN →  Reads your project files + conversation history automatically
  📋 DISCOVERY    →  Only asks what it can't figure out itself
  🌐 RESEARCH     →  Parallel search (GitHub + blogs + docs + community) → consolidated brief
  📐 ARCHITECTURE →  Proposes agents, gets your explicit approval before building
  🔨 BUILD        →  Writes all agent files directly into your project
  ✅ VERIFY       →  Self-checks everything, shows you what was built, asks for final OK

Why not just ask Claude directly?