A community-driven registry for the Claude Code ecosystem. Not affiliated with Anthropic.
Build production-ready AI agents from natural language — generates subagents, skills, hooks
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
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.
git clone https://github.com/keysersoose/claude-agent-builder.git && cp -r claude-agent-builder/agent-builder ~/.claude/skills/
git clone https://github.com/keysersoose/claude-agent-builder.git; Copy-Item -Recurse claude-agent-builder\agent-builder "$env:USERPROFILE\.claude\skills\agent-builder"
git clone https://github.com/keysersoose/claude-agent-builder.git && xcopy /E /I claude-agent-builder\agent-builder "%USERPROFILE%\.claude\skills\agent-builder"
# 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.
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
| Without Agent Builder | With Agent Builder |
|---|---|
| You need to know all 7 primitives | It picks the right ones for you |
You write from blank .md files | It writes production-ready files directly into your project |
| You guess at descriptions and tools | It optimizes for auto-triggering |
| You explain your project from scratch | It scans your codebase and conversation history first |
| You don't know what exists already | It searches GitHub, blogs, docs, and community in parallel — then consolidates |
| Trial and error | Proposes → you approve → it builds → it verifies |
agent-builder/
├── SKILL.md # Core skill — 6-phase agent building workflow
├── references/
│ ├── primitives-guide.md # Complete guide to all Claude Code building blocks
│ └── agent-patterns.md # 7 battle-tested multi-agent architecture patterns
└── scripts/
├── validate_agents.py # Lint agent files for common issues
└── scaffold_agent.py # Generate starter files from templates
The skill knows 7 proven patterns and selects the right one for your use case:
| Pattern | Best For | Example |
|---|---|---|
| Command → Agent → Skills | Multi-step pipelines | Full-stack feature builder |
| Research → Consolidate → Plan → Execute | Understanding before acting | Codebase migration |
| Parallel Specialists | Independent analyses | Security + perf + style review |
| Self-Evolving Agent | Learning over time | Project onboarding guide |
| Hook-Guarded Agent | Safety-critical workflows | Read-only database analyst |
| Slash Command + Handoff | Quick entry → complex flow | Bug investigation |
| MCP-Powered Agent | External service integration | GitHub PR review bot |
PR Security Reviewer — subagent with GitHub MCP, PreToolUse safety hooks, slash command trigger, and persistent memory.
Research Pipeline — /research command spawning 3 parallel subagents (web, codebase, Stack Overflow) with synthesis and markdown report output.
Self-Improving Onboarder — subagent with memory: project that builds institutional knowledge across conversations.
See examples/ for complete, ready-to-use configurations.
# Install dependency for validation script
pip install pyyaml
# Validate your agents for common issues
python agent-builder/scripts/validate_agents.py .claude/agents/
# Scaffold new agents from templates
python agent-builder/scripts/scaffold_agent.py my-agent .claude --type subagent
python agent-builder/scripts/scaffold_agent.py deploy-pipe .claude --type full-stack
Requirements: Claude Code installed. Python 3.7+ for utility scripts.
Your need
├── "Auto-do X when Y happens"
│ ├── During a tool call? → Hook
│ ├── Based on context? → Skill
│ └── Based on task type? → Subagent
├── "Trigger a workflow"
│ ├── Simple command? → Slash command
│ └── Multi-step? → Command + subagents
├── "Connect external services" → MCP server
├── "Remember across conversations" → CLAUDE.md / memory
└── "Production app" → Agent SDK
We welcome contributions! See CONTRIBUTING.md.
Add examples · Improve patterns · Enhance the skill · Fix bugs · Share feedback
MIT — use it, modify it, share it. See LICENSE.
Built by keysersoose · Powered by Claude Code
If this saved you time, give it a star. It helps others find it.
ML engineering — model training, deployment, MLOps, monitoring
DevOps practices — CI/CD, containers, monitoring, infrastructure automation
Professional skills marketplace with production-ready skills for enhanced development
Self-learning system that captures corrections and syncs them to CLAUDE.md and AGENTS.md
