MCP Hub
Back to servers

claude-codepro

Professional Development Environment for Claude Code with Spec-Driven Workflow, TDD, LSP, Cross-Session Memory, Semantic Search, Quality Hooks and Modular Rules System 🛠️

Stars
346
Forks
41
Updated
Jan 8, 2026
Validated
Jan 9, 2026
Claude CodePro

Professional Development Environment for Claude Code (CC)

Start shipping systematically with Endless Mode, Spec-Driven Development, Skills, TDD, LSP, Semantic Search, Persistent Memory, Quality Hooks, Modular Rules System, and much more 🚀

License: AGPL-3.0 Opus 4.5 Endless Mode Spec-Driven TDD

Star this repository · 🌐 Visit the website · 💼 Follow for updates · ✉️ Get in touch


🚀 Getting Started

Prerequisites

Note: Claude CodePro automatically runs inside a Dev Container for complete isolation, consistent tooling, and cross-platform compatibility on Windows, Mac and Linux. You can bring your own Dev Container configuration if you prefer.

Installation

Claude CodePro can be installed into any existing project:

  1. Open your project folder in your IDE
  2. Run this command in the terminal:
curl -fsSL https://raw.githubusercontent.com/maxritter/claude-codepro/v4.1.8/install.sh | bash
  1. Reopen in Container: Cmd+Shift+P → "Dev Containers: Reopen in Container"
  2. Installation completes automatically inside the container

Cursor, Windsurf, Antigravity users: These IDEs don't auto-execute postCreateCommand. After the container starts, run the install command from step 2 again in the container terminal IDE.


📦 What's Inside

♾️ Endless Mode

  • Unlimited Context - Work on complex features across unlimited sessions automatically
  • Zero Manual Intervention - Context Monitor detects when nearing limits and triggers seamless handoffs
  • Works Everywhere - With /spec workflow or Quick Mode - both get unlimited context
  • Claude Mem Integration - Relevant observations flow across sessions automatically

📋 Spec-Driven Development

  • Planning - Creates a detailed implementation plan for your review as markdown in docs/plans/
  • Approval - You review, edit if needed, and approve the plan before implementation
  • Implementation - Executes the plan with TDD enforcement and context management
  • Verification - Runs tests, quality checks, and validates completion based on the plan

💡 Modular Rules System

  • Standard Rules - Best-Practices for TDD, Context Management, etc. in .claude/rules/standard/
  • Custom Rules - Project-specific rules in .claude/rules/custom/ (never touched by updates)
  • Command Skills - Workflow-specific modes: /spec, /setup, /plan, /implement, /verify
  • Standards Skills - Best-Practices for Frontend, Backend, Testing, etc. automatically injected

🔌 Enhanced Context Capabilities

  • Claude Mem - Cross-session persistent memory system that automatically ingest context
  • Vexor - Local vector store based semantic code search for token-efficient retrieval
  • Context7 / Firecrawl - External context retrieval for code and web search / scraping
  • LSP Servers - Python and TypeScript CC Language Servers for extended code intelligence

🛠️ Quality Hooks Automation

  • Python Quality - Post-edit hook for ruff, mypy, basedpyright linting and type checking (optional)
  • TypeScript Quality - Post-edit hook for eslint, tsc, prettier checks (optional)
  • General Quality - Post-edit hook using QLTY for all languages for automated formatting and checking
  • TDD Enforcer - Pre-edit hook that warns when modifying code without failing tests first

🏗️ One-Command Installer

  • Automated Container Setup - Isolated Linux environment with pre-configured tools and extensions
  • Extended Language Support - Optionally install extended support for Python & TypeScript
  • Automated Setup Script - Installs and configures everything in one installation command
  • Shell Integration - Auto-configures bash, fish and zsh with ccp alias

⚡ Quick Start

🔧 First Time Setup

Run /setup once to initialize project context and semantic search:

ccp
> /setup

This is independent of which development mode you use - both modes benefit from the initialized context.

🔁 Two Modes of Development

Claude CodePro supports two development modes. Endless Mode works in both - you get unlimited context regardless of which mode you choose.

ModeCommandBest For
Spec-Driven/spec "task"New features, major changes, complex work
Quick ModeJust chatQuick fixes, bug fixes, small changes

📋 Spec-Driven Mode (/spec)

For structured development with planning and verification:

ccp
> /spec "Describe your feature as detailed as possible"

The workflow:

  1. Plan - Explores codebase, asks questions, generates detailed spec in docs/plans/
  2. Approve - You review, edit if needed, and approve the plan
  3. Implement - Executes tasks with TDD enforcement and quality hooks
  4. Verify - Runs tests, quality checks, validates completion

Use this mode when you want a spec to review before implementation, or when the task is complex enough to benefit from structured planning.

⏩ Quick Mode

For quick work without a spec:

ccp
> Fix the null pointer bug in user.py
> Add a loading spinner to the submit button

Just describe what you need - no plan file, no approval gate. Claude CodePro still provides all the quality hooks, TDD enforcement, and context capabilities. Perfect for bug fixes, small improvements, and exploratory work.

🎯 Customizing Rules

Claude CodePro uses Claude Code's modular rules:

  • Standard Rules in .claude/rules/standard/ - Updated on install, don't modify
  • Custom Rules in .claude/rules/custom/ - Your project-specific rules, never touched by updates
  • Path-Specific Rules - Use YAML frontmatter with paths: to scope rules to specific files

Add custom rules by creating .md files in .claude/rules/custom/. You can also use path-specific rules:

---
paths: src/**/*.py
---
# Python-specific rules for this project

♾️ Endless Mode

Both /spec and Quick Mode use the full 200K context window with automatic management via Endless Mode:

  • Automatic handoffs - When context nears the limit, state is saved and work continues in a new session
  • Claude Mem preserves understanding - Relevant observations flow across sessions
  • Auto-compact disabled - Installation disables auto-compact, giving you 20% more usable context

📜 License

Claude CodePro is dual-licensed:

Open Source (AGPL-3.0)

Free for:

  • Individuals - Personal projects and learning
  • Freelancers - Client work and consulting
  • Open Source Projects - Projects that release source under AGPL-3.0

If you find Claude CodePro useful, consider sponsoring the project to support continued development.

Commercial License

Companies using Claude CodePro in proprietary/closed-source products must obtain a commercial license.

This applies to:

  • Companies with closed-source software
  • Internal tools at companies that don't want to open-source
  • SaaS products using Claude CodePro

Contact: mail@maxritter.net for commercial licensing inquiries.


💼 Professional Services

I'm Max Ritter, a senior IT freelancer based near Munich, Germany, specializing in:

  • AWS Cloud - Cloud Infrastructure, Architecture & Development
  • Data Engineering - Data Pipelines, ETL, Analytics Infrastructure
  • Artificial Intelligence - LLM Integration, AI-Assisted Development, Agents
  • DevOps - CI/CD, Infrastructure as Code, Automation

Paid Services Available

ServiceDescription
Custom DevelopmentClaude CodePro doesn't work in your setup? Containerized environment issues? Specific software restrictions? I can customize it for your needs.
Enterprise IntegrationNeed Claude CodePro integrated into your company's existing toolchain and workflows?
ConsultingGeneral DevOps, Data Engineering, or AI consulting for your projects

Contact & Connect

✉️ Emailmail@maxritter.net
💼 LinkedInlinkedin.com/in/rittermax
📄 CVflowcv.com/resume/hcaa0q4wdd
📝 Blogblog.maxritter.net
🌐 Websitemaxritter.net

🤝 Contributing

Pull Requests are welcome! If you have new features, improvements, or bug fixes, feel free to open a PR.

Note: Issues are disabled. This project evolves alongside my professional work as a freelancer, and I don't have the capacity to maintain a public issue tracker. If you want a feature or find a bug, the best way to contribute is to submit a PR.


🙏 Acknowledgments

Reviews

No reviews yet

Sign in to write a review