Skip to content

bankielewicz/DevForgeAI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

142 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

DevForgeAI

License: MIT Node.js >= 18 Built with Claude Code PRs Welcome

Your AI coding assistant just got guardrails.

DevForgeAI adds structure to Claude Code so your AI writes code the way you'd want a senior developer to: tests first, your tech stack, your rules. It works with any language or framework.


The Problem

You've tried coding with AI. It's fast — until it rewrites your auth system in a framework you didn't choose, skips the tests, and produces code that works today but breaks next week.

The problem isn't the AI. It's the lack of guardrails.

Without structure, AI assistants will:

  • Pick technologies you didn't approve
  • Skip tests because "the implementation is straightforward"
  • Create inconsistent patterns across your codebase
  • Make architecture decisions without asking you

What DevForgeAI Does

DevForgeAI is a plugin for Claude Code that gives your AI assistant rules to follow:

Your project's rules are written down. You define your approved tech stack, code standards, and patterns in 6 simple files. The AI reads these before writing any code and cannot deviate without your permission.

Tests come first, every time. The framework enforces test-driven development. Your AI writes failing tests, then writes the minimum code to pass them, then refactors. No shortcuts.

Quality checkpoints catch problems early. Before code moves forward, it passes through automated checks: test coverage, security scanning, and pattern checks. Issues are caught before they compound.


See It in Action

Interactive Demo

Try the interactive demo at devforgeai.com — explore the full pipeline, TDD cycle, and quality gates right in your browser.

Before & After

Without DevForgeAI With DevForgeAI
AI picks random libraries AI uses only your approved stack
Tests skipped "to save time" Tests written first, every feature
Code works but you're not sure why Every decision documented and traceable
"It works on my machine" Quality checkpoints before shipping
Vague idea → spaghetti code Vague idea → structured requirements → clean code

Get Started

Prerequisites: Claude Code, Node.js 18+, Git

npx devforgeai install

That's it. This installs DevForgeAI into your project. Then open Claude Code and try your first command:

/brainstorm "I want to build a task management app"

DevForgeAI will ask you questions about your idea, help you think through requirements, and guide you toward a clear plan — all conversationally. No setup forms, no config files to write by hand.

What happens next:

  1. /brainstorm helps you explore your idea through guided questions
  2. /create-context writes down your project rules (tech stack, standards, structure)
  3. /create-story turns features into clear, implementable specs
  4. /dev STORY-001 builds it with test-driven development — tests first, then code
  5. /qa STORY-001 validates quality before you ship

You don't have to use every command. Start with /brainstorm and follow the prompts.


Start from Just an Idea

The full workflow takes you from a napkin sketch to production:

/brainstorm     "I want to build..."     You explore the idea
      |
/ideate         Idea → requirements       AI asks the right questions
      |
/create-context Requirements → rules      Your tech choices get locked in
      |
/create-epic    Rules → feature plan      Big idea broken into pieces
      |
/create-story   Features → specs          Each piece gets clear acceptance criteria
      |
/dev            Specs → tested code       Built with TDD (tests first)
      |
/qa             Code → quality check      Coverage, security, patterns validated
      |
/release        Validated → shipped       Deploy with confidence

Coming soon: MVP Fast Track — A lighter workflow for when you want to prototype quickly. Fewer phases, relaxed coverage, faster iteration. Think of it as "sketch mode" before you commit to the full blueprint.


Common Questions

Do I need to use all the commands? No. Start with /brainstorm if you have a vague idea, or /dev STORY-001 if you already have a story file. Use as much or as little as you need.

What tech stacks does it support? All of them. DevForgeAI is technology-agnostic. Your context files define whether you're using Python, TypeScript, C#, Go, Rust, or anything else. The framework adapts to your choices.

Is this only for big projects? No. It works great for side projects, prototypes, and solo dev work. The quality guardrails scale down — you're not forced into enterprise ceremony.

Do I need to know TDD? No. The framework handles the test-driven workflow for you. It writes the tests, runs them, and implements code to make them pass. You just describe what you want.

What if I just want to write code without all the process? You can. Use /dev directly with a story file and it handles the TDD cycle. Skip brainstorming, skip epic planning — jump straight to building.

How is this different from Cursor Rules or .cursorrules? DevForgeAI goes beyond static rules. It's an active framework with 60+ specialized AI helpers that enforce your rules at every step, not just suggest them. It manages the full journey from idea to deployment.


What's Under the Hood

For the technically curious — DevForgeAI is built entirely as Claude Code extensions:

  • 34 Skills — Structured workflows for each stage (brainstorming, development, QA, release)
  • 60+ Subagents — Specialized AI agents with specific jobs (test-automator writes tests, security-auditor finds vulnerabilities, code-reviewer checks quality)
  • 57+ Slash Commands — User-facing entry points from /brainstorm to /release
  • 6 Context Files — Your project's rules: tech stack, directory structure, dependencies, code standards, architecture constraints, forbidden patterns
  • Architecture Decision Records — Every significant choice documented with rationale

All components are Markdown files — readable, version-controlled, and editable by humans.

Want to learn more? Where to look
All commands explained Developer Guide
Architecture deep-dive Architecture Guide
API documentation API Reference
Troubleshooting Troubleshooting Guide
Project roadmap Roadmap

Installation Options

# Recommended (one command)
npx devforgeai install

# From source
git clone https://github.com/bankielewicz/DevForgeAI.git
cd DevForgeAI && npm install
node bin/devforgeai.js install /path/to/your-project

# Global install
npm install -g devforgeai
devforgeai install

After installing, open Claude Code in your project and run /create-context to set up your project rules interactively.


Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Use the DevForgeAI workflow: /create-story -> /dev -> /qa
  4. Push and open a Pull Request

See CONTRIBUTING.md for full guidelines.


Support

If DevForgeAI has helped your development workflow, consider supporting the project:

Buy Me A Coffee

License

MIT License — see LICENSE for details.


Built with Claude Code — Guardrails for AI-assisted development.

About

AI-powered spec-driven development framework with 26+ specialized subagents, mandatory TDD, immutable architectural constraints, and automated quality gates — enforcing zero technical debt from ideation to release.

Topics

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Packages

 
 
 

Contributors