CLI tool for instant Claude Code project scaffolding with context engineering best practices
Transform your project ideas into AI-ready applications with intelligent context engineering
๐ฏ Optimized for Claude Code with deep integration for slash commands, hooks, and PRPs
Also supports Cursor, Windsurf, Cline, Copilot, Gemini, and more AI coding assistants
๐ What's New in v3.2.9
๐ Enhanced Claude Code Integration
๐ Complete Project Structure
๐ฏ PRP Support for 6 AI IDEs!
Product Requirement Prompts (PRP) now available for Claude, Cursor, Windsurf, Cline, Copilot & Gemini!
Structured feature implementation with validation gates across all major AI coding assistants!
Features โข Quick Start โข Documentation โข Credits
๐ Overview
Context Forge is a powerful CLI tool that bridges the gap between project requirements and AI-assisted development. By implementing Andre Karpathy's context engineering principles, it generates comprehensive documentation structures that enable AI IDEs to understand and build your project efficientlyโwithout hallucinations or context confusion.
๐ Why Choose Context Forge?
๐ Universal AI IDE Support - Works with ALL major AI coding assistants
โก Zero Configuration - Intelligent defaults for each IDE
๐ฏ One Command - Generate configs for multiple IDEs simultaneously
๐ Format Conversion - Switch between IDEs without starting over
๐ Claude Hooks Integration - Seamless context preservation during compaction
๐ฆ No Lock-in - Your project, your choice of AI assistant
๐ค Supported AI IDEs & Assistants
Coming Soon: Amazon CodeWhisperer, Tabnine, and more!
๐ IDE Configuration Guides
Need help understanding how each IDE uses its configuration? Check out our detailed guides:
- ๐ค Claude Code Guide - Full PRP support, validation system, tech-stack templates
- ๐ต Cursor IDE Guide - PRP support, MDC format, hierarchical rules
- ๐ฉ Windsurf Guide - PRP support, Cascade AI integration, workflows
- ๐ข Cline Guide - PRP support, context management, code patterns, advanced commands
- ๐ฃ Roo Code Guide - Workspace rules, YAML configuration, team settings
- ๐ Gemini Guide - PRP support, hierarchical context, CLI commands, Code Assist integration
- โซ GitHub Copilot Guide - Custom instructions, VS Code settings, language-specific rules
๐ Claude Code Advanced Features Documentation
๐ Complete Claude Features Guide - Master the new advanced features:
- โก Slash Commands Reference - 20+ pre-built commands for rapid development
- ๐ค PRP Runner Guide - Automated PRP execution with validation gates
- ๐ Enhanced PRP Templates - Four specialized templates for different scenarios
- ๐ฏ Orchestration Workflow - How all components work together
๐ค AI-Powered PRP Generation (NEW in v3.2.8)
Transform your project development with intelligent, feature-specific Product Requirement Prompts (PRPs) powered by OpenAI and Anthropic Claude.
๐ง What are AI-Powered PRPs?
Unlike template-based PRPs, AI-powered PRPs are dynamically generated for each specific feature in your project, containing:
- Feature-specific implementation strategies tailored to your tech stack
- Intelligent gotchas and best practices based on your architecture
- Custom validation approaches optimized for the feature type
- Relevant documentation links curated by AI
- Complexity assessments and dependency analysis
๐ Quick Setup
# 1. Set up your AI provider (one-time setup) context-forge ai-keys --provider openai # OR context-forge ai-keys --provider anthropic # 2. Initialize project with AI-powered PRPs context-forge init --ai-prp # Your API keys are securely encrypted and stored in ~/.context-forge-keys
๐ Secure Key Management
- AES-256-CBC encryption for API key storage
- User-specific salt generation for enhanced security
- Cross-project key sharing - set up once, use everywhere
- Multi-provider support - OpenAI, Anthropic Claude, and more coming soon
โก Real-time Generation Process
Watch as Context Forge generates intelligent PRPs for each feature:
๐ค Generating AI PRP for: User Authentication & Authorization...
โ
AI content generated for: User Authentication & Authorization
๐ Generated: PRPs/feature-auth-prp.md
๐ค Generating AI PRP for: Google Drive Cloud Streaming...
โ
AI content generated for: Google Drive Cloud Streaming
๐ Generated: PRPs/feature-google-drive-cloud-streaming-prp.md
๐ฏ Example: Feature-Specific Content
Traditional Template PRP:
# TODO: Add implementation details # TODO: Add data models based on requirements
AI-Powered PRP for Google Drive Integration:
### AI-Generated Implementation Strategy Leverage Google Drive API for file organization, streaming, and redundancy. Use Google's Picker API for intelligent folder structure management. Implement JWT for access control. ### โ ๏ธ AI-Identified Gotchas - Make sure to have proper error handling for API failures - Ensure you're not exceeding Google Drive API's rate limits - Be careful with user's OAuth tokens ### โ AI-Recommended Best Practices - Encrypt OAuth tokens - Use Google's recommended best practices for Drive API - Always validate files before streaming
๐ก๏ธ Fallback & Reliability
- 30-second timeout with automatic fallback to template content
- Progress feedback so you always know what's happening
- Graceful error handling ensures project generation never fails
- Offline mode - AI enhancement is always optional
โจ Features
Core Features
- ๐ No AI Dependencies - Works completely offline without API keys
- ๐ค Multi-IDE Support - Generate configs for multiple AI IDEs at once
- ๐ Interactive CLI - Guided project setup with IDE selection
- ๐ฏ Template-based Generation - IDE-specific documentation formats
- ๐ ๏ธ Multiple Tech Stacks - Support for 9+ frameworks with specific configurations
- ๐ Structured Output - Organized documentation following each IDE's conventions
- โก Fast Setup - Go from zero to AI-ready project in minutes
- ๐ Technology Migration - Safe migration planning between tech stacks
- ๐ง Retrofit Existing Projects - Analyze and upgrade existing codebases with AI documentation
- ๐๏ธ Smart Project Detection - Automatically detects new vs existing projects
- ๐ Transparent File Operations - Shows actual file paths and comprehensive logging
Advanced Features
- ๐ค AI-Powered PRP Generation - Intelligent, feature-specific PRPs with OpenAI & Anthropic (NEW in v3.2.8!)
- ๐ PRP Integration - Product Requirement Prompts with validation loops (Claude, Cursor, Windsurf, Cline, Copilot & Gemini)
- ๐ Secure API Key Management - AES-256-CBC encrypted storage for AI provider keys
- โ Validation System - Built-in code quality checks and gates
- ๐ Human-in-the-Loop Checkpoints - Pause for verification at critical milestones
- ๐ช Claude Code Hooks - PreCompact, ContextRotation, PreSubmit, and PRPTracking hooks
- โก 20+ Slash Commands - Comprehensive command library for rapid development
- ๐จ Tech-Stack Specific Templates - Optimized CLAUDE.md for each framework
- ๐ Comprehensive Reporting - Validation reports and progress tracking
- ๐ Phased Migration Plans - Step-by-step migration with rollback strategies
- ๐ง Extensible Architecture - Easy to add new tech stacks and features
๐ Claude Hooks Manager Integration
Context Forge provides deep integration with Claude Hooks Manager through 4 powerful hooks that enhance your development workflow and maintain context throughout long sessions.
The 4 Claude Code Hooks
1. PreCompact Hook - Context Preservation
With Claude Code v1.0.48+, the PreCompact hook ensures your PRPs and project context survive conversation compaction:
- ๐ง Critical project structure persists
- ๐ฏ Current implementation stage maintained
- ๐ Validation gates remain active
2. ContextRotation Hook - Smart File Management
Intelligently manages which files stay in context as you work:
- ๐ Prioritizes relevant files based on current task
- ๐ Automatically rotates less relevant files out
- ๐พ Preserves critical configuration files
3. PreSubmit Hook - Quality Gates
Runs validation before code submission:
- โ Syntax and type checking
- ๐งช Test execution
- ๐ Coverage requirements
- ๐ Security scanning
4. PRPTracking Hook - Progress Monitoring
Tracks PRP implementation progress:
- ๐ Monitors task completion
- โฑ๏ธ Time tracking per feature
- ๐ Automatic status updates
- ๐ฏ Milestone achievements
๐ฏ NEW: Dart Integration Hooks (v3.2.1)
When Dart task management is enabled, Context Forge generates additional hooks for comprehensive task tracking:
5. DartProgressUpdater Hook - Automatic Task Progress
Automatically updates Dart task progress based on code changes:
- ๐ Detects tasks from file path patterns
- ๐ Updates task status on file modifications
- ๐ Tracks git commit messages for task completion
- ๐ Maintains progress history and suggestions
6. AutoTaskCommenter Hook - Detailed Task Documentation
Adds intelligent comments to Dart tasks with code analysis:
- ๐ง Analyzes code structure and complexity
- ๐ Tracks functions added/modified and line changes
- ๐ฏ Categorizes changes by project area (auth, API, UI, etc.)
- ๐ Creates milestone comments for builds/tests/commits
7. TaskCodeMapper Hook - Intelligent File-Task Mapping
Maintains smart mapping between Dart tasks and code files:
- ๐ง Infers task categories from file paths and content
- ๐ Confidence-based task assignment suggestions
- ๐ฏ Project-specific pattern recognition
- ๐ Learning from successful mappings
Enable Dart Integration:
context-forge init
# Select "Enable Dart task integration? Yes"Generated Dart Integration Files:
.claude/dart_progress.json- Task progress tracking.claude/task_mapping.json- File-to-task relationships.claude/task_comments.json- Automated task comments.claude/task_suggestions.json- AI-generated task suggestions
Setup
# Generate project with hooks context-forge init # Select "Enable Claude Code hooks? Yes" # Or copy hooks from another project context-forge copy-hooks --source ../claude-hooks-repo/hooks # Hooks are created in: # .claude/hooks/
This integration is especially powerful for:
- Long-running development sessions
- Complex multi-phase implementations
- Team projects requiring consistency
- Migration projects with checkpoints
๐ Human-in-the-Loop Checkpoints
Context Forge introduces a powerful checkpoint system that pauses AI development at critical milestones for human verification, ensuring you maintain control over the implementation process.
Why Checkpoints?
- Prevent Breaking Changes: Verify database migrations before data modification
- Quality Assurance: Review architectural decisions before proceeding
- Safety First: Human approval for production deployments
- Learning Opportunity: Understand what the AI has implemented
How Checkpoints Work
- Automatic Triggers: AI pauses at predefined critical points
- Manual Checkpoints: Use
/checkpointcommand anytime - Verification Request: AI presents what was done and what needs testing
- Human Decision: Approve to continue or request fixes
Checkpoint Commands
/checkpoint [description]- Create manual checkpoint/should-checkpoint- AI asks if checkpoint is needed/milestone-gate [milestone]- Major milestone verification
Example Checkpoint Flow
๐ CHECKPOINT: Human Verification Required
Analytics Dashboard - I've completed database schema setup:
โ
What I've Accomplished:
- Created PostgreSQL schema with 5 tables
- Set up foreign key relationships
- Added indexes for query optimization
๐งช Please Test:
1. Run: npm run db:migrate
2. Check tables exist: psql -c "\dt"
3. Verify foreign keys: psql -c "\d+ users"
๐ Critical Verification Points:
- [ ] All tables created successfully
- [ ] Foreign keys properly linked
- [ ] No data loss from existing tables
Please respond:
- โ
"Approved" - Continue to next task
- โ "Issues: [description]" - Fix before proceeding
Configuring Checkpoints
Checkpoints are configured during project initialization or can be added to existing projects:
# .context-forge/checkpoints.yaml checkpoints: - name: "Database Migration" phase: "infrastructure" requires_approval: true validation_steps: - "Run migration scripts" - "Verify data integrity" - "Check rollback procedures"
๐ฆ Installation
npm install -g context-forge
๐ Quick Start
Prerequisites
- Node.js 18+ and npm 7+
- Git (for version control)
- A code editor (VS Code recommended)
Basic Usage
# Initialize a new project context-forge init # Initialize with AI-powered PRPs (optional) context-forge init --ai-prp # Set up AI provider keys (optional) context-forge ai-keys # Or use npx without installation npx context-forge init
Note: Context Forge is a CLI tool and should be installed globally. Do not install it as a project dependency with npm install context-forge as this will add unnecessary files to your project.
# Initialize in current directory context-forge init # Specify output directory context-forge init --output ./my-project # Use with existing PRD file context-forge init --prd ./requirements.md # Skip interactive prompts with config context-forge init --config ./context-forge.json # Run validation on existing project context-forge validate # Retrofit existing projects with AI-optimized documentation context-forge analyze # Execute PRPs with Claude Code for one-pass implementation context-forge run-prp feature-name # NEW: Plan technology migration context-forge migrate --target "Next.js" # NEW: Copy Claude Code hooks from another project context-forge copy-hooks --source ../claude-hooks-repo/hooks # NEW: Set up AI provider keys for enhanced PRP generation context-forge ai-keys --provider openai context-forge ai-keys --provider anthropic
๐ก Usage Examples
Example 1: SaaS Dashboard Project
$ context-forge init ? Project name: Analytics Dashboard ? Project type: fullstack ? Project description: Real-time analytics dashboard with data visualization ? How would you like to provide the PRD? Create new PRD ? Frontend framework: nextjs ? Backend framework: fastapi ? Database: postgresql ? Select features: authentication, dashboard, realtime-updates, data-export ? Project timeline: standard ? Team size: small ? Enable PRP generation? Yes ? Enable AI-powered PRP generation? Yes ? Enable validation system? Yes ? Enable Human-in-the-Loop checkpoints? Yes ? Enable Claude Code hooks? Yes โ Project initialized successfully! Generated files: - CLAUDE.md (Next.js 15 specific configuration) - Docs/Implementation.md (4 development stages) - Docs/project_structure.md - PRPs/base.md (Implementation prompt with validation gates) - .claude/commands/ (20+ slash commands) - .claude/hooks/ (4 Claude Code hooks) - .context-forge/config.json Next steps: 1. cd analytics-dashboard 2. Set up AI keys (optional): context-forge ai-keys 3. Review CLAUDE.md for project rules 4. Use /prime-context to load project knowledge and activate architect mode 5. Start with Stage 1 in Docs/Implementation.md
Example 2: API-Only Microservice
$ context-forge init --output user-service ? Project name: User Service ? Project type: api ? Project description: User management microservice with JWT auth ? Frontend framework: none ? Backend framework: express ? Database: mongodb ? Authentication method: jwt ? Enable Docker support? Yes ? Enable GitHub Actions? Yes Generated structure: user-service/ โโโ CLAUDE.md # Express.js specific rules โโโ Docs/ โโโ PRPs/ โโโ Dockerfile โโโ docker-compose.yml โโโ .github/workflows/
Example 3: Nuxt 4 Vue Application
$ context-forge init --output nuxt-dashboard ? Project name: Analytics Dashboard ? Project type: fullstack ? Project description: Modern analytics dashboard with real-time data ? Frontend framework: nuxt4 # NEW: Nuxt 4 option ? Styling framework: tailwind ? State management: pinia ? Backend framework: fastapi ? Database: postgresql ? Authentication method: jwt ? Enable AI-powered PRP generation? Yes Generated structure: nuxt-dashboard/ โโโ CLAUDE.md # Nuxt 4 + Vue 3 specific rules โโโ Docs/ โโโ PRPs/ โ โโโ nuxt-dashboard-prp.md โ โโโ feature-auth-prp.md # AI-enhanced for Nuxt 4 โโโ .claude/commands/ # 25+ slash commands โจ Nuxt 4 Features Included: - New app/ directory structure documented - Vue 3 Composition API guidelines - TypeScript integration with auto-imports - SSR and data fetching best practices - Pinia state management setup
Example 4: Using Configuration File
# context-forge.json { "projectName": "E-Commerce Platform", "projectType": "fullstack", "description": "Modern e-commerce platform with AI recommendations", "prd": { "content": "# E-Commerce Platform\n\n## Overview\n...", "features": [ { "id": "auth", "name": "User Authentication", "priority": "must-have", "complexity": "medium" }, { "id": "catalog", "name": "Product Catalog", "priority": "must-have", "complexity": "complex" }, { "id": "cart", "name": "Shopping Cart", "priority": "must-have", "complexity": "medium" }, { "id": "ai-recommendations", "name": "AI Product Recommendations", "priority": "should-have", "complexity": "complex" } ] }, "techStack": { "frontend": "react", "backend": "django", "database": "postgresql", "cache": "redis", "search": "elasticsearch" }, "extras": { "prp": true, "validation": true, "docker": true, "cicd": true, "testing": true } } # Run with config $ context-forge init --config context-forge.json --output ecommerce-platform
๐ฏ Real-World Scenarios
Scenario 1: Startup MVP
You're building an MVP for a startup. You need to move fast but maintain quality:
# 1. Initialize with MVP timeline context-forge init --preset startup-mvp # 2. Review generated Implementation.md cat Docs/Implementation.md # Shows 2-week sprint plan with daily tasks # 3. Start development with Claude Code # Open CLAUDE.md in Claude Code # Follow Stage 1 tasks systematically # 4. Validate progress daily context-forge validate --levels syntax,tests
Scenario 2: Enterprise Migration
Migrating a legacy system to modern stack:
# 1. Create detailed PRD first context-forge init --prd legacy-migration-prd.md # 2. Select enterprise options # - Choose 'enterprise' timeline # - Enable all validation options # - Select comprehensive testing # 3. Generated structure includes: # - Migration strategy in Implementation.md # - Rollback procedures # - Comprehensive test suites # - Security audit checklists
Scenario 3: Hackathon Project
24-hour hackathon, need to prototype fast:
# 1. Quick setup npx context-forge init --preset hackathon # 2. Skip optional features # - Disable PRP (too detailed for hackathon) # - Basic validation only # - Focus on core features # 3. Get building in < 5 minutes # CLAUDE.md has simplified rules for rapid development
๐ง Retrofitting Existing Projects
NEW in v3.1.3+: The analyze command allows you to retrofit existing codebases with AI-optimized documentation. This is perfect for:
- Adding AI assistance to legacy projects
- Upgrading existing projects with modern context engineering
- Planning new features for established codebases
- Generating PRPs for upcoming development work
How it Works
- Smart Analysis: Automatically detects your tech stack, project structure, and existing documentation
- Interactive Setup: Asks about your future development plans
- Non-Destructive: Never overwrites existing files (appends to CLAUDE.md with clear markers)
- Feature PRPs: Generates individual PRP files for each planned feature
- Comprehensive Summary: Creates a detailed retrofit summary with file tree visualization
Usage
# Run in your existing project directory cd /path/to/your/project context-forge analyze # Specify output directory context-forge analyze --output ./ai-docs # Target specific IDEs context-forge analyze --ide claude,cursor # Skip AI analysis for faster setup context-forge analyze --no-ai
Example Output
๐ Generated Files:
โโโ CLAUDE.md (UPDATED - appended retrofit section)
โโโ Docs/
โ โโโ Implementation.md
โ โโโ project_structure.md
โ โโโ UI_UX_doc.md
โ โโโ Bug_tracking.md
โโโ PRPs/
โโโ user-authentication-prp.md
โโโ payment-integration-prp.md
โโโ api-v2-prp.md
The analyze command is intelligent enough to:
- Detect if you're using TypeScript, Python, or other languages
- Identify frameworks like React, Next.js, Express, FastAPI
- Find existing documentation to use as context
- Ask about your future plans to generate relevant PRPs
๐ Technology Migration
NEW in v3.1.4: The migrate command helps you safely transition between technology stacks with comprehensive planning, risk analysis, and rollback strategies.
When to Use Migration
Perfect for:
- Modernizing legacy applications (e.g., jQuery โ React, Flask โ FastAPI)
- Switching frameworks (e.g., Express โ Next.js, Django โ FastAPI)
- Adopting new technologies while maintaining production stability
- Planning complex migrations with shared resources (databases, auth systems)
How Migration Works
- Analyzes Current Stack: Detects your existing technology and architecture
- Assesses Complexity: Calculates migration risks and shared resource dependencies
- Creates Phased Plan: Generates step-by-step migration with checkpoints
- Provides Safety Net: Includes comprehensive rollback procedures
- Monitors Progress: Tracks migration status with validation gates
Usage
# Interactive migration planning context-forge migrate # Specify target technology context-forge migrate --target "Next.js" # Quick mode (skip detailed analysis) context-forge migrate --quick --target "FastAPI" # Analyze only (no file generation) context-forge migrate --analyze-only
Example Migration Output
๐ Migration Analysis Complete!
Source: Flask + Jinja2 + SQLAlchemy
Target: Next.js + FastAPI + Prisma
Complexity: HIGH (Score: 78/100)
Recommended Strategy: parallel-run
๐ Generated Migration Files:
โโโ CLAUDE.md (Migration-aware configuration)
โโโ PRPs/
โ โโโ migration-overview.md
โ โโโ phase-1-infrastructure.md
โ โโโ phase-2-api-migration.md
โ โโโ phase-3-frontend-migration.md
โ โโโ rollback-procedures.md
โโโ .claude/
โโโ commands/migration/
โ โโโ migration-status.md
โ โโโ migration-checkpoint.md
โ โโโ migration-rollback.md
โโโ hooks/
โโโ MigrationCheckpoint.py
โโโ DataIntegrityCheck.py
Migration Features
- Shared Resource Detection: Identifies databases, auth systems, and APIs used by both systems
- Risk Assessment: Analyzes potential breaking changes and data integrity risks
- Parallel-Run Support: Enables running old and new systems simultaneously
- Checkpoint System: Human verification at critical migration milestones
- Rollback Planning: One-command rollback to any checkpoint
- Progress Monitoring: Real-time migration status and health checks
Migration Strategies
- Big-Bang: Complete cutover (low complexity projects)
- Incremental: Feature-by-feature migration (medium complexity)
- Parallel-Run: Both systems active during transition (high complexity)
๐ Documentation
Generated Files Structure
Context Forge creates IDE-specific documentation structures:
Claude Code (Default)
project-folder/
โโโ CLAUDE.md # Main context file with tech-stack specific rules
โโโ Docs/
โ โโโ Implementation.md # Staged development plan
โ โโโ project_structure.md # Folder organization
โ โโโ UI_UX_doc.md # Design specifications
โ โโโ Bug_tracking.md # Bug tracking template
โโโ PRPs/ # Product Requirement Prompts (if enabled)
โ โโโ {project}-prp.md # Base implementation PRP
โ โโโ {project}-planning.md # Architecture planning (if enterprise/team)
โ โโโ {feature}-prp.md # Feature-specific PRPs (if retrofit)
โโโ .claude/ # Claude Code specific configuration
โ โโโ commands/ # Slash commands (20+ commands)
โ โ โโโ PRPs/ # PRP management commands
โ โ โโโ development/ # Development workflow commands
โ โ โโโ checkpoints/ # Human-in-the-loop commands
โ โ โโโ migration/ # Migration commands (if applicable)
โ โโโ hooks/ # Claude Code hooks (if enabled)
โ โโโ PreCompact.py # Context preservation hook
โ โโโ ContextRotation.py # Smart file switching
โ โโโ PreSubmit.py # Quality gates
โ โโโ PRPTracking.py # Progress monitoring
โ โโโ DartProgressUpdater.py # Dart task progress tracking
โ โโโ AutoTaskCommenter.py # Automated task documentation
โ โโโ TaskCodeMapper.py # File-to-task mapping
โโโ ai_docs/ # AI documentation curation (if enabled)
โโโ README.md # Documentation guide
Cursor IDE
project-folder/
โโโ .cursorrules # Main Cursor rules file
โโโ .cursor/
โโโ rules/
โโโ global.md # Global development rules
โโโ project.md # Project-specific rules
โโโ prp-overview.mdc # PRP implementation overview
โโโ prp-stage-1.mdc # Foundation setup tasks
โโโ prp-stage-2.mdc # Core feature implementation
โโโ prp-stage-3.mdc # Advanced features & polish
โโโ prp-validation.mdc # Validation gates & checks
Cline
project-folder/
โโโ .clinerules/ # Configuration directory
โโโ README.md # Main configuration
โโโ context.md # Project context
โโโ rules.md # Development rules
โโโ patterns.md # Code patterns
โโโ prp-overview.md # PRP implementation overview
โโโ prp-stage-1.md # Foundation setup tasks
โโโ prp-stage-2.md # Core feature implementation
โโโ prp-stage-3.md # Advanced features & polish
โโโ prp-validation.md # Validation gates & checks
Gemini
project-folder/
โโโ GEMINI.md # Main Gemini configuration
โโโ .gemini/
โโโ context/
โ โโโ project.md # Project context
โ โโโ architecture.md # Architecture docs
โ โโโ guidelines.md # Development guidelines
โโโ prp/ # PRP files (if features defined)
โ โโโ overview.md # PRP implementation overview
โ โโโ stage-1-foundation.md
โ โโโ stage-2-core.md
โ โโโ stage-3-advanced.md
โ โโโ validation.md
โโโ config.yaml # Gemini config with PRP settings
Understanding Generated Files
CLAUDE.md
The main context file that Claude Code reads first. It contains:
- Project overview and tech stack
- Development philosophy (KISS, YAGNI)
- Code structure rules and limits
- Tech-stack specific guidelines
- Testing requirements
- Pre-commit checklist
Docs/Implementation.md
Your roadmap with staged development:
- Stage 1: Foundation (1-2 weeks) - Setup, configuration, base structure
- Stage 2: Core Features (2-3 weeks) - Must-have functionality
- Stage 3: Advanced Features (2-3 weeks) - Should-have features
- Stage 4: Polish & Optimization (1-2 weeks) - Testing, performance
Each stage contains:
- Dependencies and prerequisites
- Detailed task checklist
- Validation requirements
- Expected deliverables
PRPs (Product Requirement Prompts)
Advanced prompts for complex implementations:
- base.md - Implementation blueprint with pseudocode
- planning.md - Architecture diagrams and decisions
- spec.md - Technical specifications
- validation-gate.md - Quality checkpoints
Interactive Setup Flow
When you run context-forge init, you'll be guided through:
- Project Information - Name, type, and description
- PRD Input - Provide or create product requirements
- Tech Stack Selection - Choose frontend, backend, and database
- Feature Selection - Pick core features for your MVP
- Configuration - Timeline, team size, and deployment
- Advanced Options - PRP, validation, AI docs
Supported Tech Stacks
Frontend Frameworks
- Next.js 15 - App Router, Server Components, React 19
- Nuxt 4 - NEW! Vue-based full-stack with enhanced TypeScript support
- React - SPA with TypeScript and modern patterns
- Vue.js 3 - Composition API and TypeScript
- Angular - Standalone components, RxJS
- Vanilla JavaScript - No framework approach
Backend Frameworks
- FastAPI (Python) - Async, Pydantic v2, type hints
- Express.js (Node.js) - TypeScript, middleware patterns
- Django (Python) - MVT, ORM, admin interface
- Spring Boot (Java) - REST APIs, dependency injection
- Ruby on Rails - Convention over configuration
Databases
- PostgreSQL, MySQL, MongoDB, SQLite, Redis
Validation System
Context Forge includes a powerful validation system that ensures code quality:
# Run all critical validations context-forge validate # Run specific validation levels context-forge validate --levels syntax,tests # Run all validations including optional ones context-forge validate --all # Generate detailed report context-forge validate --report # Validate in specific directory context-forge validate --path ./my-project
Validation Levels
| Level | Description | Critical | Commands |
|---|---|---|---|
| syntax | Type checking and linting | โ Yes | tsc, eslint, mypy, etc. |
| tests | Unit and integration tests | โ Yes | jest, pytest, rspec, etc. |
| coverage | Code coverage analysis | โ No | With coverage reporters |
| build | Production build | โ Yes | Framework-specific build |
| security | Vulnerability scanning | โ No | npm audit, safety, etc. |
Example Validation Report
๐ Validation Report - Analytics Dashboard
==================================================
โ
Status: PASSED
Total: 5 | Passed: 5 | Failed: 0
โ
syntax:tsc --noEmit (342ms)
โ
syntax:eslint src --ext .ts,.tsx (567ms)
โ
tests:jest --coverage (4521ms)
โ
build:next build (8234ms)
โ
security:npm audit (1023ms)
Full report saved to: .validation-reports/latest-report.md
Configuration File
Skip interactive prompts with a configuration file:
{
"projectName": "My App",
"projectType": "fullstack",
"description": "A collaborative platform",
"techStack": {
"frontend": "nextjs",
"backend": "fastapi",
"database": "postgresql",
"auth": "jwt"
},
"features": [
{
"id": "auth",
"name": "Authentication",
"priority": "must-have"
}
],
"extras": {
"prp": true,
"validation": true,
"docker": true
}
}Use with: context-forge init --config context-forge.json
๐ Complete Workflow
Step 1: Initialize Your Project
# Run the init command context-forge init # Answer the interactive prompts # Context Forge will analyze your requirements and generate appropriate documentation
Step 2: Review Generated Documentation
# 1. Start with CLAUDE.md cat CLAUDE.md # This is your project's "constitution" - rules Claude Code will follow # 2. Check your implementation plan cat Docs/Implementation.md # This breaks down development into manageable stages # 3. Review project structure cat Docs/project_structure.md # This defines how your code should be organized
Step 3: Start Development with Claude Code
- Open your project in Claude Code
- Add the entire project folder to Claude's context
- Start with Stage 1 tasks from Implementation.md
- Claude will follow the rules in CLAUDE.md automatically
Step 4: Validate Your Progress
# After completing each stage context-forge validate # Before committing code context-forge validate --levels syntax,tests # For comprehensive check context-forge validate --all --report
Step 5: Iterate and Improve
- Update Bug_tracking.md when you encounter issues
- Claude Code will learn from documented bugs
- Run validation frequently to maintain quality
๐ฎ Advanced Usage
Custom Templates
Create your own templates in ~/.context-forge/templates/:
# Custom tech stack template ~/.context-forge/templates/claude/my-stack.md # Custom validation commands ~/.context-forge/templates/validation/my-validation.json
Hooks and Automation
Add pre/post hooks in .context-forge/hooks/:
# pre-init.sh - Run before initialization #!/bin/bash echo "Setting up environment..." # post-init.sh - Run after initialization #!/bin/bash echo "Installing dependencies..." npm install
CI/CD Integration
# .github/workflows/validate.yml name: Context Forge Validation on: [push, pull_request] jobs: validate: runs-on: ubuntu-latest steps: - uses: actions/checkout@v3 - uses: actions/setup-node@v3 - run: npm install -g context-forge - run: context-forge validate --all
๐๏ธ Development
# Clone the repository git clone https://github.com/webdevtodayjason/context-forge.git cd context-forge # Install dependencies npm install # Build the project npm run build # Run in development mode npm run dev # Run tests npm test # Run linting npm run lint
Project Structure
context-forge/
โโโ src/
โ โโโ cli/ # CLI entry point and commands
โ โโโ commands/ # Command implementations
โ โโโ generators/ # Document generators
โ โโโ templates/ # Handlebars templates
โ โโโ data/ # Tech stack configurations
โ โโโ types/ # TypeScript definitions
โโโ templates/ # Document templates
โโโ tests/ # Test files
๐ Credits
Special Thanks
This project was inspired by and built upon the work of amazing developers:
- Rasmus Widing (Wirasm) - For the incredible PRPs-agentic-eng project that provided the foundation for our PRP (Product Requirement Prompt) system. The PRP methodology and validation loops are directly inspired by Rasmus's groundbreaking work.
- AILABS (@AILABS-393) - For the excellent educational content and YouTube tutorials on AI-assisted development, prompt engineering, and Claude Code workflows
- AI Labs Discord Community - For feedback, ideas, and support
- Dynamous.ai Community - For pioneering work in AI-assisted development and collaborative innovation
Built With
- Andre Karpathy - Context engineering principles
- Claude Code by Anthropic - The AI assistant this tool is designed for
- Commander.js - CLI framework
- Inquirer.js - Interactive prompts
- Handlebars - Template engine
๐ค Contributing
Contributions are welcome! Please read our Contributing Guide for details on our code of conduct and the process for submitting pull requests.
Ways to Contribute
- ๐ Report bugs and issues
- ๐ก Suggest new features
- ๐ Improve documentation
- ๐ง Add new tech stack templates
- ๐ Translate documentation
- โญ Star the project!
๐ License
This project is licensed under the MIT License - see the LICENSE file for details.
๐ Links
- Repository: github.com/webdevtodayjason/context-forge
- npm Package: npmjs.com/package/context-forge
- Issues: GitHub Issues
- Discussions: GitHub Discussions
Made with โค๏ธ by the Context Forge community
Empowering developers to build smarter, not harder



