context-forge
Version:
AI orchestration platform with autonomous teams, enhancement planning, migration tools, 25+ slash commands, checkpoints & hooks. Multi-IDE: Claude, Cursor, Windsurf, Cline, Copilot
291 lines (225 loc) • 6.54 kB
Markdown
Retrofit Guide - Context Forge
# What is Retrofit?
The retrofit feature (via the `analyze` command) allows you to add AI-optimized documentation and configuration to existing projects. It's designed to seamlessly integrate Context Forge into established codebases without disrupting your current workflow.
# When to Use Retrofit
Use the `analyze` command when you have:
- An existing project that needs AI documentation
- A legacy codebase you want to modernize with AI assistance
- A project you're inheriting and need to understand
- A codebase that lacks proper documentation
# Step-by-Step Workflow
## 1. Initial Analysis
```bash
Basic analysis
context-forge analyze
With specific output directory
context-forge analyze -o ./ai-docs
Target specific IDEs
context-forge analyze -i claude,cursor
```
## 2. What Gets Analyzed
The analyzer examines:
- **Project Structure**: Directory layout, file organization
- **Tech Stack**: Frameworks, libraries, dependencies
- **Code Patterns**: Architecture, design patterns
- **Quality Metrics**: Complexity, test coverage
- **Documentation**: Existing docs, comments, READMEs
## 3. Interactive Configuration
During analysis, you'll be asked about:
1. **Project Confirmation**
- Verify detected tech stack
- Confirm project type
- Set project name and description
2. **Documentation Preferences**
- Choose documentation depth
- Select target AI IDEs
- Enable advanced features
3. **Integration Options**
- Slash commands (Claude Code)
- Hooks and automation
- Checkpoint system
## 4. Generated Outputs
### Standard Files
```
your-project/
├── CLAUDE.md # Main context file
├── PRPs/ # Implementation guides
│ └── retrofit/ # Retrofit-specific PRPs
└── .gitignore # Updated with AI files
```
### Claude Code Specific
```
.claude/
├── commands/ # Custom slash commands
│ ├── run-tests.md
│ ├── check-lint.md
│ └── project-status.md
├── hooks/ # Automation scripts
│ ├── pre-commit.py
│ └── post-test.py
└── docs/ # Extended documentation
```
# Common Retrofit Patterns
## 1. Minimal Integration
For projects that just need basic AI context:
```bash
context-forge analyze --quick
```
## 2. Full Integration
For comprehensive AI assistance:
```bash
context-forge analyze --deep
```
## 3. Incremental Adoption
Start small and expand:
```bash
Phase 1: Basic documentation
context-forge analyze --quick
Phase 2: Add PRPs
context-forge analyze --prp
Phase 3: Enable automation
context-forge analyze --hooks --checkpoints
```
# Handling Special Cases
## 1. Monorepos
```bash
Analyze from monorepo root
cd my-monorepo
context-forge analyze
Or analyze specific package
cd packages/api
context-forge analyze --scope package
```
## 2. Legacy Codebases
```bash
Use legacy mode for older projects
context-forge analyze --legacy
This enables:
- Broader framework detection
- Legacy pattern recognition
- Compatibility documentation
```
## 3. Mixed Tech Stacks
```bash
Explicitly specify primary stack
context-forge analyze --primary-stack react
For full-stack projects
context-forge analyze --full-stack
```
# Advanced Usage
## 1. Custom Analysis Depth
```bash
Shallow analysis (faster)
context-forge analyze --depth shallow
Deep analysis (comprehensive)
context-forge analyze --depth deep
With AI-powered insights
context-forge analyze --ai-insights
```
## 2. Excluding Paths
```bash
Exclude specific directories
context-forge analyze --exclude node_modules,dist,build
Use .cfignore file
echo "*.test.js" >> .cfignore
context-forge analyze
```
## 3. Framework-Specific Options
```bash
React projects
context-forge analyze --framework react --detect-patterns hooks,context
Node.js APIs
context-forge analyze --framework express --detect-patterns middleware,routes
```
# Integration with Existing Tools
## 1. Preserving Existing Documentation
Context Forge appends to existing files rather than overwriting:
- Existing CLAUDE.md files are backed up
- READMEs are preserved
- Comments in code remain untouched
## 2. Git Integration
```bash
See what will be added
context-forge analyze --dry-run
Commit AI documentation separately
git add .claude CLAUDE.md PRPs/
git commit -m "Add AI development context"
```
## 3. CI/CD Compatibility
Add to your CI pipeline:
```yaml
.github/workflows/ai-docs.yml
- name: Update AI Documentation
run: |
npx context-forge analyze --ci
git add .
git commit -m "Update AI context" || true
```
# Best Practices
## 1. Initial Setup
- Run analysis on a clean working directory
- Review detected tech stack carefully
- Enable all Claude Code features if using Claude
## 2. Maintenance
- Re-run analysis after major changes
- Update PRPs when adding features
- Keep slash commands synchronized
## 3. Team Adoption
- Share generated docs with team
- Document custom patterns in ai_docs/
- Create team-specific PRPs
# Example: Retrofitting a React App
```bash
1. Navigate to your React project
cd my-react-app
2. Run comprehensive analysis
context-forge analyze -i claude --deep
3. During prompts:
- Confirm React + TypeScript stack
- Enable hooks, commands, checkpoints
- Select comprehensive documentation
4. Review generated files
cat CLAUDE.md
ls -la .claude/commands/
ls -la PRPs/
5. Test with Claude Code
Open project in Claude Code
Try: /project-status
Try: /run-tests
```
# Troubleshooting
## Detection Issues
```bash
Force framework detection
context-forge analyze --force-detect
Specify frameworks manually
context-forge analyze --frameworks react,typescript,jest
```
## Performance
```bash
For large codebases
context-forge analyze --parallel
Limit file scanning
context-forge analyze --max-files 1000
```
## Integration Problems
```bash
Check compatibility
context-forge analyze --check-only
Generate report
context-forge analyze --report-only
```
# Next Steps
After retrofitting your project:
1. **Test AI Integration**
- Open in your AI IDE
- Test slash commands
- Verify context understanding
2. **Enhance Documentation**
- Add project-specific PRPs
- Document unique patterns
- Create custom commands
3. **Plan Improvements**
- Use `enhance` for new features
- Consider `migrate` for tech updates
- Keep context current with regular analysis