Performance Optimization
Model Selection Strategy
Haiku 4.5 (90% of Sonnet capability, 3x cost savings):
- Lightweight agents with frequent invocation
- Pair programming and code generation
- Worker agents in multi-agent systems
Sonnet 4.5 (Best coding model):
- Main development work
- Orchestrating multi-agent workflows
- Complex coding tasks
Opus 4.5 (Deepest reasoning):
- Complex architectural decisions
- Maximum reasoning requirements
- Research and analysis tasks
Context Window Management
Avoid last 20% of context window for:
- Large-scale refactoring
- Feature implementation spanning multiple files
- Debugging complex interactions
Lower context sensitivity tasks:
- Single-file edits
- Independent utility creation
- Documentation updates
- Simple bug fixes
Ultrathink + Plan Mode
For complex tasks requiring deep reasoning:
- Use
ultrathinkfor enhanced thinking - Enable Plan Mode for structured approach
- "Rev the engine" with multiple critique rounds
- Use split role sub-agents for diverse analysis
Build Troubleshooting
If build fails:
- Use build-error-resolver agent
- Analyze error messages
- Fix incrementally
- Verify after each fix