Context Optimization

​

Why Context Matters

• Decision accuracy - Better context = better decisions
• Token efficiency - Optimized context = lower costs
• Response speed - Focused context = faster processing

​

Context Feeding Strategies

​

Progressive Disclosure

# Level 1: Task Context (always include)
- Current objective
- Immediate constraints
- Expected output format

# Level 2: Domain Context (include when relevant)
- Project conventions
- Team standards
- Historical decisions

# Level 3: Deep Context (include on-demand)
- Full codebase structure
- Complete documentation
- External references

​

Structured Context Files

project/
├── CLAUDE.md           # Project-level context
├── src/
│   └── CLAUDE.md       # Module-specific context
└── .agents/
    └── memory/         # Dynamic agent memory

project/
├── GEMINI.md           # Project-level context
├── src/
│   └── GEMINI.md       # Module-specific context
└── .gemini/
    └── settings.json   # Tool configuration

project/
├── AGENTS.md           # Project-level context
├── src/
│   └── AGENTS.md       # Module-specific context
└── .opencode/
    └── config.json     # Tool configuration

project/
├── .cursorrules        # Project instructions
└── .cursor/
    └── rules/          # Additional rule files

project/
└── .github/
    └── copilot-instructions.md

project/
├── .windsurfrules      # Project instructions
└── .windsurf/
    └── rules/          # Additional rules

​

Context Hierarchy

1. System context - Model capabilities, safety guidelines
2. User context - Personal preferences (global CLAUDE.md)
3. Project context - Codebase rules (project CLAUDE.md)
4. Task context - Current objective, constraints
5. Dynamic context - Retrieved knowledge, memory queries

​

Optimization Techniques

​

Minimize Redundant Reads

# Bad: Reading the same file multiple times
Read file.ts
# ... do something ...
Read file.ts  # Redundant!

# Good: Read once, reference in context
Read file.ts
# Continue working with the content already in context

​

Use Targeted Queries

# Bad: Read entire codebase
Read **/*.ts

# Good: Query specific patterns
Grep "export function" --type ts
Glob "src/api/**/*.ts"

​

Leverage Memory

# Check existing knowledge before researching
squads memory query "authentication patterns"

# Update memory after discoveries
squads memory update engineering

​

Context Window Management

​

Monitor Usage

​

When Context Gets Large

1. Summarize - Compress verbose content
2. Prune - Remove irrelevant sections
3. Externalize - Store in memory, reference by key
4. Delegate - Spawn sub-agents with focused context

​

Anti-Patterns

​

Best Practices Checklist

​

Related