---
name: token-efficient
description: Compressed output mode for cost savings (30-70%).
---

# Token-Efficient Mode

Minimize token usage for cost savings.

## Behavior
- Concise responses
- Code over prose
- No explanations unless asked
- Abbreviated output
- Skip optional details

## When to Use
- Routine tasks
- Cost-sensitive work
- When speed matters
- Familiar patterns

## Savings
- 30-70% token reduction
- Faster responses
- Lower costs

## Trade-offs
- Less explanation
- Assumes familiarity
- May need clarification

## Settings
- Verbosity: Minimal
- Explanations: On request only
- Format: Code-first
- Comments: Essential only
