gemini-token-optimization

# Gemini Token Optimization

## 🚨 MANDATORY: Invoke gemini-cli-docs First

> **STOP - Before providing ANY response about Gemini token usage:**
>
> 1. **INVOKE** `gemini-cli-docs` skill
> 2. **QUERY** for the specific token or pricing topic
> 3. **BASE** all responses EXCLUSIVELY on official documentation loaded

## Overview

Skill for optimizing cost and token usage when delegating to Gemini CLI. Essential for efficient bulk operations and cost-conscious workflows.

## When to Use This Skill

**Keywords:** token usage, cost optimization, gemini cost, model selection, flash vs pro, caching, batch queries, reduce tokens

**Use this skill when:**

- Planning bulk Gemini operations
- Optimizing costs for large-scale analysis
- Choosing between Flash and Pro models
- Understanding token caching benefits
- Tracking usage across sessions

## Token Caching

Gemini CLI automatically caches context to reduce costs by reusing previously processed content.

### Availability

| Auth Method | Caching Available |
| --- | --- |
| API key (Gemini API) | YES |
| Vertex AI | YES |
| OAuth (personal/enterprise) | NO |

### How It Works

- System instructions and repeated context are cached
- Cached tokens don't count toward billing
- View savings via `/stats` command or JSON output

### Maximizing Cache Hits

1. **Use consistent system prompts** - Same prefix increases cache reuse
2. **Batch similar queries** - Group related analysis together
3. **Reuse context files** - Same files in same order

### Monitoring Cache Usage

```bash
result=$(gemini "query" --output-format json)
total=$(echo "$result" | jq '.stats.models | to_entries | map(.value.tokens.total) | add // 0')
cached=$(echo "$result" | jq '.stats.models | to_entries | map(.value.tokens.cached) | add // 0')
billable=$((total - cached))
savings=$((cached * 100 / total))

echo "Total: $total tokens"
echo "Cached: $cached tokens ($savings% savings)"
echo "Billable: $billable tokens"
```

## Model Selection

### Model Compariso