gemini-cli

# Gemini CLI Integration

Always run through subagents for better iteration and summarization. Make the subagent always ask Gemini to provide evidence, and make the subagent verify the findings before summarizing for the main agent.

## Quick Reference

```bash
# Basic one-shot query (non-interactive mode)
gemini "Explain this codebase architecture"

# Specify model
gemini -m gemini-3-flash-preview "Complex analysis task"
gemini -m gemini-2.5-flash "Standard analysis task"
gemini -m gemini-2.5-pro "Deep reasoning task"

# Include additional directories
gemini --include-directories ./libs,./shared "Analyze dependencies"

# Multi-line prompt using heredoc
gemini <<'__GEMINI_PROMPT__'
Analyze this codebase for security vulnerabilities.
Focus on: SQL injection, XSS, authentication issues
__GEMINI_PROMPT__

# Output formats
gemini -o json "query"
gemini -o text "query"        # default
gemini -o stream-json "query"
```

## Available Models

### Gemini 3 (Preview)
- **gemini-3-flash-preview** - Best for agentic coding (78% SWE-bench), 1/4 cost of Pro.
- **gemini-3-pro-preview** - Most powerful for multimodal understanding and deep reasoning.

### Gemini 2.5 (GA)
- **gemini-2.5-flash** - Stable, fast
- **gemini-2.5-pro** - Balanced performance for complex tasks
- **gemini-2.5-flash-lite** - Lowest latency and cost

## Subagent Delegation Pattern

**CRITICAL:** Always delegate Gemini tasks to a subagent using the Task tool for multiple retry attempts, better summarization, and error handling.

### Pattern: Using Task Tool with Gemini

```bash
Task(
  subagent_type: "general-purpose",
  description: "Analyze codebase with Gemini",
  prompt: "Use the gemini-cli skill to analyze /path/to/project.
  Focus on security vulnerabilities and performance issues.
  See references/prompt_patterns.md for effective prompts.
  Ask Gemini to provide evidence for findings.
  Verify findings before summarizing key points in bullet form."
)
```

### Pattern: Second Opinion

```bash
Task(
  su