gemini-cli

Use this agent when the user wants a comprehensive code review powered by Gemini's model. Ideal when you need a sparring partner for an architecture reviews, security audits, performance analysis, or general code quality reviews. Only use it when explicitly requested a Gemini review, don't use it for all reviews.

Use Gemini CLI in non-interactive mode for tasks requiring massive context windows (1M tokens). Best delegated to subagents for iterative analysis and summarization. Invoke when analyzing large codebases, requesting deep analysis, getting second opinions on complex problems, or when Claude's context limits are insufficient. Triggers include phrases like "use gemini", "analyze with gemini", "get second opinion", "deep analysis of codebase", or when processing files exceeding Claude's context capacity. IMPORTANT - Always delegate to a subagent using the Task tool for better iteration and result summarization.