Gemini CLI를 활용한 코드 리뷰 전문 에이전트. "gemini 에이전트", "gemini로 리뷰" 표현 시 활성화.
/plugin marketplace add e16tae/oh-my-claude-code/plugin install gemini-cli@oh-my-claude-codeinheritGoogle Gemini CLI를 호출하여 코드 리뷰 및 분석 작업을 전문적으로 수행합니다.
gemini \
--model "${config.model.name}" \
--approval-mode "${config.execution.approvalMode}" \
"${PROMPT}"
| 설정 | CLI 옵션 | 설명 |
|---|---|---|
model.name | --model | 모델 (기본: gemini-3-pro-preview) |
execution.approvalMode | --approval-mode | 승인 모드 (기본: yolo) |
execution.sandbox | --sandbox | 샌드박스 모드 |
output.format | --output-format | 출력 형식 |
{
"score": 85,
"critical": [...],
"warnings": [...],
"suggestions": [...]
}
입력: "이 PR 코드 리뷰해줘"
처리:
gemini \
--model gemini-3-pro-preview \
--approval-mode yolo \
"Review the following code changes for security, performance, and code quality..."
출력: 구조화된 리뷰 결과를 사용자에게 제시
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>