菜单
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. "codex", "코덱스", "codex 실행", "codex exec", "코드 검증", "AI 리뷰" 키워드에 반응.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Orchestrates a dual-AI engineering loop where Claude CLI runs with `--dangerously-skip-permissions` for planning/implementation and Codex validates/reviews outputs. Use when users ask for Claude+Codex collaboration, cross-review, dual AI loop, or explicit Claude CLI execution with skip-permission mode ("claude", "dangerously-skip-permission", "dangerously-skip-permissions", "codex claude", "dual AI", "교차 검증", "claude 협업").
Codex Agent 작성 전문가. Frontmatter 검증, 트리거 키워드 제안, 구조 템플릿 제공, 테스트 시나리오 작성을 지원합니다.
Synchronize all agile development artifacts in one command. Updates CHANGELOG, README stats, progress tracking, and validates documentation completeness.
Agent/Skill 사용 통계 및 성과 리포트 생성 전문가. CLI 차트로 시각화하고 인사이트를 제공합니다. "통계", "사용량", "analytics", "성과", "리포트", "메트릭", "분석", "usage", "metrics", "statistics", "report" 키워드에 반응.
Tool/Agent 사용 통계를 CLI 차트로 시각화. "통계", "사용량", "analytics", "metrics", "리포트" 키워드에 반응.
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
| name | codex |
| description | Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. "codex", "코덱스", "codex 실행", "codex exec", "코드 검증", "AI 리뷰" 키워드에 반응. |
Codex CLI를 통한 코드 분석, 리팩토링, 자동 편집 실행.
| Model | Description | Use Case |
|---|---|---|
gpt-5.2-codex | 최신 에이전틱 코딩 모델 (기본값) | 일반 코딩, 리팩토링, 분석 |
gpt-5.1-codex-mini | 경량 비용 효율 모델 | 빠른 리뷰, 간단한 작업 |
gpt-5.1-codex-max | 확장 에이전틱 코딩 모델 | 대규모 리팩토링, 장시간 작업 |
| Step | Action |
|---|---|
| 1 | ask the user: model (gpt-5.2-codex (Recommended), gpt-5.1-codex-mini, gpt-5.1-codex-max) |
| 2 | ask the user: reasoning effort (low, medium, high) |
| 3 | Select sandbox mode (default: read-only) |
| 4 | Assemble and run command |
| 5 | Capture output, summarize for user |
| Flag | Purpose |
|---|---|
-m, --model <MODEL> | Model selection |
--config model_reasoning_effort="<level>" | Reasoning effort |
--sandbox <mode> | Sandbox mode |
--full-auto | Full automation |
-C, --cd <DIR> | Working directory |
--skip-git-repo-check | Skip git check |
| Use Case | Mode | Flags |
|---|---|---|
| Read-only review | read-only | --sandbox read-only |
| Apply local edits | workspace-write | --sandbox workspace-write --full-auto |
| Network/broad access | danger-full-access | --sandbox danger-full-access --full-auto |
| Resume session | Inherited | echo "prompt" | codex exec resume --last |
Resume: Cannot specify flags — inherits all from original session.
codex command → ask the user for next stepsecho "new prompt" | codex exec resume --last| Situation | Action |
|---|---|
| Non-zero exit | Stop, report, ask direction |
| High-impact flags | ask the user for permission first |
| Warnings/partial results | Summarize, ask how to adjust |