멀티 에이전트 협업 프레임워크 Claude Code가 Codex CLI(심층 추론)와 Gemini CLI(대규모 리서치)를 오케스트레이션하여 각 에이전트의 강점을 극대화하고 개발 속도와 품질을 동시에 끌어올리는 구조다. IMPORTANT: 각 에이전트는 단독으로도 강력하지만, 의도적으로 역할을 분리했을 때 성능이 폭발한다. Claude Code의 최대 컨텍스트는 200k 토큰이지만, 툴 정의 / 시스템 프롬프트 등을 제외하면 실질적으로 70~100k 수준이다. YOU MUST 👉 그래서 출력이 큰 작업은 반드시 서브 에이전트 경유가 원칙이다. → 참고: .claude/rules/codex-delegation.md → 참고: .claude/rules/gemini-delegation.md → 관련 커맨드: /startproject, /plan, /tdd skills → 참고: .claude/rules/dev-environment.md
189mo agoReviewMountCreate a free account to mount
Save session context to agent configuration files or create full checkpoint files. Supports three modes: session history (default), full checkpoint (--full), and skill analysis (--full --analyze) for extracting reusable patterns.
189mo agoReviewMountCreate a free account to mount
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
189mo agoReviewMountCreate a free account to mount
PROACTIVELY track and document project design decisions without being asked. Activate automatically when detecting architecture discussions, implementation decisions, pattern choices, library selections, or any technical decisions. Also use when user explicitly says "記録して", "設計どうなってる", "record this". Do NOT wait for user to ask - record important decisions immediately.
189mo agoReviewMountCreate a free account to mount
PROACTIVELY consult Gemini CLI for research, large codebase comprehension, and multimodal data processing. Gemini excels at: massive context windows (1M tokens), Google Search grounding, video/audio/PDF analysis, and repository-wide understanding. Use for pre-implementation research, documentation analysis, and multimodal tasks. Explicit triggers: "research", "investigate", "analyze video/audio/PDF", "understand codebase".
189mo agoReviewMountCreate a free account to mount
You are called by Claude Code for deep reasoning tasks. You are part of a multi-agent system. Claude Code handles orchestration and execution. You provide deep analysis that Claude Code cannot do efficiently in its context. You can read project context from .claude/: Always check these before giving advice. Structure your response for Claude Code to use: Codex/Gemini 에의 입출력은 .claude/logs/cli-tools.jsonl 에 기록되고 있다. 과거 상담 내용을 확인하려면 이 로그를 참조한다. /checkpointing 실행 후 아래에 Session History가 추가된다.
189mo agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.