~14 min · decision-framework, cross-tool, tool-selection
적합한 CLI 가 일에 fit 하는 거 — 친구가 사용하는 거나 가장 큰 블로그 포스트 가진 거 X. 간단한 프레임워크: (1) 작업 부하가 뭔지 (코드 편집? 리서치 합성? 원격 작업? 웹 자동화?), (2) 신뢰 프로필 뭔지 (네 repo 또는 남의? 민감 코드 또는 실험적?), (3) 비용 모양 뭔지 (일회성, 반복, 병렬 fan-out?).
실용 default: 터미널의 코드 편집 → Claude Code (가장 깊은 IDE-like 흐름), Codex (오픈소스, multi-provider 인증), 또는 Gemini (1M context, free tier). knowledge 작업, 파일 네이티브 리서치 → Cowork. 모바일-to-Mac async → Dispatch. 머신 가로지르는 긴 세션 → Claude Remote. 웹 작업, booking/양식 → Operator. 빠른 async 질문 → Claude.ai 또는 ChatGPT Desktop.
1. What kind of work?
• Code editing → Step 2
• Knowledge work / research / docs → Cowork
• Web automation (booking, etc.) → Operator
• Quick async questions → claude.ai / ChatGPT Desktop
2. Code editing — which CLI?
• Need 1M context / free tier → Gemini
• Open source, multi-provider auth → Codex
• Deepest skill / hook ecosystem → Claude Code
• Already using one — stay there → Whichever
(the differences are smaller than the picking-time)
3. Need across-machine?
• Move sessions cleanly between Macs/cloud → Claude Remote
• Send tasks from phone to home Mac → Dispatch
• Run on a remote with full context → SSH + your CLI on remoteProductive setups in 2026:
A) Solo dev, free-tier-first
Gemini CLI (free tier) for daily code
Cowork for research / docs
ChatGPT for quick questions
B) Pro subscriber, Anthropic-heavy
Claude Code for daily code
Cowork for research / docs
Dispatch for mobile-trigger tasks
Claude Remote for cross-machine
C) Multi-tool team
AGENTS.md as canonical project memory
MCP servers for org capabilities
Skills repo with cross-CLI Skills
Each dev picks their preferred CLI아직 댓글이 없어요. 첫 댓글을 남겨보세요.