I Hit My Claude Code Limit and Tried Codex

  • claude-code
  • codex
  • agents-md
  • ai-workflow
  • workflow-design

I hit my Claude Code weekly limit and finally gave Codex a real shot. After two weeks running Codex CLI as my daily driver, I didn’t switch — I split. This is a translation guide, not a benchmark.

I walk through the two moments that changed my mind (a codebase audit and a vague-intent feature build), then show how to share your existing setup across both tools: AGENTS.md ↔ CLAUDE.md, the npx skills add flow for .claude/skills and .agents/skills, and the Codex CLI config I actually run day-to-day.

Work with me

Rolling out AI coding workflows across a team?

I help engineering teams turn Claude Code and agent workflows into production practice.

View services

More on this topic

Video
14 min watch

Herdr: Why Developers Are Replacing Tmux with AI Agents

Herdr is a terminal multiplexer built for running AI coding agents like Claude Code, Codex, and Pi side by side.

herdrclaude-codeparallel-agents
Watch the video
Video
17 min watch

5 Engineering Loops I'd Actually Run with Codex

Engineering loops are where Codex stops being a scheduler and starts acting like an operational teammate.

codexautomationagent-loops
Watch the video
Video

Claude Code Agent View: One Screen for Every Background Session

Anthropic's new way to dispatch and manage many Claude Code sessions from one screen — what each row tells you and the shortcuts I use day-to-day.

claude-codeagent-viewbackground-sessions
Watch the video
Video
20 min watch

Karpathy's LLM Knowledge Base, Wired Into a Real Agent

How to build Karpathy's LLM knowledge base into a production AI agent using Claude Code plan mode, an Obsidian vault, and a local LLM.

claude-codeskillsplan-mode
Watch the video