Codex

There comes a time in every programmer’s life, when using coding copilots, where you look at your monthly bill and think: “This is great and all, but I have more subscriptions than my local gym membership.” That moment came for me with quite a lineup: Claude Max 5, Codex Plus, and the temptation to throw in Z.AI with OpenCode for the grunt work. The idea sounded fantastic. The problem? If you throw three agents into your workflow with no ground rules, you’ll end up like a chaotic construction site boss—everyone scrambling around while no one holds the blueprints. ...

TL;DR: If you’re using Codex, use a command to control the session or application, and use a skill to teach the agent a way of working. In Claude Code, the current documentation already treats skills as something you can invoke with /skill-name, so the concepts merge more there. Not so in Codex: types might exist as a skill, but /types won’t exist by default. There’s a common confusion when switching from Claude Code to Codex. And it’s understandable. ...

TL;DR: After 165 sessions with Claude Code and 27 with Codex CLI, one thing is clear: use Claude for interactive, exploratory work and Codex for autonomous tasks you can delegate and forget about. It’s not about which is better — it’s about when to use each. My data shows the combination outperforms either one alone. It’s 9:00 a.m., coffee in hand, and I have a vague idea about restructuring a module. I don’t know exactly what I want yet — I just know the current setup isn’t right. ...

Have you ever written a technical plan at 11 PM, convinced it was flawless, only to realize the next morning you forgot authentication? Happens to me. More than once. And the worst part isn’t the oversight—it’s that when you use AI to plan things out, the plan sounds so coherent your brain stops looking for flaws. Claude generates a document with sections, dependencies, execution order, and it all checks out. Seems like a senior engineer’s masterpiece. But nobody has challenged it. ...

If you’ve read my post about worktrees in Claude Code, you know the key to parallel workflows is a simple flag: --worktree. Run it, and you get an agent working in its own isolated repo copy. Launch three, and you’ve got three agents working in parallel without clashing. Magic. Now you open Codex CLI, look for an equivalent flag… and it doesn’t exist. There’s no --worktree. No --tmux. No isolation: worktree for custom agents. Issue #12862 has been open on GitHub asking for exactly this, with community members proposing their own implementations in forks, but nothing has been merged. Native parallelism for Codex CLI doesn’t exist — not yet. ...

You install Codex CLI. You launch it with excitement and tell it to “Fix the broken tests in this repo,” and then the nightmare begins: Codex: I want to run pytest Allow? (y/n) You press y. Immediately, this pops up: Codex: I want to modify test_user.py Allow? (y/n) So, you press y. Again, and again, and again. Every file it wants to read, every command it wants to run, every line it wants to modify. Confirm, confirm, confirm. It’s like working with an intern that asks permission for everything. ...

Two weeks ago, OpenAI introduced Codex Automations. The idea: define a trigger (a cron job, a push, a new issue), write instructions in natural language, and an agent runs it solo in an isolated worktree. No human intervention. While you sleep, the agent triages issues, summarizes CI failures, generates release briefs, and even improves its own instructions. Sounds like magic, right? And it is, a little. But there’s one catch they didn’t emphasize too much in the keynote: you need the Codex App running on your desktop. macOS or Windows only. No headless servers. No running it on a mini PC and forgetting about it. ...

The first time I used Claude Code to refactor an entire module, I had an almost mystical experience. I described what I wanted, went to grab a coffee, and when I came back there was a pull request with 14 changed files, updated tests, and a decent commit message. “This is magic,” I thought. It’s not magic. It’s a while loop. Michael Bolin from OpenAI recently published an article breaking down the internal workings of Codex CLI. And it turns out the secret behind AI coding agents isn’t some revolutionary algorithm or mysterious neural network. It’s a loop that calls an LLM, executes tools, and repeats until there’s nothing left to do. ...