Agents

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. ...

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. ...

A few weeks ago, I wrote about git worktrees — what they are, how to create them, and why they’re better than cloning a repo three times. The basics. But the basics are only half the story. Because Claude Code doesn’t just work with worktrees — it has native support for them. Dedicated flags, automatic isolation, integration with tmux. And the difference between knowing worktrees exist and knowing how Claude Code uses them is like the difference between having a car and knowing it has sport mode. ...

I published six articles this week. One about PostgreSQL. Another about AI agents. Another on context management. A tutorial on automation. An analysis of debugging. And an adversarial advice framework for evaluating MVPs. It wasn’t planned. Each article came from a paper, a talk, or a project that I found interesting individually. But looking at them together, there’s a common thread I hadn’t noticed while writing them. All six are saying the same thing. ...

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. ...

Imagine you hire a brilliant consultant. They have two PhDs, speak seven languages, and solve problems you didn’t even know you had. You sit them in a room and say: “I need you to refactor the authentication in the project.” The consultant looks at you, nods, and asks: “What project?” You haven’t given them access to the code. You haven’t explained the architecture. They don’t know if you use JWT tokens or session cookies. They don’t know what language you’re using, how many microservices you have, or why the last migration attempt ended in disaster. ...

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. ...

A space lobster on your computer Picture this: an Austrian developer creates a personal AI assistant, names it after a space lobster, and decides to open-source it. Within 24 hours it has 9,000 GitHub stars. Within 48 hours, 17,000. It also has 300+ open issues, several critical security vulnerabilities, and someone created an unofficial cryptocurrency with its name. Welcome to Clawdbot. What exactly is this thing? Clawdbot is an open-source AI assistant that runs locally on your machine. The difference from other assistants: it doesn’t just answer questions, it does things. ...