engineering @ ShopBack; creator of ai-devkit.com
When building AI DevKit (https://github.com/codeaholicguy/ai-devkit), I had to look much deeper into different coding agent harnesses. Each one has its own structure, workflow, and mental model. In this post, I’ll share
I spend most of my time in the AI DevKit agent console. I start one agent as the manager, usually Codex, and brainstorm with it. Once an idea becomes concrete enough to execute, I ask the manager to
A common question that I still see flying around is that: will skills replace MCP? I understand why people ask. Both can extend what an AI agent can do. A skill can include scripts that call APIs,
I have been running multiple coding agents at the same time for a while now. Sometimes I have Claude Code working on one feature, Codex reviewing a plan, Gemini CLI exploring another direction, and
I used to think the hard part was getting people to use AI. Now I think that is only the first step. AI is becoming part of how we write, build, research, design, analyze, and operate. That is a good
AI makes it easy to produce output. You can generate code, designs, marketing ideas, user flows, or even a prototype in a few minutes. It looks impressive on the surface. It also creates a trap.
