I am officially canceling google one, Claude and sticking with GPT codex 5.3. It has not gone into endless error loops like Gemini and is great at design. Yes its a little slower than Claude and cost a little more in credits, but the trade offs in that regard are worth it. 9/10 accuracy, and speed are worth it. ADD IT TO ANTIGRAVITY AND TRY IT FOR YOURSELF. You will not look to the right side of your IDE ever again.

Big Dawg Corbin, I just binged your content over the last 3 days. Implemented stuff into my Base44 app. Holy shit man. You single handedly made my app a banger. The stripe pricing, the help center, the debug logic, the changelog -> updates, just turned something good into great. Deeply appreciate you brother. You’re the man. Keep making content, you are making a difference

Okay, now that we have all these tools inside Claude Code, has anybody figured out what would be the best practice? I'm talking about custom slash commands, the agents and also the new skill feature. And how to reduce the Claude.md overhead and also optimize the token windows. I'm thinking about having a lean Claude.md file for acting like an orchestrator and then calling multiple sub-agents, and each sub-agent would have its own skill. So we will have a very long running main task and saving its context window, while delegating all the subtasks to the agents with their specialization.