Setup
- Claude Code
- Anthropic Teams plan
- Claude Pro Max 200 plan (personal)
- Codex CLI + Deep Research
- OpenAI Enterprise (work)
- ChatGPT Pro subscription (personal)
- OpenAI Enterprise (work)
- Visual Studio Code
Claude Code + Codex CLI
I still mostly work in Claude Code. With the release of Sonnet 4.5, Anthropic removed the opusplan model from Claude Code, claiming that Sonnet 4.5 is a superior model to Opus 4.1. Unfortunately, I haven’t found this to be the case.
I ended up so frustrated with Sonnet 4.5 that I installed Codex CLI and gave it a spin. The UX isn’t as good as Claude Code, but the GPT-5 Codex model more than makes up for that. For very small tasks, I’ll generally let the model plan and make changes, but for larger tasks I’ll ask it for a plan, then copy and paste it over to Claude Code for Sonnet 4.5 to execute.
I’ll still sometimes switch the model to Opus 4.1 manually, but that has been relatively rare since the workflow is much more tedious without the opusplan model. When planning, I have to instruct it to add “stop so I can switch models” as the first step of the plan. I’ve also had to restart the planning process from scratch when I’ve run out of Opus subscription credits.
With this iteration, I’ve ended up with one codex and one claude tab per my three project lanes. Codex does planning, debugging, and reviewing. Claude Code is purely for code (and nonsense) generation.
Deep Research + Agent mode
The new Agent mode is a bit frustrating; it feels like a sidegrade from the older Deep Research project due to the trade offs.
If I need up-to-date information or better reasoning, I’ll use Agent mode. The new model is superior and desktop access means web search is visual. It’s also convenient that I don’t need long, detailed prompts. The major downside is the quality of the generated reports. While I have gotten decent reports, the structure and length are worse even if I use my older Deep Research prompt.
If I want “proper” reports, I fall back to the other product and accept that the actual research and reasoning capabilities are lower. I’d like to see an updated version of Deep Research with a GPT 5.x model.
Visual Studio Code
Given how little value I’ve gotten from Cursor, I’ve actually switched back to Visual Studio Code as my editor. It’s nice to be able to hit tab without wincing.