Thanks, this is super informative! It sounds like maybe you weren't running multiple concurrent agents in the GPT-5.5 days, but now you are? Maybe you're on one of those US$200-a-month plans?
Sure. No, I was also running 2-5 agents typically at that time.
When working on trickier things that require me to test on device and report results, this would drop to only a single session. I can't context switch between multiple threads while focusing on an investigation where I need to steer the agent.
Yes, I'm using the $200 plan for Claude, and only $20 for Codex, where I use 6.1 Sol to review every change implemented by Opus 5.5.
In the past I paid for both $200 subscriptions, but with Claude's current usage limits, that is no longer needed.
When working on trickier things that require me to test on device and report results, this would drop to only a single session. I can't context switch between multiple threads while focusing on an investigation where I need to steer the agent.
Yes, I'm using the $200 plan for Claude, and only $20 for Codex, where I use 6.1 Sol to review every change implemented by Opus 5.5.
In the past I paid for both $200 subscriptions, but with Claude's current usage limits, that is no longer needed.