HN Explorer

Ask HN: How do you handle hitting AI coding agent usage limits?

1 points by VoidWhisperer ↗ HN
One topic I've been researching lately is the best way to handle switching to another agent when I hit a usage limit on one of them. For example, if I hit the usage limit on Codex, I would want to switch to Claude Code and vice versa.

The important part is not losing the ongoing context/task(s) when switching between the tools.. I have found a few things that say they do this but none seem to have much traction.

As a result, I was hoping to pick the brain of HN'ers to see how you all handle this

(To head off comments regarding 'pay for a better plan for more usage' - I can't currently really afford the jump from $20 a month per agent to $100-200/m per agent)

8 comments

[ 2.9 ms ] story [ 35.2 ms ] thread
sujithappikatla
have you tried caveman plugin?
VoidWhisperer
I have not. Seems like that would help too, although im still hoping to get ideas on the agent-to-agent handoff part
damli40
wow, literally working on exactly the agent-to-agent handoff part, so read this with that bias (open source, I'm the author).

Hooks in Claude Code and Codex save a short handoff as the agent works: objective, progress, decisions, rejected approaches, next step.

When you hit the limit you open the other agent, type "Continue.", and it starts from that.

I've run it Claude Code to Codex and back.

Current limits: it is early, you would be one of the first testers, and the summary step calls a model API(you can host your own or use ours!).

Happy to set it up with you if you want to try it.