Anthropic announced today that starting June 15, paid Claude plans get a separate monthly credit pool for programmatic usage (claude -p, Agent SDK). Seems OK at first glance but it turns out the monthly credit pool is charged at API rates, which effectively kills any serious programmatic usage for hobbyists.
This is a small Claude Code wrapper which runs claude in a PTY, injecting input, finding the session transcript jsonl file, and using a stop hook to determine when claude is done.
It's a drop-in replacement for claude code. All arguments except the "-p" argument are forwarded as-is.
claude-pee -p "hello world"
Could be used as a cheap way of using Anthropic subscriptions for OpenClaw, Hermes, etc.
Written in Rust, MIT license.
Can you still stream the outputs back using this?
I’m about to give up building projects on top of the frameworks these companies provide, I thought I was doing everything right with using the Claude Agent SDK, and that this was how they wanted people to use their product.
Not sure how to proceed, because this tool feels exactly the kind of thing about “working around the rules” that I was trying to avoid.
You definitely can! I started implementing the stream-json output mode; take a look at that. All it does is effectively "tail" the jsonl transcript to stdout