The sub only works in Claude Code itself (unless they changed that rule again?), and all the Chinese models are trained on Claude Code (a bunch of them don't even work in Codex).

I use a custom harness, but I constantly hear good things about Pi.

EDIT: Checked out Pi and Oh-My-Pi. 250k LoC and 1.5M LoC respectively. Sheesh. How's that for minimalism...

Mine's 50. (Lines.)

https://gist.github.com/a-n-d-a-i/bd50aaa4bdb15f9a4cc8176ee3...

Vendored in my own LLM micro library (100 LoC) so it's 150.[0]

There's no parallelism or anything, but I use it for surgical edits and it's much faster and cheaper than the official harnesses for some reason. (Absence of sysprompt bigger than my repo probably helps there...)

[0] This one uses OpenRouter so you can use it with any model, but jerry rigged Codex sub version available on demand :)

---

I also have a ultra turbo bloated version (500 lines... need to strip it down a bit!) which has autorun files (for grep-based context injection), notification (frog croak when agent done, etc.) Watch this space!