Coding agent where a 0.8B decision model works alongside Qwen 3.8-27B: Jeff takes the routine steps itself and decides when Qwen should think. 47% faster (32% less time) per task at the same pass rate. A fork of Pi.
1 file for Codex and OpenCode: jeff-code AGENTS.md — 1,972 tokens loaded in every session.
AGENTS.md A 1,972 tok These files are firelex/jeff-code's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.