Meet TokenEconomizer: Microsoft’s Plugin That Cuts Coding Agent Costs by Up to 30.9%

Researchers from Microsoft Research and UC Berkeley released TokenEconomizer, an open-source Apache 2.0 plugin that learns per-repository policies from past sessions to reduce waste in coding agents such as Claude Code, Codex, GitHub Copilot CLI and Pi, without touching model weights or agent code. On 277 SWE-Bench tasks it lowered mean cost by 18.4% to 30.9% across five agent-model settings and was cheaper in all 30 repository-setting cells, with Pass@1 improving in four of five settings and dropping 1.0 point on Opus 4.8. It combines micro-skills, tool pruning and failure-loop intervention, and installs with Python 3.10+ while keeping learned data local in ~/.tokeneconomizer.