Minify source code before feeding it to a coding agent to cut input tokens ~42%

Reducing Token Usage of State-in-Context Agents using Minification (arXiv 2606.01326)·medium signal

A June 2026 paper shows source code is the dominant token sink for state-in-context SWE agents, and applying code minification (stripping non-essential lexical elements while preserving semantics) cuts average input tokens by 42% for only a 12-point drop in SWE-bench Verified resolution rate. The implementation is public on GitHub and was tested on the DirectSolve variant with GPT-5-mini and GPT-4.1. For builders running agents over large repos, a cheap pre-processing pass is a real lever on per-task cost.