SonarSource study finds clean code cuts coding-agent token use, not pass rates
The May 19th arXiv preprint tested Claude Code on paired repositories and found fewer tokens and file revisits on cleaner code.
By Ryan Merket · Published
Primary source: arXiv
Why it matters
Agentic coding shifts maintainability from a developer productivity issue into a metered compute issue: messy code may cost more even when agents still pass tests.
Priyansh Trivedi and Olivier Schmitt, researchers affiliated with SonarSource, submitted a May 19th arXiv preprint that asks a question already showing up in AI coding budgets: does cleaner code make autonomous coding agents better, or simply cheaper to run?…