Energy smell detector and repairer saves Python code energy costs
Identifying and Repairing Energy Smells with Agent Skills
Software Engineering
Summary
Energy smells are parts of computer programs that waste power because they're not written efficiently. The authors created DR. GREENS, a tool that helps programmers find and fix these wasteful parts inside their coding software. It uses a detailed list of common energy problems and checks that fixes don't change how the program works while actually saving energy. Tests showed that most fixes made by DR. GREENS reduced energy use by about a quarter, helping developers make greener and more efficient programs.
What this means in practice
- •For software developers: Identify and fix inefficient energy usage in Python code early in the development process to reduce operational costs.
- •For cloud infrastructure teams: Detect energy hotspots in deployed Python services and apply automated repairs to lower energy consumption without changing functionality.
Authors
Mohammadjavad Mehditabar, Saurabhsingh Rajput, Tushar Sharma
Abstract
Energy smells are inefficient implementations that waste energy. Once code reaches production, these smells become costlier and riskier to fix, so energy efficiency checks should shift left, i.e., move earlier in the development lifecycle, to where code is written. Existing energy smell tools rely on fixed static rules and do not measure energy savings, whereas LLM-based optimizers mostly target execution time and rarely ground their changes in concrete smell definitions. To address both limitations, we present DR. GREENS, an agent skill that detects and repairs energy smells in Python code within the developer's coding environment. The skill grounds the coding agent in our taxonomy of 12 energy smells and 65 root causes, augmented with repair guidance drawn from 230 measured cases. The skill also encapsulates a static analyzer and an independent verifier to confirm behavior preservation and energy saving for each attempted repair. We evaluated DR. GREENS in 18 sessions on three open-source repositories, with two models and three skill configurations. Of the 258 measured repairs, 68.6% saved energy, with a median saving of 24.9%. Compared with a baseline skill that lacks the taxonomy, the full skill found more energy smells with verified savings in all three repositories with both models. DR. GREENS helps developers detect energy hotspots and fix them reliably without altering program behavior, which makes energy-efficient development more feasible.