Fancy harnesses make coding agents more expensive but not better, study finds
AI 摘要
Color illustration of a spacesuit with a retro computer, cables, and a token power meter in the background. A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup. Cost per task, however, can triple, driven mainly by the system prompt that gets resent with every step. The article Fancy harnesses make coding agents more expensive but not better, study finds appeared first on The Decoder .