Measuring the Post-Merge Fate of Agentic Code

A first longitudinal empirical study of 182 public GitHub repositories tracking 30K+ agentic commits and 121M+ lifecycle lines from May 2025 to May 2026 found that agentic code has 46% higher corrective maintenance rates and 1.51 times more high-severity static security findings than human contributions, and that increasing agentic code share raises the corrective maintenance burden within projects.

Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code First longitudinal empirical study of the post-merge lifecycle of agentic and human code in real-world open source projects. 182 public GitHub repositories 30K+ agentic commits 121M+ lifecycle lines tracked 12 maintenance operational intents 143K+ security & dependency findings 1 year May 2025 to May 2026 Finding Highlights: 46% higher corrective maintenance rates than human contributions 1.51x times more high-severity static security findings than human contributions Agentic code share increases the corrective maintenance burden within projects No review rate increases the agentic maintenance burden of a project Interested to learn more? Check out the interactive visualization to play with the data yourself