How Do Developers Maintain and Evolve Their Agents' Instructions? An Empirical Study
For developers using AI coding agents, this paper provides the first empirical understanding of how to manage agent instructions, though it is an incremental contribution as it applies existing maintenance theory to a new artifact.
This study investigates how developers maintain and evolve Agent Context Files (ACFs) used to guide autonomous coding agents, finding that ACF changes are associated with code quality outcomes and exhibit distinct temporal patterns.
Context. Autonomous coding agents are increasingly used in software development, shifting parts of the engineering process to AI assistance. While this automation brings clear benefits, it introduces challenges in governance, traceability, and control over agent behavior. Agent Context Files (ACFs) have emerged as a practical mechanism to guide agents through structured instructions, yet little is known about how these artifacts are maintained and how their evolution relates to code development. Objective. This paper plans to investigate the evolution of ACFs and their role in agent-driven development. Specifically, we (1) classify ACF changes through a taxonomy grounded in software maintenance theory, (2) analyze how different types of changes are associated with code quality outcomes, and (3) examine their temporal patterns across the development lifecycle. Method. We conduct a large-scale mining study combining repositories with ACFs and agent-generated commits. We reconstruct ACF evolution at the commit level, classify changes using a qualitative approach, and analyze their association with code quality metrics. Statistical analyses and hypotheses are used to evaluate differences across maintenance categories, to inform future design of ACFs for governing autonomous coding agents.