AI coding agents such as Codex and Claude Code are increasingly used to autonomously contribute to software repositories. However, little is known about how repository-level configuration artifacts affect operational efficiency of the agents. In this paper, we study the impact of AGENTS$.$md files on the runtime and token consumption of AI coding agents operating on GitHub pull requests. We analyze 10 repositories and 124 pull requests, executing agents under two conditions: with and without an AGENTS$.$md file. We measure wall-clock execution time and token usage during agent execution. Our results show that the presence of AGENTS$.$md is associated with a lower median runtime ($Δ28.64$%) and reduced output token consumption ($Δ16.58$%), while maintaining a comparable task completion behavior. Based on these results, we discuss immediate implications for the configuration and deployment of AI coding agents in practice, and outline a broader research agenda on the role of repository-level instructions in shaping the behavior, efficiency, and integration of AI coding agents in software development workflows.

翻译：诸如Codex和Claude Code等AI编程代理正日益广泛地应用于软件仓库的自动化贡献。然而，关于仓库级配置制品如何影响代理运行效率的研究尚不充分。本文通过分析10个代码仓库中的124个拉取请求，在存在与不存在AGENTS.md文件的两种条件下执行AI编程代理，系统研究了AGENTS.md文件对GitHub拉取请求场景中AI编程代理运行时间与令牌消耗的影响。我们测量了代理执行过程中的实际运行时间与令牌使用量。实验结果表明：AGENTS.md文件的存在与较低的中位运行时间（Δ28.64%）及减少的输出令牌消耗（Δ16.58%）显著相关，同时保持了可比的任务完成行为。基于这些发现，我们探讨了当前AI编程代理配置与部署实践的即时影响，并提出了关于仓库级指令在塑造AI编程代理行为模式、运行效率及其在软件开发工作流中集成方式等方面的更广泛研究议程。