@inproceedings{galster2026_116537,
  title = {Configuring Agentic AI Coding Tools : An Exploratory Study},
  author = {Galster, Matthias and Mohsenimofidi, Seyedmoein and Lulla, Jai Lal and Abubakar, Muhammad Auwal and Treude, Christoph and Baltes, Sebastian},
  year = {2026},
  pages = {11-20},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-116537x},
  url = {https://fis.uni-bamberg.de/handle/uniba/116537},
  language = {eng},
  abstract = {Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration mechanisms for agentic AI coding tools, covering Claude Code, GitHub Copilot, Cursor, Gemini, and Codex. We identify eight configuration mechanisms spanning from static context to executable and external integrations and, in an empirical study of 2,853 GitHub repositories, examine whether and how they are adopted, with a detailed analysis of Context Files, Skills, and Subagents. First, Context Files dominate the configuration landscape and are often the sole mechanism in a repository, with AGENTS.md emerging as an interoperable standard across tools. Second, few repositories adopt advanced mechanisms such as Skills and Subagents. Skills predominantly rely on static instructions rather than executable scripts. Third, distinct configuration practices are forming around different tools, with Claude Code users employing the broadest range of mechanisms. These findings establish an empirical baseline for understanding how developers configure agentic tools, suggest that AGENTS.md serves as a natural starting point, and motivate longitudinal and experimental research on how configuration strategies evolve and affect agent performance.},
  keywords = {Software Engineering, Generative AI, AI Agents, Configuration}
}

@inproceedings{galster2026_116536,
  title = {Configuring Agentic AI Coding Tools : An Exploratory Study},
  author = {Galster, Matthias and Mohsenimofidi, Seyedmoein and Lulla, Jai Lal and Abubakar, Muhammad Auwal and Treude, Christoph and Baltes, Sebastian},
  year = {2026},
  booktitle = {Proceedings of the 3rd ACM International Conference on AI-Powered Software},
  pages = {11-20},
  publisher = {ACM},
  address = {New York},
  isbn = {979-8-4007-2601-9},
  doi = {10.1145/3805760.3814887},
  url = {https://fis.uni-bamberg.de/handle/uniba/116536},
  language = {eng},
  abstract = {Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration mechanisms for agentic AI coding tools, covering Claude Code, GitHub Copilot, Cursor, Gemini, and Codex. We identify eight configuration mechanisms spanning from static context to executable and external integrations and, in an empirical study of 2,853 GitHub repositories, examine whether and how they are adopted, with a detailed analysis of Context Files, Skills, and Subagents. First, Context Files dominate the configuration landscape and are often the sole mechanism in a repository, with AGENTS.md emerging as an interoperable standard across tools. Second, few repositories adopt advanced mechanisms such as Skills and Subagents. Skills predominantly rely on static instructions rather than executable scripts. Third, distinct configuration practices are forming around different tools, with Claude Code users employing the broadest range of mechanisms. These findings establish an empirical baseline for understanding how developers configure agentic tools, suggest that AGENTS.md serves as a natural starting point, and motivate longitudinal and experimental research on how configuration strategies evolve and affect agent performance.},
  keywords = {Software Engineering, Generative AI, AI Agents, Configuration}
}

@inproceedings{galster2026_116535,
  title = {A Dataset of Agentic AI Coding Tool Configurations},
  author = {Galster, Matthias and Mohsenimofidi, Seyedmoein and Böhme, Levi and Lulla, Jai Lal and Abubakar, Muhammad Auwal and Treude, Christoph and Baltes, Sebastian},
  year = {2026},
  pages = {314-322},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-116535x},
  url = {https://fis.uni-bamberg.de/handle/uniba/116535},
  language = {eng},
  abstract = {Agentic AI coding tools such as Claude Code and OpenAI Codex execute multi-step coding tasks with limited human oversight. To steer these tools, developers create repository-level configuration artifacts (e.g., Markdown files) for configuration mechanisms such as Context Files, Skills, Rules, and Hooks. There is no curated dataset yet that captures these configurations at scale. This dataset, collected from open-source GitHub repositories, fills that gap. We selected 40,585 actively maintained repositories through metadata filtering, classified them using GPT-5.2 to identify 36,710 as belonging to engineered software projects, and systematically detected configuration artifacts in these repositories. The dataset covers 4,738 repositories across five tools (Claude Code, GitHub Copilot, OpenAI Codex, Cursor, Gemini) and eight configuration mechanisms. We collected 15,591 configuration artifacts, the full content of 18,167 configuration files associated with these configuration artifacts, and 148,519 AI-co-authored commits. The dataset and the construction pipeline are publicly available on Zenodo under CC BY 4.0. An interactive website allows researchers to browse and explore the data. This data supports research on context engineering, AI tool adoption patterns, and human-AI collaboration.},
  keywords = {Software Engineering, Generative AI, AI Agents, Configuration}
}

@inproceedings{galster2026_116534,
  title = {A Dataset of Agentic AI Coding Tool Configurations},
  author = {Galster, Matthias and Mohsenimofidi, Seyedmoein and Böhme, Levi and Lulla, Jai Lal and Abubakar, Muhammad Auwal and Treude, Christoph and Baltes, Sebastian},
  year = {2026},
  booktitle = {Proceedings of the 3rd ACM International Conference on AI-Powered Software},
  pages = {314-322},
  publisher = {ACM},
  address = {New York},
  isbn = {979-8-4007-2601-9},
  doi = {10.1145/3805760.3814922},
  url = {https://fis.uni-bamberg.de/handle/uniba/116534},
  language = {eng},
  abstract = {Agentic AI coding tools such as Claude Code and OpenAI Codex execute multi-step coding tasks with limited human oversight. To steer these tools, developers create repository-level configuration artifacts (e.g., Markdown files) for configuration mechanisms such as Context Files, Skills, Rules, and Hooks. There is no curated dataset yet that captures these configurations at scale. This dataset, collected from open-source GitHub repositories, fills that gap. We selected 40,585 actively maintained repositories through metadata filtering, classified them using GPT-5.2 to identify 36,710 as belonging to engineered software projects, and systematically detected configuration artifacts in these repositories. The dataset covers 4,738 repositories across five tools (Claude Code, GitHub Copilot, OpenAI Codex, Cursor, Gemini) and eight configuration mechanisms. We collected 15,591 configuration artifacts, the full content of 18,167 configuration files associated with these configuration artifacts, and 148,519 AI-co-authored commits. The dataset and the construction pipeline are publicly available on Zenodo under CC BY 4.0. An interactive website allows researchers to browse and explore the data. This data supports research on context engineering, AI tool adoption patterns, and human-AI collaboration.},
  keywords = {Software Engineering, Generative AI, AI Agents, Configuration}
}

