Matthias Galster

Jai Lal Lulla, Matthias Galster, Jie M. Zhang et al.

Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from scratch. These decisions, whether to build functionality from scratch or buy into an external library, hereafter build-versus-buy, carry direct consequences for software security, licensing compliance, performance, and long-term maintainability. Yet no controlled experimental study has examined what governs build-versus-buy decisions in agentic AI coding tools. Configuration mechanisms, i.e., the means by which developers tailor agentic AI coding tool behavior to a project or workflow, are one of the primary means by which practitioners can influence these decisions. However, it is unclear which configuration mechanisms influence build-versus-buy decisions most effectively. We present a pre-registered protocol to study how configuration mechanisms alter build-versus-buy behavior in two popular agentic AI coding tools: Claude Code and OpenAI Codex. We will execute controlled programming tasks drawn from a benchmark of staged projects, each constructed around identifiable build-versus-buy points, and will manipulate the configuration supplied to each tool, ranging from no configuration, through context files with soft preferences and explicit prohibitions, to Skills (instructions that can be autonomously discovered), MCP-enabled library discovery tools, and permission controls, measuring which libraries the tool selects, whether it discloses newly introduced libraries, and whether those disclosures are complete and accurate. Nine pre-registered hypotheses structure the protocol. The resulting benchmark dataset and analysis pipeline will be released as a reusable artifact for evaluating build-versus-buy behavior in agentic AI coding tools.

Matthias Galster, Seyedmoein Mohsenimofidi, Levi Böhme et al.

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.

Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla et al.

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 a spectrum from static context to executable and external integrations, and, in an empirical study of 2,923 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, advanced mechanisms such as Skills and Subagents are only shallowly adopted. Most repositories define only one or two artifacts, and Skills predominantly rely on static instructions rather than executable workflows. Third, distinct configuration cultures 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.

Jai Lal Lulla, Seyedmoein Mohsenimofidi, Matthias Galster et al.

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.

Mohamed Soliman, Matthias Galster, Paris Avgeriou

Software developers use issue trackers (e.g. Jira) to manage defects, bugs, tasks, change requests, etc. In this paper we explore (a) how architectural knowledge concepts (e.g. architectural component behavior, contextual constraints) are textually represented in issues (e.g. as adjectives), (b) which architectural knowledge concepts commonly occur in issues, and (c) which architectural knowledge concepts appear together. We analyzed issues in the Jira issue trackers of three large Apache projects. To identify ``architecturally relevant'' issues, we linked issues to architecturally relevant source code changes in the studied systems. We then developed a code book by manually labeling a subset of issues. After reaching conceptual saturation, we coded remaining issues. Our findings support empirically-grounded search tools to identify architectural knowledge concepts in issues for future reuse.