Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › A Dataset of Agentic AI Coding Tool Configurations

Publication

A Dataset of Agentic AI Coding Tool Configurations

Galster, Matthias; Mohsenimofidi, Seyedmoein; Böhme, Levi; u. a. (2026): A Dataset of Agentic AI Coding Tool Configurations, in: Tse-Hsun (Peter) Chen, Chao Peng, Baishakhi Ray, u. a. (Hrsg.), Proceedings of the 3rd ACM International Conference on AI-Powered Software, New York: ACM, S. 314–322, doi: 10.1145/3805760.3814922.

Details

Faculty/Chair
Faculty/Professorship
Author
Galster, Matthias
Mohsenimofidi, Seyedmoein
Böhme, Levi
Lulla, Jai Lal
Treude, Christoph
Baltes, Sebastian
Title of the compilation
Proceedings of the 3rd ACM International Conference on AI-Powered Software
Editors
Chen, Tse-Hsun (Peter)
Peng, Chao
Ray, Baishakhi
Conference
AIware '26: 3rd ACM International Conference on AI-Powered Software, July 6 - 7, 2026, Montreal, Canada
Publisher Information
ACM : New York
Year of publication
2026
ISBN
979-8-4007-2601-9
Language
English
DOI
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
Type
Conferenceobject
URI
Activation date
2026-08-03
Project(s)

Permalink: https://fis.uni-bamberg.de/handle/uniba/116534 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.