Coding agents are increasingly used to automate software engineering tasks. To guide their behavior, these agents commonly rely on configuration files, typically named AGENTS.md or CLAUDE.md, which provide instructions about architecture, workflows, coding conventions, and testing practices. Despite their growing importance, little is known about common problems affecting the definition and maintenance of these files. In this paper, we present the first catalog of smells for coding-agent configuration files. To identify such smells, we first conducted a grey literature review and a repository mining analysis. As a result, we identified six configuration smells and proposed automated heuristics to detect them. To evaluate the prevalence of the proposed smells, we analyzed 100 popular open-source repositories containing either an AGENTS.md or a CLAUDE.md file. Our results show that configuration smells are widespread. Lint Leakage was the most common smell, affecting 62% of the files, followed by Context Bloat (42%) and Skill Leakage (35%). We further show that several smells frequently co-occur, particularly Context Bloat, Skill Leakage, and Conflicting Instructions.

翻译：编码智能体正被越来越多地用于自动化软件工程任务。为引导其行为，这些智能体通常依赖配置文件（通常命名为 AGENTS.md 或 CLAUDE.md），其中提供关于架构、工作流程、编码规范及测试实践等指令。尽管其重要性日益凸显，但关于这些文件定义与维护中的常见问题仍知之甚少。本文首次提出了编码智能体配置文件的坏味目录体系。为识别此类坏味，我们首先进行了灰色文献综述和仓库挖掘分析。由此，我们识别出六种配置坏味，并提出了自动检测启发式方法。为评估所提坏味的普遍程度，我们分析了包含 AGENTS.md 或 CLAUDE.md 文件的100个流行开源仓库。结果表明，配置坏味广泛存在。Lint Leakage（检查泄漏）是最常见的坏味，影响62%的文件；其次是Context Bloat（上下文膨胀，占42%）和Skill Leakage（能力泄漏，占35%）。我们进一步发现，多种坏味频繁共现，尤其是Context Bloat（上下文膨胀）、Skill Leakage（能力泄漏）与Conflicting Instructions（指令冲突）。