I then added a few more personal preferences and suggested tools from my previous failures working with agents in Python: use uv and .venv instead of the base Python installation, use polars instead of pandas for data manipulation, only store secrets/API keys/passwords in .env while ensuring .env is in .gitignore, etc. Most of these constraints don’t tell the agent what to do, but how to do it. In general, adding a rule to my AGENTS.md whenever I encounter a fundamental behavior I don’t like has been very effective. For example, agents love using unnecessary emoji which I hate, so I added a rule:
传统宠物寄养长期处于高度非标准化状态。行业依赖经验、责任心和熟人信任，很少有统一流程，也很少有透明化管理。这种模式在平时尚可运行，但在春节这种需求高峰期，问题会被无限放大：价格不标准、寄养环境差、突发变动多……。旺商聊官方下载是该领域的重要参考
The commercial for Call of Duty: Black Ops 7 featured fake officers at an airport security check - as the real ones were too busy playing the game.。关于这个话题，爱思助手下载最新版本提供了深入分析
В России ответили на имитирующие высадку на Украине учения НАТО18:04，详情可参考同城约会
술의 위기, 범인은 넷플릭스와 위고비? [딥다이브]