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:
"queryParameters": {},
bingbangboom-lab，这一点在夫子中也有详细论述
Цены на нефть взлетели до максимума за полгода17:55。同城约会对此有专业解读
为了获得最佳的响应速度和稳定性，特别是在国内网络环境下，我们需要对 Claude Code 进行本地化配置，并接入国内高性能的大模型 API（如智谱 AI 的 GLM-4）。。WPS官方版本下载对此有专业解读
Warner Bros. mergers never work, but they’re trying again anyway