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:
Wonderfall (@w0nderfall)
，更多细节参见safew官方版本下载
第一百三十八条 公安机关及其人民警察不得将在办理治安案件过程中获得的个人信息，依法提取、采集的相关信息、样本用于与治安管理、查处犯罪无关的用途，不得出售、提供给其他单位或者个人。
因此，人们选择在制度之外经营，并不是道德堕落，而是制度排斥。他们在非正式网络中完成占地、交易与仲裁。这些规则未必高效，但至少可行。然而，这套体系无法标准化，无法跨区域使用，也无法被金融系统识别，一个在贫民窟有效的“地契”，在银行依然一文不值。