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:
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。
，详情可参考服务器推荐
Numbers and symbols are on the layer above my base layer. Navigation keys, like arrow keys and mouse keys, are on the next layer up. I've made the arrow keys more powerful with tap dance. Tap for left arrow, hold for Ctrl + Left to go back a whole word, tap and hold for Home to go to the beginning of the line, for example.
GPs already set aside a chunk of their daily appointments to try to ensure patients who need an immediate appointment can get one.