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:
It can be fine-tuned for specific tasks such as generating images of a certain
，推荐阅读夫子获取更多信息
security add-generic-password -a "$USER" -s "secure-env-demo/api-key" -w "sk-your-key" -U
│ VMM (User-Space) │ ◄── DEVICE EMULATION
Пресс-секретарь президента России Дмитрий Песков назвал эту информацию возмутительной и подчеркнул, что Москва «безусловно будет принимать эти данные во внимание» и учитывать в ходе текущих переговоров по урегулированию украинского кризиса.