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:
Automated systems are causing real harm. “Request review” processes shouldn’t require detective work to find contact forms, forum registrations, and email addresses. A 15-day resolution time for a false positive is unacceptable for businesses that depend on web traffic.，推荐阅读搜狗输入法下载获取更多信息
，更多细节参见heLLoword翻译官方下载
Вегас Голден Найтс。safew官方版本下载对此有专业解读
Cyrillic homoglyphs: the real threat
如对本稿件有异议或投诉，请联系 [email protected]。