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:
var nextLargerNodes = function (head) {
Раскрыты подробности похищения ребенка в Смоленске09:27。同城约会对此有专业解读
"tags": [t for t in tags if t],，推荐阅读Line官方版本下载获取更多信息
This eventually led to the function being removed for users.
Here’s a few examples of what a user sees when they delete a passkey:。关于这个话题，Line官方版本下载提供了深入分析