Viewing profile — xinbenlv

I've been starting new repos over and over again, kept a list of personal skills too. But recently I have been thinking of a different approach: a "Minimal AGENTS.md" (or CLAUDE.md…

Thanks, that's helpful. Do you use gitleaks or other library to do pre-commit protection? @toomuchtodo

Hi HN friends, it's july 2026 and I am assuming many of you use fully agentic building now. Securing secrets and credentials from being committed to GitHub repo has been even more …

And if you are interested in testing it please let me know

I had a pain point with my watch, so I built something to address it. A watch should do one thing well, and today it doesn't: help me avoid missing my next meeting/event. That's it…

I’ve been using OpenClaw intensively for about two weeks. The first few days were exciting. It felt like we’re finally getting closer to autonomous agents that can actually operate…

Hi HN, I'm looking to use Claude Code to build something—specifically, a tool that generates illustrations for finished articles using its 'Skills' feature. However, as I started s…

Hi HN, I built CancelShouldBeEasy.com after a frustrating experience with a SaaS subscription. I was overcharged and found it incredibly difficult to get a cancellation and refund.…

Thanks @pjjpo, exactly. My bad to confuse people, no we don't put real prod-prod credentials in .env. We use mechanisms to ensure separation of secrets. Thank you for saying that i…

That's a good idea too, thanks for the suggestion

Good points

I am interested, that said, there are many memory and context services. What makes this one different?

I’ve recently started integrating AI coding agents into my daily workflow (specifically when using Cursor Composer, Devin, Claude Code), and I’ve noticed a strange pattern in my be…

It happened multiple times to me on Claude Code too, next time I caught it I will try to record its history and show it here

I've been using Cursor with Claude as my coding assistant. I set up explicit workspace rules stating that the agent must ask for my approval before executing any git operations (gi…

My question is not about on or off storage, is more about when you give agent access, it assume the environment agent runs is safe

What if you simply need to give them access. E.g if you want them to do code review you have to at least give them code repo read access. But you don't know if the environment wher…

is the permission device+client based or role based?

Any prompt injection attack could by pass this by simply do a base64 or any encoding, I guess?