This is a short post (two in one day!) to talk about a new tool I’ve written to help with Claude Code permissions. Note see also my standard AI Disclaimer The problem with permissions In my previous post I mentioned a frustrating issue with Claude Code - it kept asking me to approve the same commands over and over again. The documentation says you can use wildcards in permissions but in practice, even simple patterns don’t work reliably. I’d give it permissions like Bash(rm /tmp/mermaid...
