Blog

Field notes on agent security

Practical, tested guides to running AI coding agents on your own machine without handing them your secrets. Most of it works with nothing but the agents' own settings.

  1. Is it safe to run AI coding agents with --dangerously-skip-permissions?

    An honest look at what skip-permission modes in Claude Code, Codex and Gemini CLI actually turn off, what tends to go wrong, and how to use them with much less at stake.

  2. Claude Code hooks explained: block dangerous commands before they run

    What hooks are, which events matter for safety, how matchers and exit codes work, and a tested script that stops rm -rf on your home folder, curl-pipe-to-shell and force pushes.

  3. How to stop Claude Code from reading your .env file

    Deny rules stop Claude Code's file tools, but not a plain cat in the shell. Here is a setup that covers both, with a tested hook script you can copy.