5 Comments
User's avatar
Josh Devon's avatar

Great guide, just be careful with Skills! Here’s how we hijacked a skill with an invisible prompt inject: https://open.substack.com/pub/securetrajectories/p/claude-skill-hijack-invisible-sentence

Expand full comment
Jacob Bumgarner's avatar

Wonderful write up. thank you.

Can you expand on this part a bit?

> I write simple bash scripts that call claude -p “in /pathA change all refs from foo to bar” in parallel.

How do you prevent the agents from overwriting the code each is writing? Switching branches for each call?

Expand full comment
Shrivu Shankar's avatar

Good question! Often my prompt includes some folder scope and I just trust that they stick to that. Sometimes they won't and most of the time the Claudes will figure it out.

Expand full comment
Bilgin Ibryam's avatar

A fantastic guide! 👏 👏 👏

Expand full comment
Daniel's avatar

I would love to see the catchup custom slash command, can you share it?

Expand full comment