Been playing around with drag-and-drop reordering in @expo . The transitions are smooth, and the little haptic feedback as items switch places makes it feel so good✨

Played around this card drag interactions on a calendar using @expo ✨

One thing that worries me about using AI coding agents is how easy it is to accidentally share something sensitive. You could paste a terminal log, ask for help debugging, and unknowingly include an API key. That’s why I’m building Promptwall. I want to make it harder for developers to accidentally expose secrets while working with AI.

Played around with @X ’s slide-out drawer in @expo . Also added a solid/soft toggle that changes the calendar cards on the fly. Love how it turned out.

Ever pasted a log into an AI coding agent without realizing it contained a live API key? That’s what I’m building Promptwall to prevent. It catches secrets in prompts, logs, and commands before they reach your agent.

CSM manages your AI coding sessions. Promptwall catches secrets in prompts, logs, and commands before they reach your agents. I’m exploring how both can work together to make agentic coding safer. Here’s a quick look.

A quick look at Promptwall. Paste a prompt containing a secret, and Promptwall catches it before it reaches your AI agent. Here’s a short demo.

Been working on making CSM a better place to manage all your coding agents and accounts, without the constant logging in and out.🚀 usecsm.xyz ✨

I'm building Promptwall, a local guard for agentic coding that catches API keys and sensitive data in your prompts to Claude Code, Codex and other AI agents, then blocks or redacts them.