Seedling·March 1, 2026·1 min read

Better Safe Than Sorry: Locking Down Your Agentic Lobster

Security patterns for AI agents — sandboxing, permission models, and making sure your agent doesn't go rogue.

Kevin De Asis

aisecurityagents

Still thinking through this one... The ideas here might look different tomorrow.

Introduction

Coming soon.

Build Your Own GREMLIN IN THE SHELL

A hands-on guide to building your own shell-based AI agent that haunts your terminal and gets things done.

Stitching the Monster: How I Made My Own Codex

A deep dive into building a Codex-like coding agent from scratch — the architecture, the mistakes, and the lessons learned.

Make Your Own Claude Code

How to build your own CLI coding assistant inspired by Claude Code — from terminal UI to tool use to agentic loops.