I Scanned My AI Agent Skills and Found 140 Vulnerabilities
You install a skill for your AI coding agent. It does what it says. You move on. But what else did it do? What did it r…
#claude code
9 posts
Superpowers Isn't the Only Framework: A New AI Coder's Guide to Skills and Plugins
As of posting time, obra/superpowers sits at 276k star count on GitHub. That number alone is enough to make it the firs…
Why Use Many Token When Few Token Do Trick — Meet opencode-caveman
Smarter, cheaper, faster AI responses with caveman token compression. The Problem: Your AI Talks Too Much Every time yo…
OpenCode One Month Later: My Honest Sysadmin Verdict
If you caught my earlier post evaluating OpenCode against Claude Code, you know I liked what I saw on paper — privacy p…
Beyond the Model: Understanding the AI Harness
Introduction If you've been following along since the WordPress to Django migration post, you already know the drill ar…
Claude Code, One Month In: A DevOps-Minded Retrospective
Introduction If you've been following along here on Sandbox99 Chronicles, you already know the last few weeks have been…
The Secret Handbooks of AI: Why Leaked System Prompts Change Everything
Introduction I will be sharing content in this format periodically as a personal reference to revisit over time. This p…
Claude Plugins, Explained: What They Are and Why Your "Skills" Just Got an Upgrade
Introduction If you've followed our posts on structured prompting and automation, you know we like AI tools that act li…