I Audited My Claude Code Config and Found 32% Was Wasted
I ran a new skill called Claudit on my Claude Code configuration and discovered that roughly 32% of my CLAUDE.md was doing nothing. Duplicate instructions, stale references to skills that no longer exist, and a contradiction in my error handling guidance that I never caught. Most of us set up our config once and keep adding to it over time without ever cleaning house. This video walks through what Claudit does, how its four-phase audit works, and the specific issues it caught in my real setup.
Want hands-on help with Claude Code?
I offer 1:1 coaching sessions where we work through your actual setup, workflow, and codebase.
Learn about coaching
Claude Code Agent View: One Screen for Every Background Session
Anthropic's new way to dispatch and manage many Claude Code sessions from one screen — what each row tells you and the shortcuts I use day-to-day.
I Hit My Claude Code Limit and Tried Codex
After two weeks running Codex CLI as my daily driver, I didn't switch from Claude Code — I split. Here's how to share your setup across both tools.
Karpathy's LLM Knowledge Base, Wired Into a Real Agent
How to build Karpathy's LLM knowledge base into a production AI agent using Claude Code plan mode, an Obsidian vault, and a local LLM.
Automate Everything With Claude Code Channels and Webhooks
Claude Code Channels let you connect your coding sessions to Telegram, Discord, webhooks, or any custom UI — here's how they work.
Get new videos and posts by email
Weekly videos on AI engineering, plus deeper dives in the newsletter.
Occasional emails, no fluff.