Claude Code: from zero to professional. Tips, tutorials and deep dive guides from an engineer who uses it 12 hours a day.
Explore the hub →Claude Code first steps: the fundamentals that don't expire
The Claude Code fundamentals that don't expire: install, sessions, context, quota, models, permissions. What you actually need to grasp on day 1.
AI: the joy of missing out on what doesn't matter
You can't keep up with AI, and you shouldn't try. The answer isn't resistance or passive acceptance: go all in, but deep on one thing instead of scattered.
Claude Code Agent View: managing parallel agents without leaving the terminal
I spent months managing many Claude Code agents by hand. Agent View now does it: my terminal-native workflow with Warp and Neovim, and the gaps I patch.
Claude Code auto mode now protects you from yourself
You already trust auto mode to stop a `git push` to main. Over the last few weeks it learned to block three subtler, nastier things, and one is the `rm -rf` that quietly becomes a wipe of your home folder.
Claude Code's security plugin doesn't know your repo's rules. Teach it.
The security plugin reviews Claude's code for generic vulnerabilities: injection, deserialization, SSRF. But it doesn't know you never log customer_id here, or that every /admin route needs a guard. You write that in yourself.
Paste screenshots into Claude Code with Ctrl+V (and why some silently vanish)
You save the screenshot, drag it in, type out the path. Skip all of it: one key pastes it straight into the prompt. And if you ever tried and nothing happened, it wasn't you.
Attribution in Claude Code: strip the 'Co-Authored-By: Claude' line from your commits
Claude Code signs every commit it touches, unless you tell it no twice: once for the model, once for the CLI itself.
Get only what matters
If I have nothing worth saying, you won't hear from me. When I do, you'll be the first to know. 7,000+ people already trust this.
Unsubscribe at any time.