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 hides its thinking now: what actually brings it back (and the fixes that don't)
Since an update, Claude Code on a subscription redacts the reasoning by default: the model thinks (and you pay), but you don't see it. The real way to bring it back is a combination of two settings, not the tricks going around.
Your own security rules in Claude Code: catch hardcoded secrets on every edit, for free
Claude Code's security plugin ships generic checks. The part almost nobody configures is the free layer: a file of your own patterns that catches your secrets and leaks on every edit, without spending a token.
Stop babysitting your PRs: let Claude Code fix the failing CI for you
You push the PR and sit there refreshing GitHub to see if CI passes. There's a terminal command that moves that loop to the cloud: it watches the PR and pushes the fix on its own when CI fails or a review comment lands.
Prompts in Claude Code: the 5 rules Anthropic actually follows
Five concrete rules straight from Anthropic's official docs that any Claude Code prompt should follow. Not from a prompt-engineering course, from the docs themselves. Same rules whether you're vibe coding or shipping production.
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.