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.
Sonnet 5 in Claude Code: near-Opus quality, at Sonnet prices
Sonnet 5 just landed in Claude Code: the most agentic Sonnet yet, with 1M context and near-Opus 4.8 quality at a clearly lower cost. Here's what changes for you and how to switch (heads-up: on Max your Default is still Opus).
Your Claude Code output style is silently deleting its engineering behavior
You build an output style with personality and, without warning, Claude starts coding worse. It isn't the model: your style stripped the built-in engineering instructions. One frontmatter line prevents it.
Your Claude Code usage limit, always in sight in the status line
The 5-hour limit runs out without warning and Claude stops. The number already ships in every response: with four lines of bash you keep it in the status line, without stopping to run /usage.
Stop approving every plan in Claude Code (without opening the floodgates)
You kick off a plan, step away, and come back to find it idle, waiting for your OK. A hook scoped to one permission auto-approves the plan while bash, edits and MCP keep asking.
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.