Claude Code has been updating so frequently that there are some things you might have missed. This quick walkthrough highlights the most useful recent upgrades: custom status lines for instant context, true background commands you can monitor and kill, and flexible output styles that shift Claude from default to explanatory or learning modes. You’ll see how the status line reads structured JSON from each message, why padding matters, and how “bashes” + stdin unlock smoother debugging without constant copy-paste. We’ll also cover permissions/workspaces, Opus plan mode paired with Sonnet’s 1M token context, and a simple way to add your own output style. Perfect if you build daily in Claude Code and want practical gains without hype.

❤️ More about us
Radically better observability stack: https://betterstack.com/
Written tutorials: https://betterstack.com/community/
Example projects: https://github.com/BetterStackHQ

📱 Socials
Twitter: https://twitter.com/betterstackhq
Instagram: https://www.instagram.com/betterstackhq/
TikTok: https://www.tiktok.com/@betterstack
LinkedIn: https://www.linkedin.com/company/betterstack

📌 Chapters:
00: 00 What’s new in Claude Code
00: 23 Custom status line
01: 05 Background commands
01: 40 Output styles: default, explanatory, learning
02: 50 Ask permissions
03: 06 Opus plan mode
03: 20 Bonus release notes