Discover insights, learn best practices, and connect with
the growing Claude Code ecosystem
The race to catch Cursor continues...
Loading trends data...
When exploring unfamiliar codebases, use the Task tool with subagent_type=Explore instead of running Glob/Grep directly. This specialized agent handles complex searches more efficiently.
Set up user-prompt-submit-hook to automatically lint, format, or test code before Claude commits. This ensures code quality on every change.
When requesting multiple independent operations, Claude can execute them in parallel. Ask for multiple things at once instead of sequentially.
Claude uses TodoWrite to track multi-step tasks. You can see progress in real-time as tasks move from pending → in_progress → completed.
The code-reviewer agent runs automatically after significant code changes. It catches bugs, security issues, and suggests improvements.
Instead of adding console.logs everywhere, ask Claude to "add strategic debug logging" - it places logs at key decision points.
Get the latest trends, tips, and community insights delivered to your inbox every week. Stay ahead in the Claude Code ecosystem.
Join the community of Claude Code enthusiasts • Free weekly updates
Dec 29 - Jan 4, 2026
The race to catch Cursor continues...
Claude Code
Cursor
Antigravity
bcherny
@bcherny
👋 Hi I'm Boris and I work on Claude Code. I am going to start being more active here on X, since there are a lot of AI and coding related convos happening here. Feel free to tag me with Claude Code feedback or bug reports. Love to hear how y'all are using Claude Code, and what we can do to make it even better.
