Claude Code automatically compacts conversation history while preserving important information, so you can work on longer problems without worrying about context limits.
8/ Web fetch
Paste a URL into Claude Code, and it will pull the content from that webpage as context.
Super handy to not context switch as much between Claude Code and a browser.
Up first: Vim mode. This gives you the familiar insert/command modes for editing your prompts in Claude Code. Turn it on by typing the slash command /vim.
But that's not all:
Custom slash commands. You can create personalized workflows that can be invoked anytime as slash commands.
Make them by adding Markdown files to your .claude/commands/ or ~/.claude/commands/ directories. The contents of those files will become new commands.
You can build commands for common workflows like "triage GitHub issues," "spellcheck the code," and "query Sentry logs then bisect to a git commit."
Think of them as saved workflows for tasks you want to run more often.
We've just shipped a new feature in Claude Code: extended thinking. You can simply ask Claude to “think”, “think more”, or “think harder” and it’ll show its extended thinking process.
This is all powered by our hybrid reasoning model, Claude 3.7 Sonnet.
Best practice: First tell Claude about your task and let it gather context from your project. Then, ask it to “think” to create a plan.
Claude will think more based on the words you use. For example, “think hard” will trigger more extended thinking than saying “think” alone.
I'll be sharing more new features for Claude Code over the coming weeks.