Content History
RT Mike Krieger Claude is #1 in the App Store today — I want to say a huge thank you to all of our new (and existing!) users for the support. We’re working hard for you, please share your thoughts and feedback along the way. Original tweet: https://x.com/mikeyk/status/2027882977422610586
In the next version of Claude Code.. We're introducing two new Skills: /simplify and /batch. I have been using both daily, and am excited to share them with everyone. Combined, these kills automate much of the work it used to take to (1) shepherd a pull request to production and (2) perform straightforward, parallelizable code migrations.
RT SemiAnalysis 4% of GitHub public commits are being authored by Claude Code right now. At the current trajectory, we believe that Claude Code will be 20%+ of all daily commits by the end of 2026. While you blinked, AI consumed all of software development. Original tweet: https://x.com/SemiAnalysis_/status/2027443723362042308
RT Cerebral Valley A global virtual hackathon for Opus 4.6 🌐 13,000+ applicants. 500 selected. 227 projects. 6 finalists. 3 winners. Final presentations in front of @bcherny & @_catwu Attendees flying in to be at @SHACK15sf Safe to say, Claude Code’s 1st birthday was one for the ages ⚡️ Original tweet: https://x.com/cerebral_valley/status/2026066211482857844
🎂 Happy 1st birthday to Claude Code Thanks everyone for coming out and celebrating with us!!
RT Dan Shipper 📧 PSA if you're iterating on front-end designs, you should try Claude Code desktop. it's great Original tweet: https://x.com/danshipper/status/2025618482994229431
RT Eren Bali Every technical founder who had stopped coding 10 years ago Original tweet: https://x.com/erenbali/status/2025243266715893922
1/6 2/ Use worktree mode in the Desktop app If you prefer not to use terminal, head to the Code tab in the Claude Desktop app and ☑️ worktree mode https://code.claude.com/docs/en/desktop-quickstart#install2/6 1/ Use claude --worktree for isolation To run Claude Code in its own git worktree, just start it with the --worktree option. You can also name your worktree, or have Claude name it for you. Use this to run multiple parallel Claude Code sessions in the same git repo, without the code edits clobbering each other. You can also pass the --tmux flag to launch Claude in its own Tmux session.3/6 Introducing: built-in git worktree support for Claude Code Now, agents can run in parallel without interfering with one other. Each agent gets its own worktree and can work independently. The Claude Code Desktop app has had built-in support for worktrees for a while, and now we're bringing it to CLI too. Learn more about worktrees: https://git-scm.com/docs/git-worktree4/6 4/ Custom agents support git worktrees You can also make subagents always run in their own worktree. To do that, just add "isolation: worktree" to your agent frontmatter5/6 3/ Subagents now support worktrees Subagents can also use worktree isolation to do more work in parallel. This is especially powerful for large batched changes and code migrations. To use it, ask Claude to use worktrees for its agents. Available in CLI, Desktop app, IDE extensions, web, and Claude Code mobile app.6/6 5/ Also available for non-git source control If you're a Mercurial, Perforce, or SVN user, define worktree hooks to benefit from isolation without having to use Git
🫶
Just tried Claude Cowork now… and I seriously regret not using it sooner. This thing is actually insane/crazy good.
Thanks for having me on the pod @garrytan! I joined a YC startup back in the early days of YC in 2011. It’s crazy how much has changed for founders building today vs back then. Small teams (and their Claudes) can do so much now!
1/9 2/ Adjust effort level Run /model to pick your preferred effort level. Set it to: - Low, for less tokens & faster responses - Medium, for balanced behavior - High, for more tokens & more intelligence Personally, I use High for everything.2/9 1/ Configure your terminal - Theme: Run /config to set light/dark mode - Notifs: Enable notifications for iTerm2, or use a custom notifs hook - Newlines: If you use Claude Code in an IDE terminal, Apple Terminal, Warp, or Alacritty, run /terminal-setup to enable shift+enter for newlines (so you don't need to type \) - Vim mode: run /vim https://code.claude.com/docs/en/terminal-config3/9 3/ Install Plugins, MCPs, and Skills Plugins let you install LSPs (now available for every major language), MCPs, skills, agents, and custom hooks. Install a plugin from the official Anthropic plugin marketplace, or create your own marketplace for your company. Then, check the settings.json into your codebase to auto-add the marketplaces for your team. Run /plugin to get started. https://code.claude.com/docs/en/discover-plugins4/9 4/ Create custom agents To create custom agents, drop .md files in .claude/agents. Each agent can have a custom name, color, tool set, pre-allowed and pre-disallowed tools, permission mode, and model. There's also a little-known feature in Claude Code that lets you set the default agent used for the main conversation. Just set the "agent" field in your settings.json or use the --agent flag. Run /agents to get started, or learn more: https://code.claude.com/docs/en/sub-agents5/9 5/ Pre-approve common permissions Claude Code uses a sophisticated permission system with a combo of prompt injection detection, static analysis, sandboxing, and human oversight. Out of the box, we pre-approve a small set of safe commands. To pre-approve more, run /permissions and add to the allow and block lists. Check these into your team's settings.json. We support full wildcard syntax. Try "Bash(bun run *)" or "Edit(/docs/**...
RT alistair In the next version of Claude Code `claude --version` gets 15x faster Original tweet: https://x.com/alistaiir/status/2021639295313019126
actually codex is better because it’s 7x faster to print the version number
View quoted postRT Eric Buess Agent swarms in Claude Code 2.1.32 with Opus 4.6 are very very very good. And with tmux auto-opening each agent in it's own interactive mode with graceful shutdown when done it's a breeze to do massive robust changes without the main agent using up much of its context window!🔥 Original tweet: https://x.com/EricBuess/status/2019569423670211030
RT Dylan Patel 4% of GitHub public commits are being authored by Claude Code right now. At the current trajectory, we believe that Claude Code will be 20%+ of all daily commits by the end of 2026. While you blinked, AI consumed all of software development. Read more 👇 https://newsletter.semianalysis.com/p/claude-code-is-the-inflection-point Original tweet: https://x.com/dylan522p/status/2019490550911766763
Claude Code is the Inflection Point, What It Is, How We Use It, Industry Repercussions, Microsoft's Dilemma, Why Anthropic Is Winning. https://newsletter.semianalysis.com/p/claude-code-is-the-inflection-point
View quoted post1/6 2. Start every complex task in plan mode. Pour your energy into the plan so Claude can 1-shot the implementation. One person has one Claude write the plan, then they spin up a second Claude to review it as a staff engineer. Another says the moment something goes sideways, they switch back to plan mode and re-plan. Don't keep pushing. They also explicitly tell Claude to enter plan mode for verification steps, not just for the build2/6 1. Do more in parallel Spin up 3–5 git worktrees at once, each running its own Claude session in parallel. It's the single biggest productivity unlock, and the top tip from the team. Personally, I use multiple git checkouts, but most of the Claude Code team prefers worktrees -- it's the reason @amorriscode built native support for them into the Claude Desktop app! Some people also name their worktrees and set up shell aliases (za, zb, zc) so they can hop between them in one keystroke. Others have a dedicated "analysis" worktree that's only for reading logs and running BigQuery See https://code.claude.com/docs/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees3/6 3. Invest in your http://CLAUDE.md. After every correction, end with: "Update your http://CLAUDE.md so you don't make that mistake again." Claude is eerily good at writing rules for itself. Ruthlessly edit your http://CLAUDE.md over time. Keep iterating until Claude's mistake rate measurably drops. One engineer tells Claude to maintain a notes directory for every task/project, updated after every PR. They then point http://CLAUDE.md at it.4/6 5. Claude fixes most bugs by itself. Here's how we do it: Enable the Slack MCP, then paste a Slack bug thread into Claude and just say "fix." Zero context switching required. Or, just say "Go fix the failing CI tests." Don't micromanage how. Point Claude at docker logs to troubleshoot distributed systems -- it's surprisingly capable at this.5/6 8. Use subagents a. Append "use subagents" to any request w...
Just released: Plugins support for Cowork https://claude.com/download
Cowork now supports plugins. Plugins let you bundle any skills, connectors, slash commands, and sub-agents together to turn Claude into a specialist for your role, team, and company.
Interesting
As of Q4 2025 Anthropic is now beating OpenAI to first spend from new startups (based on Mercury spend data). Claude Code and Opus 4.5 has been a step change improvement and startups are the quickest to react.
In the next version of Claude Code, you can customize spinner verbs for yourself and your team
RT The Wall Street Journal They call it getting “Claude-pilled.” It’s the moment software engineers, executives and investors turn their work over to Anthropic’s Claude AI—and then witness a thinking machine of shocking capability, even in an age awash in powerful AI tools. https://on.wsj.com/4k2CU9E Original tweet: https://x.com/WSJ/status/2015530668365611340
Hooks can now run in the background without blocking Claude Code's execution. Just add async: true to your hook config. Great for logging, notifications, or any side-effect that shouldn't slow things down.
Cowork update: @-mention files, MCP resources, or windows from your desktop apps directly in the chat. And if your task calls for a specific tool, Claude will suggest the right connector automatically
Proud of the team for shipping the VSCode extension! It has been available for many months, and is now officially generally available
The VS Code extension for Claude Code is now generally available. It’s now much closer to the CLI experience: @-mention files for context, use familiar slash commands (/model, /mcp, /context), and more. Download it here: https://marketplace.visualstudio.com/items?itemName=anthropic.claude-code
Now in Claude Code: when you accept a plan, Claude automatically clears your context, so your plan gets a fresh context window. We found this helps keep Claude on track longer, and significantly improves plan adherence. If you prefer not to clear your context when accepting a plan, that option is still available too.
Was super fun to dial into Claude Code Istanbul and Tokyo. Excited to do a bunch more of these, and to meet more Claude Code users around the world!
We ran over 50 Claude Code community meetups in December, with almost every one of them having someone from the Claude Code team call in. We're going to continue this throughout the entire year! I hope you get to attend one :)
You asked, we listened. The team has been cooking this for a while. Can't wait to hear what you think.
New in Claude Code on the web and desktop: diff view. See the exact changes Claude made without leaving the app.
