Skip to main content
Releases v2.1.234 → v2.1.2393 features · August 17–21
/designresearch preview

The /design skill brings Claude Design’s artboard workflow into the CLI and Claude Code Desktop, built on artifacts. Run it with a brief and Claude publishes a canvas of editable artboards for your UI. Pick one, tweak it, then have Claude implement it. Available on Pro, Max, Team, and Enterprise. Requires v2.1.233 or later.

Describe what you want designed and let Claude draft the options:

Claude Code

Claude prints a link to the published canvas. Open it, pick an artboard, and tell Claude which option to implement.

Where artifacts are available
Concise output stylev2.1.237

Concise is a new built-in output style. Claude leads with the result and skips preamble and narration, while doing the work as thoroughly as in the Default style. When you ask for an explanation or more detail, Claude answers in full. Error reports, security warnings, and confirmations for destructive actions keep their complete content.

Turn it on under Output style in /config, or set it in your settings file:

~/.claude/settings.json

Run /clear or start a new session, and Claude’s replies lead with the result.

Built-in output styles
Start a session on your machine from your phonemobile

Any machine running claude remote-control now shows up as a device card at the top of the Code tab in the Claude app. Remote Control is also out of research preview.

The Code tab in the Claude mobile app with a Devices section showing a connected MacBook as a device card above the sessions list

Start Remote Control on the machine you want to reach, then open the Code tab on your phone:

terminal

Your machine appears as a device card at the top of the Code tab. Tap it to pick a directory and start a session there.

Start a Remote Control session

Other wins

Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off from the Continue automatically at usage limit row in /config
The optional spellcheck setting underlines misspelled words in the prompt input as you type, using your installed aspell, hunspell, or ispell
On a branch with an open GitLab merge request, with the glab CLI authenticated through glab auth login, the footer shows an MR !N badge colored by whether the merge request is a draft, open, or mergeable
Change the effort level from your phone or claude.ai/code and it applies to the session on your machine; Remote Control sessions hosted by Desktop or VS Code also show connected devices the session’s current permission mode
You can open /permissions or run /add-dir <path> while Claude is working; permission rule changes apply to the rest of the current turn
When background tasks keep a /goal waiting, Claude checks in on them after 30 minutes instead of waiting indefinitely and keeps checking in, at longer intervals while the session sits idle; set CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0 to opt out
Your own prompts now render markdown in the transcript, with highlighted code blocks, inline code, and lists, the same way replies do
The new ANTHROPIC_DEFAULT_MODEL environment variable sets the model new sessions start on; a /model pick still overrides it and persists across restarts
With the notify_when_idle input on SendMessage, Claude can ask another Claude Code session on the same machine to send one notice when it next goes idle
Set keybindingFlavor to “readline” to make Ctrl+W in the prompt delete back to the previous whitespace, as Bash does, instead of stopping at punctuation such as /
On native Windows, your Claude Code sessions can now message each other with SendMessage and find each other with ListAgents, as on macOS and Linux
Self-hosted runners accept --defer-shutdown-max-min, which keeps serving attached sessions for a set number of minutes after SIGTERM
Self-hosted runners accept --proxy-authorization-command or --proxy-authorization-file to supply a fresh Proxy-Authorization header for egress proxies that require one
Full changelog for v2.1.234–v2.1.239 →