Daily · · Claude Code · 🌶️🌶️Medium: worth a look this week Why: New warning and commands
Claude Code warns before a costly resume
Back to an old chat after a break? On Pro and Max plans, Claude Code now warns you when resuming an inactive conversation would use a noticeable share of your 5-hour usage limit.
Resume anyway, or start a new conversation and Claude can look up the previous one if you refer to it.
In plain English
Now you’ll know before an old chat takes a noticeable bite of your 5-hour limit. The same release adds two setup commands, new Code Review options and two safety fixes.
Two new setup commands
/is a guided setup that reads your project and recent sessions to teach auto mode about your environment. It’s now also available on Bedrock, Vertex, Foundry, Claude apps gateway and in telemetry-disabled sessions.auto-mode-setup /compares a Managed Agents agent’s settings with Anthropic’s published security guide, without changing anything.claude-api managed-agents-secure
Also in this release
- Code Review owners can choose Quick, Standard (the default) or Deep reviews for the organization, and give individual repositories their own level.
- A new Code Review admin option reviews every repository in a GitHub organization, including ones added later, without selecting them one by one.
rm -rof a mounted drive or a folder at its top level, such as/Volumes,/mediaor WSL’s/mnt/c, now gets the same safety prompt asrm -rf /.Applications claude --worktreeno longer removes the worktree and its branch without asking at exit when HEAD was detached or on another branch, which could lose commits.
To get the Claude Code changes, update to v2.1.304 or later.