Claude Code v2.1.304 Is Here: /auto-mode-setup and Resume Warnings for Pro and Max!

Hi everyone, it's Shii-chan! Claude Code v2.1.304 is out, so let me pick out the highlights.

What was announced?

These are the Claude Code release notes. It's a packed release with many additions, fixes, improvements, and changes.

Here are the notable additions, with what's new for each:

/auto-mode-setup: 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 telemetry-disabled sessions
/claude-api managed-agents-secure: compares a Managed Agents agent's settings with Anthropic's published security guide, without changing anything
On Pro and Max plans, a warning appears when resuming an inactive conversation would use a noticeable share of your 5-hour usage limit. You can resume anyway, or start a new conversation and Claude can look up the previous one if you refer to it
The compaction summary in the transcript view (Ctrl+O) now includes the names of tools called earlier

Fixes worth knowing about:

Sandboxed commands failing to start on Linux when a sandbox.filesystem.denyRead glob contains brackets that are not a character class, such as a [user-id] route folder
rm -r of a mounted drive or a top-level folder (/Volumes, /media, WSL's /mnt/c) now gets the same safety prompt that rm -rf /Applications gets
claude --worktree could remove the worktree and its branch without asking at exit when HEAD was detached or on another branch, which could lose commits
CLAUDE_CODE_AUTO_COMPACT_WINDOW=200k silently set a 100K window. The variable now accepts k and M suffixes and warns on out-of-range values
Self-paced /loop wakeups scheduled at the 1-hour maximum no longer fire just after the prompt cache expires
context_management: Extra inputs are not permitted errors behind LLM gateways are handled by resending the request without that field

There are changes around mods and settings too:

Added decider: "person" to a mod's tool.check answer. Only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked
Added e.isReadOnly to a mod's tool.check event, set when the tool call is read-only
Mods' settings.read hooks now receive each settings layer and rewrite the merged settings, so a managed mod can make an organization's setting a ceiling, including cleanupPeriodDays
Tool search is on by default behind a custom ANTHROPIC_BASE_URL, and a 400 or 422 from the gateway is retried without it
Skills from one source (a repo, your own folder, or a plugin) can register at most 1,024 hooks and 16,384 matcher characters per session
Code Review gets review levels: Quick, Standard (the default), or Deep, chosen by owners for the organization with optional per-repository levels
Also included: clearer /usage rate limit messages, better responsiveness and memory use with many subagents, and fixes for the VS Code extension and Claude Tag

This release is for heavy users of auto mode and the sandbox, and for anyone writing mods!