Claude Code 2.1.304
By Steven Van ·
The release adds a person-only approval option for mod tool checks and brings /auto-mode-setup to Bedrock, Vertex and Foundry.
Claude Code 2.1.304 adds new controls for mods, a guided auto mode setup and a usage warning for resumed conversations on Pro and Max.
Mod hooks and tool checks
- A transcript line now appears when a plugin that runs first skips one of your mod's hooks. It names the event and the plugin.
- A mod's tool.check answer accepts decider: "person". Only the permission dialog or a host's callback can then approve the ask. Where nobody can be asked, the ask is refused with the mod's reason.
- The tool.check event now carries e.isReadOnly, set when the tool call is read-only.
Auto mode and API commands
/auto-mode-setup is a guided setup that reads your project and recent sessions to teach auto mode about your environment. It is 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. It does not change anything.
Transcript and usage limits
The compaction summary in the transcript view (Ctrl+O) now lists the names of tools called earlier.
On Pro and Max plans, Claude Code warns when resuming an inactive conversation would use a noticeable share of the 5-hour usage limit. You can resume anyway, or start a new conversation. Claude can look up the previous one if you refer to it.
