Skip to content

Claude Code Changelog

Release notes, new features, and updates tracked daily. Sourced from the official Claude Code changelog at docs.anthropic.com.

  1. Featurev2.1.208

    Claude Code adds vimInsertModeRemaps for custom insert-mode mappings

    Claude Code added the vimInsertModeRemaps setting to map two-key insert-mode sequences such as jj to Escape in vim mode.

    Source ↗
  2. Featurev2.1.203

    Claude Code adds login expiration warnings for background sessions

    Claude Code displays a warning notification when login is about to expire. Users can re-authenticate before background sessions are interrupted.

    Source ↗
  3. Featurev2.1.205

    Claude Code adds auto mode rule to prevent session transcript tampering

    Claude Code added an auto mode security rule that blocks attempts to tamper with or modify session transcript files.

    Source ↗
  4. Featurev2.1.210

    Claude Code adds live elapsed-time counter to collapsed tool summary

    Claude Code now displays a live elapsed-time counter in the collapsed tool summary line for long-running tool calls.

    Source ↗
  5. Featurev2.1.191

    Claude Code adds /rewind to resume conversations from before /clear

    Claude Code added /rewind support to restore conversations cleared by the /clear command.

    Source ↗
  6. Featurev2.1.198

    Claude Code adds /dataviz skill for chart and dashboard design

    Claude Code adds a new /dataviz skill that provides chart and dashboard design guidance along with a runnable color-palette validator.

    Source ↗
  7. Featurev2.1.199

    Claude Code supports up to five stacked slash-skill invocations

    Claude Code now loads all leading skills in stacked slash-skill invocations like /skill-a /skill-b do XYZ, up to five instead of only the first.

    Source ↗
  8. Featurev2.1.198

    Claude Code enables background execution for subagents by default

    Claude Code now runs subagents in the background by default. Users receive notifications upon task completion.

    Source ↗
  9. Featurev2.1.191

    Claude Code adds /rewind command and fixes scroll behavior

    Claude Code adds support for the /rewind command to resume conversations from before a clear. The update fixes scroll position jumping during streaming responses and prevents stopped background agents from resurrecting.

    Source ↗
  10. Featurev2.1.196

    Claude Code adds organization default models and clickable file attachments

    Claude Code now allows admins to set organization default models. The update also adds readable default session names, clickable file attachments in chat, and enhanced security for MCP server spawning.

    Source ↗
  11. Featurev2.1.198

    Claude Code 2.1.198: Background subagents by default and Claude in Chrome GA

    Claude Code 2.1.198 enables subagents to run in the background by default and launches Claude in Chrome to general availability. The release adds background agent notifications, the /dataviz skill, and AWS as an upstream provider.

    Source ↗
  12. Featurev2.1.181

    Claude Code adds /config key=value syntax to configure settings from prompts

    Claude Code added the /config key=value syntax for setting configuration options directly from the prompt in interactive, print, and remote control modes.

    Source ↗
  13. Featurev2.1.191

    Claude Code adds support for resuming conversations before /clear

    Claude Code adds a /rewind command to resume conversations from before the /clear command while preserving context.

    Source ↗
  14. Featurev2.1.186

    Claude Code adds CLI auth for MCP servers and automatic bash responses

    Claude Code adds claude mcp login and logout commands for authenticating MCP servers via CLI. Bash commands prefixed with '!' now trigger automatic Claude responses to output.

    Source ↗
  15. Featurev2.1.187

    Claude Code adds sandbox.credentials to block credential access

    Claude Code adds a sandbox.credentials setting that blocks sandboxed commands from reading credential files and secret environment variables.

    Source ↗