Anthropic released Claude Code 2.1.328 on November 18. The biggest change: Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry and the Claude apps gateway now support auto mode, and interactive sessions with no permission mode set start in it; disableAutoMode turns it off. On most models, /code-review now reports only bugs and CLAUDE.md violations and marks each finding Important, Pre-existing or Nit, while cleanup suggestions move to /simplify.

Key Takeaways

  • ✓Auto mode reaches third-party platforms: Opus 4.6 and Sonnet 4.6 on Bedrock, Google Cloud's Agent Platform, Microsoft Foundry and the Claude apps gateway
  • ✓Default change: interactive sessions with no permission mode start in auto mode; plan mode and Bash prompts also offer it, and disableAutoMode turns both off
  • ✓/code-review: on most models it reports only bugs and CLAUDE.md violations, marks each Important, Pre-existing or Nit and suggests a fix; reuse, simplification and efficiency cleanups move to /simplify
  • ✓Hooks: mcp_tool hooks accept "onFailure": "block", so a failed hook call blocks the action
  • ✓Also: fixes zsh commands failing with "not found" on words starting with =, automatic compaction reusing an old system prompt, and many Code Mode issues
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🧭

Heavy Claude Code use: compare subscription limits and API bills

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Background

Many companies use Claude through Amazon Bedrock, Google Cloud or Microsoft Foundry, but auto mode was not available there for Opus 4.6 and Sonnet 4.6, so developers either approved prompts constantly or skipped permission checks entirely. Separately, /code-review output mixed many style and cleanup suggestions in with the bugs that actually needed fixing.

How it works

According to the official CHANGELOG, 2.1.328 brings auto mode to Opus 4.6 and Sonnet 4.6 on those third-party platforms, and interactive sessions with no permission mode set start in it; plan mode and Bash prompts now offer auto mode too, and disableAutoMode turns both off. /code-review is split up: it reports and grades only bugs and CLAUDE.md violations, while cleanup suggestions go to /simplify. mcp_tool hooks gain "onFailure": "block".

Benchmarks

This is a tool release; Anthropic published no benchmarks or impact figures.

What it means for developers

Run claude update or upgrade through npm to 2.1.328. On third-party platforms, sessions without a permission mode now behave differently; teams that do not want auto mode by default should enable disableAutoMode or set an explicit permission mode. After upgrading, try /code-review on an existing PR, then run /simplify for cleanup suggestions.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

Up NextX Debate: AI Commentator Chubby Says Claude Code and Opus 5.5 Have Been His Daily Driver for Two Months and GPT Is "Not Close," but Concedes Computer Use Is Still GPT's Edge; 150+ Replies Focus on Splitting Work by Task and the Same-Day Claude Login Outage
Read Now→