Claude Code v2.1.146: Code Review Command and PowerShell Fixes
TL;DR
Renamed the `/simplify` command to `/code-review` with optional effort levels. This release also resolves Windows PowerShell tool failures, fixes MCP pagination issues, and improves auto-updater reliability and diff rendering performance.
The latest update to Claude Code brings version 2.1.146. The command previously known as simplify has been renamed to code review. This new command includes options for different effort levels during reviews.
Windows users will notice fixes for PowerShell tool problems. Additional improvements address pagination issues in MCP. The auto updater has become more reliable as well.
Diff rendering performance has seen enhancements too. These changes make the overall experience smoother for users. Small business owners can benefit from more consistent code assistance.
Who this matters for
- Vibe Builders: Use the new /code-review command to audit prompt-generated scripts for logic and security flaws.
- Developers: Update to v2.1.146 to fix PowerShell tool failures and improve diff rendering for large codebases.
Harsh’s take
Anthropic is rapidly maturing its CLI tool to compete with Aider and Cursor. Renaming simplify to code-review signals a shift from basic refactoring to professional grade quality assurance. For developers on Windows, the PowerShell fixes are critical as early versions were notoriously buggy outside of Linux environments.
The focus on MCP pagination and diff performance shows Claude Code is moving past the experimental phase. Builders should prioritize this update to maintain stable connections with external data sources via MCP. This release proves that the terminal is becoming the primary interface for high velocity AI engineering.
by Harsh Desai
About Claude Code
View the full Claude Code page →All Claude Code updatesGo deeper
More AI news
- Daily RoundupVercel for Slack beta, Fish Audio free on AI Gateway, and agent tools for builders
Vercel expanded Slack integration and added free audio models while Google pushed Gemini to students and Waymo; Hugging Face and Product Hunt surfaced new models and agent loops; industry stories covered compute pricing and watermark bypasses.
- Daily RoundupGLM 5.3 and Vercel agent tools land, Gemini SAT practice, plus fresh models on Hugging Face
Google and Vercel released new agent and model features while Hugging Face and Replicate added trending models; OpenAI tightened safety after agent issues.
- Daily RoundupVercel-Origin beta and GPT-5.6 Sol discount, plus agent tools for builders
Vercel rolled out Origin repository deployments and a month-long GPT-5.6 Sol discount on AI Gateway while Product Hunt featured new agent layers and Hugging Face highlighted an uncensored Qwen model, with industry moves around data use and automation exits.