ultrathink returns to Claude Code CLI
Claude Code has brought back the ultrathink command, allowing users to increase reasoning depth during the current turn when a task turns out to be more complex than expected.
ultrathink returns to Claude Code CLI
The feature was previously disabled because it seemed unusual and could confuse users.
Developers have now decided to bring it back. If a task turns out to be more complex than you expected, simply enter ultrathink while Claude is still working. This raises the reasoning level until the end of the current turn.
Why it matters
AnalysisThe return of ultrathink gives developers a quick way to deepen analysis and planning in Claude Code without restarting the session.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Claude Code Skill Brainstorming: Designing a Project Before Writing Code
Skill Brainstorming in Claude Code helps explore approaches, clarify requirements, and design architecture before the first line of code is written.
Claude Code Projects: How a Single AI Orchestrates a Team of Autonomous Agents
A deep dive into Claude Code Projects: Coordinator and Threads architecture, parallel branches, shared memory via MEMORY.md, and cloud agent management.
Claude Code: The Beginner's Handbook
Complete engineering guide to Claude Code by Anthropic: CLI setup, authentication, permissions management, essential hotkeys, and building your first project.
Claude Code
The official terminal agent from Anthropic, operating directly in the command line via Claude 3.7 Sonnet with native support for Bash, Git, file systems, and the MCP protocol.