Skip to content

Conversation

nicholasachow
Copy link

  • Clarifies how each escalating prompt (“think” → “ultrathink”) increases Claude’s thinking budget
  • Adds a reference to Anthropic’s official Claude Code Best Practices for deeper guidance

- Clarifies how each escalating prompt (“think” → “ultrathink”) increases Claude’s thinking budget
- Adds a reference to Anthropic’s official *Claude Code Best Practices* for deeper guidance
@zebbern zebbern requested review from zebbern and Copilot August 21, 2025 17:15
Copy link

@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR adds documentation to explain Claude's escalating prompt levels and their effect on thinking budgets. It clarifies the hierarchy of prompts from "think" to "ultrathink" and references Anthropic's official best practices guide.

  • Adds explanation of Claude's escalating prompt levels ("think" → "ultrathink")
  • Includes reference to Anthropic's official Claude Code Best Practices documentation

Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.

@zebbern zebbern removed their request for review August 24, 2025 23:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant