Getting the most out of Opus 5.5 in Claude and Claude Code
This guide provides best practices for using Anthropic's Opus 5.5 model within Claude apps and Claude Code. It emphasizes that the model is optimized for long-running tasks and does not require explicit 'think step-by-step' prompting.
Why it matters
As AI models become more autonomous, understanding how to effectively prompt and steer them is critical for developers and power users.
[ H ] HOME [ M ] MODS [ D ] DOCS [ T ] TERMINAL Playbooks Getting the most out of Opus 5.5 in Claude and Claude Code How to prompt Opus 5.5, steer a long run, and check your results in Claude apps and Claude Code.
Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.
Three things to try in your first session with Opus 5.5
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in