@addyosmani: Claude Code tip: if a task turns out harder than you expected, type ultrathink while Claude is working. It raises the e…
Summary
Addy Osmani shares a Claude Code tip: typing "ultrathink" while Claude works raises the effort for the rest of that turn, a feature recently re-enabled in the CLI by Anthropic's Adam Wolff.
View Cached Full Text
Cached at: 11/02/26, 04:03 AM
Claude Code tip: if a task turns out harder than you expected, type ultrathink while Claude is working. It raises the effort for the rest of that turn. In the terminal on the latest release.
Adam Wolff (@dmwlff): ultrathink is back in the CC CLI.
We turned this off for a while because it’s weird and maybe confusing.
But I like weird, and I don’t think it’s that confusing.
I mostly run Opus 5.5 on medium. Some turns, though, I want to put a little extra mustard on it. ultrathink!
Similar Articles
@thedelost: THIS IS PURE F*CKING GOLD Anthropic just shared one of the best tricks for Claude Code. The idea: run Sonnet, Haiku and…
A thread sharing Anthropic's Claude Code 'advisor' trick: run Sonnet for coding, Haiku for parallel exploration, and Opus as an on-call advisor to get better results with far fewer tokens, along with a paste-ready configuration prompt.
@PrajwalTomar_: Someone on the Claude Code team finally wrote this and honestly it's crazy how many people still don't know this. Low f…
A tweet highlights insights from Claude Code team member Thariq (@trq212) on how to use Claude Code's effort levels wisely—using low for quick edits, medium for building, and high or max only when deep verification is needed, since max effort on everything just wastes credits and slows you down.
@ClaudeDevs: How do you keep Claude working until the job is done? Claude Code helps with this in a few ways, including one we shipp…
Anthropic's Claude Code introduces the /goal command to help the AI agent persist and complete tasks until the job is fully done.
@addyosmani: https://x.com/addyosmani/status/2115688494865465370
Addy Osmani shares prompting and workflow tips for Claude Opus 5.5, arguing users are overprompting newer models and outlining how to leverage autonomous verification, subagents, cloud sessions, and Projects in Claude Code.
@addyosmani: Introducing Claude Code mods! Customize how it looks and works just by prompting it. https://claude.dev/blog/getting-st…
Anthropic introduces Claude Code mods, a plugin system of small JS/TS files that run inside a Claude Code session to observe, rewrite, or answer events and draw custom terminal UI, enabling users to customize behavior by simply prompting the assistant.