Claude Code command that plans your codebase in the cloud
/ultraplan offloads implementation planning from your terminal to a cloud session, where you can annotate, revise, and approve the plan before execution. For engineers using Claude Code.
Claude Code just added a new slash command,/ultraplan, that moves the planning phase of your coding workflow out of the terminal and into the browser.
The problem with planning in a CLI is that you're stuck in a linear, terminal-bound loop.
You run /plan, read a wall of text, approve or reject the whole thing, and move on.
There's no way to comment on a specific section, annotate what you agree with, or flag what you want changed without rewriting the entire prompt.
/ultraplan fixes this.
You run the command from your local CLI, and Claude generates the implementation plan remotely on Anthropic's cloud infrastructure.
Your terminal stays free while that's happening.
When the plan is ready, you open it in a browser on claude.ai and interact with it like a document: inline comments on specific passages, emoji reactions per section, and an outline sidebar to jump around.
You can ask Claude to revise, iterate, and re-draft until the plan looks right.
Once approved, you choose: execute the plan in the same cloud session and get a PR, or teleport it back to your terminal with full local environment access.
What makes it interesting is the split between where planning happens and where execution happens.
Planning is mostly reading and reasoning, so the cloud is fine.
Execution often needs your local environment. /ultraplan respects that distinction.
Who it's for: engineers and teams already using Claude Code who need more control over the planning phase before code gets written.
Particularly useful for larger refactors, migrations, or anything where approving a plan blindly feels risky.
Worth noting: requires Claude Code v2.1.91 or later, Claude Code on the Web enabled, and a GitHub repo. Not available on Bedrock, Vertex, or Foundry.
Claude Code just added a new slash command,/ultraplan, that moves the planning phase of your coding workflow out of the terminal and into the browser.
The problem with planning in a CLI is that you're stuck in a linear, terminal-bound loop.
You run /plan, read a wall of text, approve or reject the whole thing, and move on.
There's no way to comment on a specific section, annotate what you agree with, or flag what you want changed without rewriting the entire prompt.
/ultraplan fixes this.
You run the command from your local CLI, and Claude generates the implementation plan remotely on Anthropic's cloud infrastructure.
Your terminal stays free while that's happening.
When the plan is ready, you open it in a browser on claude.ai and interact with it like a document: inline comments on specific passages, emoji reactions per section, and an outline sidebar to jump around.
You can ask Claude to revise, iterate, and re-draft until the plan looks right.
Once approved, you choose: execute the plan in the same cloud session and get a PR, or teleport it back to your terminal with full local environment access.
What makes it interesting is the split between where planning happens and where execution happens.
Planning is mostly reading and reasoning, so the cloud is fine.
Execution often needs your local environment. /ultraplan respects that distinction.
Who it's for: engineers and teams already using Claude Code who need more control over the planning phase before code gets written.
Particularly useful for larger refactors, migrations, or anything where approving a plan blindly feels risky.
Worth noting: requires Claude Code v2.1.91 or later, Claude Code on the Web enabled, and a GitHub repo. Not available on Bedrock, Vertex, or Foundry.