Blog · November 7, 2026 · 8 min read · by Vilva Athiban P B

Claude Code Ultrareview: The 15–25 Minute Cloud Review, What to Do While It Runs, and How the Findings Come Back

Most Claude Code commands finish while you are still looking at the terminal. /code-review ultra does not. The ultrareview docs, read on 7 November 2026, say a review “typically takes 15 to 25 minutes” and runs as a background task on Anthropic’s infrastructure. That is long enough to leave the desk, which is exactly the window this site is about. Here is what the command does, what to do during those minutes, how the findings come back, local vs ultra, a CI recipe, and the trade-offs.

What /code-review ultra is

Ultrareview is a research preview, and the docs say the feature, pricing and availability may change. It went public in week 17 (20 to 24 April 2026, v2.1.114 to v2.1.119) under the name /ultrareview, still an alias where the feature is available to your account; the canonical command is /code-review ultra. It launches “a fleet of reviewer agents in a cloud sandbox” against your branch or pull request. Three claims distinguish it from the local review: every reported finding is independently reproduced and verified, a larger fleet explores the change in parallel, and nothing runs on your machine. Claude never starts an ultrareview on its own; it runs only when you type the command.

By default it reviews the diff between your current branch and the default branch, including uncommitted and staged changes, bundled and uploaded under the rules for sending a local repository to a cloud session. /code-review ultra develop compares against another base. /code-review ultra 1234 reviews a pull request on github.com: the sandbox clones the PR and uploads nothing from your machine. Since v2.1.218 you can add a note in plain words, as in /code-review ultra check my auth changes. A branch review takes up to 500 changed files and 8,000 changed lines by default.

Who can run it

It needs a claude.ai sign-in because it runs as a cloud session; with an API key alone, run /login first. It is not available on Amazon Bedrock, Google Cloud’s Agent Platform or Microsoft Foundry, nor to organisations with Zero Data Retention or the HIPAA configuration; there /code-review ultra runs a local review instead, so read the launch dialog. CMEK organisations cannot run it at all.

Pricing: Pro and Max accounts get three free runs, a one-time allotment that does not refresh. After that a review bills usage credits, “typically $5 to $25” depending on the size of the change, matching the launch dialog’s estimate. A run counts once the cloud session starts, so a review you stop early still spends a free run. Usage credits must be turned on first or Claude Code blocks the launch; /usage-credits checks the setting.

The 15 to 25 minutes: what to do while it runs

After you confirm the launch dialog, the review continues in the background and you can keep using the session. Here is a sensible plan for the gap, in order of how far you want to go from the keyboard.

  1. Keep the session open. This is the one hard rule if you chose to post findings to the PR: Claude Code starts the post when the findings arrive and keeps that choice only in the session. If the session ends first, it posts nothing, even if you resume the conversation later. Without --post the rule relaxes; the review finishes in the cloud regardless.
  2. Check on it with /tasks. It lists running and completed reviews, opens a detail view, and can stop a review in progress. Stopping archives the cloud session and returns no partial findings. The mechanics are the same as any other background task; our background tasks guide covers /tasks in general.
  3. Work on something else in the same session. The docs say so explicitly; the terminal is free.
  4. Step away. Twenty minutes is past the five-minute prompt cache lifetime, if that is the one your plan gets, and short of idle compaction at about minute 54, so read what happens when you step away to know what your first turn back will cost. Leave the terminal running; do not close it.

How the findings come back, and how to hear about it

The docs put it in one line: “When the review finishes, Claude Code shows the verified findings as a notification in your session.” Each finding carries a file location and an explanation, and you can ask Claude to fix it directly; /code-review ultra --fix asks Claude to apply the findings to your working tree when they arrive. With posting enabled, Claude then reports one of three outcomes: posted (with a link to the comment), already posted (an earlier post of the same review is on the PR, so it links to the PR), or failed (with the reason, and the findings stay in your terminal).

That notification is inside the session. The ultrareview page says nothing about a terminal bell or an OS alert, so if you have walked away you need the usual plumbing: the notifications guide and the hooks guide cover running a command when Claude’s turn ends or a permission prompt appears. The moment to catch is not the cloud review finishing but Claude acting on it: with --fix, the edits go through your permission mode, so a prompt can sit waiting while you make coffee. That is what AI Done Now watches for.

Local vs ultra: a decision table

The local review page says you use them at different stages. The rows are from the two docs pages.

  • Target. Local: your working diff, a PR, a branch, a path or a commit range such as HEAD~15..HEAD. Ultra: your working diff or a github.com PR.
  • Where it runs. Local: a background subagent in your session with its own context window. Ultra: a cloud sandbox.
  • Duration. Local: seconds to a few minutes. Ultra: roughly 15 to 25 minutes.
  • Cost. Local: normal plan usage or API billing. Ultra: three free runs, then roughly $5 to $25 per review as usage credits.
  • Depth. Local: scales with the effort level you type (/code-review high), which later runs remember. Ultra: a multi-agent fleet with independent verification; it neither uses nor updates the remembered level.
  • Posting. Local: --comment posts inline PR comments. Ultra: --post posts one plain comment from your GitHub account, v2.1.227 or later, never by default.
  • Use it for. Local: quick feedback while iterating. Ultra: pre-merge confidence on a substantial change; the week 17 note’s examples are auth and data migrations.

A CI recipe with claude ultrareview

claude -p '/code-review ultra' does not get you findings: it launches the cloud review and exits without waiting, and when the review would bill usage credits it stops without launching. The claude ultrareview subcommand, added in week 18 (27 April to 1 May 2026), is the scripting path. It blocks until the review finishes, writes progress to stderr and findings to stdout, exits 0 on completion (with or without findings), 1 on launch failure, stop, cloud error or timeout, and 130 on Ctrl-C. Running it yourself is what counts as consent to billing and to the whole-repository fallback, so it starts without prompting. Our headless mode guide covers the -p side for everything else.

# Review PR 1234 against github.com, wait up to 30 minutes,
# keep the raw bugs.json, and post one comment from your account.
claude ultrareview 1234 --json --timeout 30 --post > bugs.json
status=$?
if [ "$status" -eq 1 ]; then
  echo "ultrareview did not complete (launch failed, stopped, errored or timed out)" >&2
fi
exit "$status"

Three details from the docs. --timeout defaults to 45 minutes; if the subcommand exits before the findings arrive they never reach your terminal, and running it again starts a new review that spends a free run or bills credits. With --post, a run that fails, is stopped or times out posts nothing. The job needs the same claude.ai sign-in and usage-credits setting as the interactive command; it is not an API-key feature.

Honest trade-offs

  • It costs real money after three runs. $5 to $25 per review in usage credits is a different budget line from your plan. Save it for the changes the docs name: substantial, pre-merge, auth and migrations. Not every PR.
  • Research preview. Pricing, limits and availability can change; the docs say so up front.
  • A stopped run is a spent run. Stopping from /tasks returns nothing and uses a free run, and closing the terminal twelve minutes in means no PR comment.

Keep reading

Desk Exercises for Programmers: 15 Moves to Do While Your AI Agent Codes

7 min read

Exercise While Coding: Turn Claude Code Wait Time Into Micro-Workouts

7 min read

Claude Code Notch Notifications on Mac: See When Claude Is Done Without Watching the Terminal

7 min read

Claude Code Tips and Tricks: 12 Ways to Use Claude Code Effectively

8 min read

Claude Code Multiple Sessions: How to Run Agents in Parallel Without Losing Track

6 min read

A Claude Code Workflow That Doesn't Involve Watching the Terminal

5 min read

Claude Code Hooks: A Practical Guide to Automating Your Agent Workflow

7 min read

Claude Code Auto Mode: Fewer Permission Prompts Without Living Dangerously

7 min read

Claude Code Subagents: How to Delegate Work to Specialized Agents

7 min read

Claude Code Context Management: Treat the Context Window Like a Budget

6 min read

Per-Subagent Model Selection: Route the Grunt Work Down, Keep the Judgment Up Top

7 min read

Skills and Plugins: How to Teach Claude Code Your Way of Working

7 min read

Claude Code Background Tasks: Run Long Commands Without Blocking Your Session

6 min read

Codex CLI Notifications: How to Get a Ding When Codex Is Done or Needs Input

7 min read

Cursor Notification When Done: Every Way to Get Notified When Cursor Finishes

6 min read

Claude Code Notifications: How to Get Notified When Claude Code Finishes or Needs Your Input

6 min read

Want to Be Notified When Claude Responds? How Claude Notifications Work on Web, Desktop, and Mobile

5 min read

Claude Code Notification Scripts: Copy-Paste Recipes for Every Platform

6 min read

Get a Ding the Moment Codex Needs Your Response

6 min read

Get Notified the Moment Claude Code Is Waiting for Your Input

6 min read

“Notifications Are Turned Off for Claude” — Here Is the Fix

6 min read

Codex Sound When Done: Make Codex CLI Play a Sound When It Finishes

6 min read

terminal-notifier + Claude Code: Native macOS Alerts When Your Agent Finishes

6 min read

Gemini CLI Notifications: How to Get a Sound or Alert When Gemini Finishes

6 min read

Get Claude Code Notifications on Your Phone

6 min read

Claude Code Remote Control, Explained

7 min read

preferredNotifChannel: Claude Code's Built-In Notification Setting

6 min read

Claude Code Notifications in tmux and Over SSH

7 min read

Claude Code Effort Levels: Why Your Setting Keeps Getting Ignored

8 min read

Codex vs Claude Code Notifications: How Each One Tells You It Is Done

8 min read

Claude Code Notifications Not Working: A Diagnostic Checklist

10 min read

Claude Code Notifications Inside Your Editor's Terminal

7 min read

CLAUDE_CODE_DISABLE_BACKGROUND_TASKS Explained

7 min read

CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP Explained

8 min read

Cursor Alerts Explained: Every Alert Cursor Raises, and How to Control Them

7 min read

Claude Code Environment Variables: The Groups That Actually Matter

10 min read

Claude Code Notifications on WSL and Windows

9 min read

Claude Code Checkpoints and /rewind

8 min read

Claude Remote Control: How It Works, Turning It Off, and Auto Mode

7 min read

Claude Code /loop: Poll a Deploy, Babysit a PR, and Get Told When It's Done

8 min read

Setting Up NotchFit With OpenAI Codex CLI: Hooks, $notchfit-plan, and the Daily Flow

7 min read

Claude Mods Explained: What the New Plugin Layer Can Do, and How to Turn On 'You Should Know'

9 min read

NotchFit vs Mac Break Reminder Apps: A Clock or a Signal From Your Coding Agent?

8 min read

Claude Code Headless Mode: Running claude -p in Scripts and CI, and the Three Signals That It Finished

10 min read

Building a Movement Habit at a Desk: Use the Agent Run as the Cue, One Set as the Unit, and Streaks Carefully

8 min read

Claude Code MCP Servers Explained: Adding Servers, Choosing a Scope, Handling Secrets, and Why Long Tool Calls Go to the Background

10 min read

/notchfit:plan Explained: How Claude Code or Codex Writes a Weekly Workout Plan the Notch Can Actually Run

8 min read

Claude Code Spinner Verbs Explained: What “Pondering” and “Brewing” Mean, How to Change Them, and Why You Should Stop Watching the Spinner

7 min read

Why NotchFit's Done and Permission Alerts Wait Until Your Set Ends, When That Costs You, and How to Turn the Workout Off

7 min read

How to Resume a Claude Code Session: --continue vs --resume, Naming Sessions, the Session Picker, Branching, and What Comes Back

9 min read

NotchFit on a Mac Without a Notch: How Pill Mode Works on Mac mini, iMac, Mac Studio and a MacBook With the Lid Closed

6 min read

How to Run a Claude Code Session in the Background: /background, claude --bg, Agent View, and Getting Back to It

9 min read

What a Notch App Can See: NotchFit's Local-First Design, What the Claude Code and Codex Hooks Send, and What Stays on Your Mac

7 min read

Why Codex CLI Asks for Permission Every Time, and How to Tune the Sandbox and Approval Policy Without Going Full Access

8 min read

What to Do While Claude Code or Codex Works: A Simple Protocol for the Two-to-Twenty-Minute Gap in Every Agent Run

7 min read

Is It Possible to Get a Notification When Claude Code or Codex Hits a Reset? Yes for Claude Code: the quota_auto_resume Hooks, Explained

8 min read

What a MacBook Notch App Can Actually Do: The Five Kinds of Notch Utility, Their Trade-offs, and Where NotchFit Fits

7 min read

How to Make MCP Servers Not Take Up as Much Context in Claude Code: Tool Search, alwaysLoad, Scopes and Output Caps

8 min read

The notchfit Command Line: Drive Your Workout, Read Status as JSON, Validate Plans and Test the Notch Without Leaving the Terminal

7 min read

How to Audit MCP Tool Calls Made by Claude Code: A Five-Minute Hook Audit Log, OpenTelemetry Tool Events, and the Transcript for Investigations

9 min read

Exercise Snacks: What the Research Actually Says About One-Minute Vigorous Breaks, What It Does Not, and How NotchFit's Agent-Run Sets Compare

8 min read

How Long Until a Claude Code MCP Tool Call Times Out? The Four Timers (Startup, Two-Minute Backgrounding, Idle, Wall-Clock), Their Defaults, and Which One to Change

8 min read

Sitting Too Long as a Developer: The Posture Problems Coding Agents Made Worse, What the Research Says About Breaking Up Sitting, and How NotchFit Turns an Agent Run Into the Break

8 min read

Claude Code .mcp.json Explained: Where Project-Scoped MCP Servers Are Read From, What Happens in Subfolders and Monorepos, and Why a Committed Server Shows Pending Approval

8 min read

Standing Desk Exercises for Developers: Why Standing Still Is Not the Goal, Eight Movements That Fit a Thirty-Second Agent Run, and How NotchFit Cues Them From the Notch

8 min read

The claude mcp Command Reference: add Syntax by Transport, What --scope local, project and user Actually Mean, add-json and add-from-claude-desktop, list, get, remove, login and serve

9 min read

Your First Week With NotchFit: Install and Simulate, Run Real Tasks, Write a Smaller Plan Than You Want, Tune the Alerts, Survive the First Skipped Day, and Decide What Stays

8 min read

How to Stop a Running Claude Code Task: Esc vs Ctrl+C, Background Tasks, Subagents, and Disconnecting Remote Control

8 min read

Pomodoro vs Agent-Driven Breaks: Timing Movement to Claude Code and Codex Runs Instead of a Timer

7 min read

Claude Desktop MCP Configuration: claude_desktop_config.json, Logs, Extensions, and the Difference From Claude Code

9 min read

The 20-20-20 Rule for Developers: Eye Strain, the Evidence, and Agent Runs as the Cue

8 min read

Claude Agent SDK + MCP Servers: mcpServers, allowedTools, Status Checks and Auth

9 min read

Discreet Desk Exercises for an Open-Plan Office While Claude Code Runs

7 min read

claude remote-control Server Mode: Run Claude Code as a Session Server

9 min read

Wrist and Forearm Stretches for Developers: A 60-Second Routine for Every Claude Code Run

7 min read

Claude Remote Control vs Claude Code on the Web: Which to Use and How They Differ

9 min read

Neck and Shoulder Stretches for Developers: A 90-Second Routine Between Agent Runs

7 min read

What Happens When You Step Away From a Claude Code Session: Prompt Cache Expiry, Idle Compaction, and When to Come Back

8 min read

Hip Flexor and Lower Back Stretches for Developers: A Two-Minute Standing Routine Between Agent Runs

7 min read

Claude Code's Monitor Tool: Watch Logs, CI Runs and PRs (Even a WebSocket) and Let Claude React While You Keep Working

7 min read

Hunched Over the Keyboard? Upper-Back (Thoracic) Stretches for Developers: A Two-Minute Seated Routine Between Agent Runs

6 min read

Why Your Legs Go Dead After a Long Claude Code Session: A Two-Minute Standing Calf, Glute and Hamstring Routine Between Agent Runs

7 min read

claude --teleport: Pull a Cloud Session Into Your Terminal, Start One With --cloud, Send Follow-Ups From the CLI, and the Requirements That Trip People Up

8 min read

Rounded Shoulders From Typing? A Two-Minute Chest Opener, Chair Twist and Wall Press Desk Routine for Developers Between Agent Runs

7 min read

Claude Code ultrathink Explained: It Now Runs the Turn at xhigh Effort, How It Differs From /effort, What It Costs in Time, and What to Do While It Runs

7 min read

Best Break Reminder Apps for Mac in 2026: Time Out, Stretchly, BreakTimer, LookAway and NotchFit Compared

7 min read

Claude Code 2.1.319: denyInsteadOfPrompting, MCP Background Tasks and What Changes for Unattended Runs and Notifications

8 min read

Drink Water and Stand Up Cues for Developers: Use Claude Code Agent Runs as Hydration and Standing Reminders

7 min read

Claude Code 2.1.323: Code Mode, Progress Heartbeat, Auto-Mode Fallback and 1M Context — What Changed for Unattended Runs

9 min read

Notch Media Controls on a Mac: What the MacBook Notch Can and Cannot Do, Dynamic Island-Style Apps vs NotchFit

7 min read