Find bugs with ultrareview changedultrareview
Nearest release: v2.1.309, published 4 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 23 Oct 2026 00:36 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 23 Oct 2026 00:37 UTC.
Upstream edited
Recorded here
Lines+19added
Lines−6removed
From line
143
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits22to this page, all time
### Trust the folder before the review runs
The whole hunk
from line 143, old and new numbered
/
from line 143
143143
144144## Run ultrareview non-interactively
145145
146Use the `claude ultrareview` subcommand to start an ultrareview from CI or a script without an interactive session. The subcommand launches the same review as `/code-review ultra`, blocks until the remote review finishes, and prints the findings to stdout.
146Use the `claude ultrareview` subcommand to start an ultrareview from CI or a script without an interactive session. The subcommand launches the same review as `/code-review ultra`, blocks until the remote review finishes, and prints the findings to stdout. If the run exits with `Error: Workspace not trusted`, see [Trust the folder before the review runs](#trust-the-folder-before-the-review-runs).
147147
148148```bash theme={null}
149149claude ultrareview
from line 153
153153
154154Without arguments, the subcommand reviews the diff between your current branch and the default branch, with the same [whole-repository fallback](#diff-limits-and-fallbacks) as `/code-review ultra` when no merge base exists. Pass a PR number to [review a pull request on `github.com`](#review-a-pull-request), or a base branch to review against it; [base-branch handling](#review-against-a-different-base) matches the interactive command.
155155
156You consent to the whole-repository fallback and to the billing and terms prompt when you run the subcommand, so the run starts without waiting for input. Running it yourself is what counts as consent. When Claude runs the subcommand for you instead, for example through the Bash tool, Claude Code refuses the whole-repository review.
156You consent to the whole-repository fallback and to the billing and terms prompt when you run the subcommand, so the run doesn't stop to confirm them. Running it yourself is what counts as consent. When Claude runs the subcommand for you instead, for example through the Bash tool, Claude Code refuses the whole-repository review.
157157
158158`claude -p '/code-review ultra'` doesn't get you the findings, so use `claude ultrareview` in scripts. The `-p` run launches the cloud review and exits without waiting for it. When the review would bill usage credits, the `-p` run stops without launching it. Before v2.1.218, `/code-review ultra` in a non-interactive session ran a local review.
159159
160`claude ultrareview` writes its progress messages to stderr so stdout stays parseable. Use these flags to control its output, the timeout, and whether to post the findings:
161
162160| Flag | Description |
163161| - | - |
164162| `--json` | Print the raw `bugs.json` payload instead of the formatted findings |
from line 163
165163| `--timeout <minutes>` | Maximum minutes to wait for the review to finish. Defaults to 45 |
166164| `--post` | [Post the finished findings](#post-findings-to-the-pull-request) to the pull request as one plain comment from your GitHub account. Works on `github.com` pull request targets; on other targets, Claude Code ignores the flag and says so. Requires Claude Code v2.1.227 or later |
167165| `--no-post` | Don't post the findings. This is the default, and if you pass both flags, Claude Code doesn't post. Requires Claude Code v2.1.227 or later |
166| `--trust-workspace` | [Trust the current folder](#trust-the-folder-before-the-review-runs) for this run only, without asking, so a script or CI job can review a checkout you haven't trusted. Takes no value: put a PR number or base branch before it. Requires Claude Code v2.1.309 or later |
168167
168`claude ultrareview` writes its progress messages to stderr so stdout stays parseable.
169
169170Running `claude ultrareview` requires the same authentication and usage-credits configuration as `/code-review ultra`.
170171
171172The subcommand exits with one of three codes:
172173
173174* **0**: the review completed, with or without findings
174* **1**: the review failed to launch or was stopped before it finished, the cloud session errored, or the timeout elapsed
175* **130**: you interrupted the subcommand with Ctrl-C
175* **1**: the review failed to launch or was stopped before it finished, the cloud session errored, or the timeout elapsed. The code is also 1 when the [folder isn't trusted](#trust-the-folder-before-the-review-runs), including when you answer `n` or press Ctrl-C at the trust question.
176* **130**: you pressed Ctrl-C while the subcommand was launching the review, waiting for the findings, or sending the `--post` comment, rather than at the trust question
176177
177178If the subcommand exits before the findings arrive, they never reach your terminal. The review may still be running in the cloud. Running the subcommand again starts a new review rather than resuming that one, and the new review [uses a free run or bills as usage credits](#pricing-and-free-runs).
178179
from line 183
182183* If the review completes but the comment isn't posted, Claude Code prints the reason to stderr, and the findings stay on stdout so you can post them by hand.
183184
184185For automatic reviews on GitHub pull requests, [Code Review](/docs/en/code-review.md) integrates with your repository directly and posts findings as inline PR comments without a CLI step.
186
187### Trust the folder before the review runs
188
189When `claude ultrareview` asks `Trust <folder>? [y/N]`, answer `y` to [trust the folder](/docs/en/permissions.md#project-allow-rules-and-workspace-trust). Trust it only if you trust its code, because git and Claude Code can then run programs named in its git configuration and project settings.
190
191When it can't ask you, such as in a CI job or with output sent to a file, it exits with [`Error: Workspace not trusted`](/docs/en/errors#workspace-not-trusted-when-running-claude-ultrareview). Append `--trust-workspace` to trust the folder for that run:
192
193```bash theme={null}
194claude ultrareview 1234 --trust-workspace
195```
196
197To review an untrusted pull request, run `claude ultrareview <PR number> --trust-workspace` from a branch you trust. Unlike `y`, the flag saves nothing. The PR is [cloned in the cloud](#review-a-pull-request), so you don't need its branch locally.
185198
186199## How ultrareview compares to /code-review
187200
No line in this hunk matches that.