Claude Code Stops Auto-Running /verify and /code-review
Claude CodeAnthropic changed Claude Code's default behavior so that Claude no longer runs the /verify and /code-review skills on its own initiative; developers must now explicitly invoke /verify or /code-review when they want them to run. The skills themselves are unchanged — only the automatic triggering was removed. This flips the experience for two different groups of users: those who relied on automatic checks now need to add explicit invocations to their workflow, while those who found the unprompted reviews disruptive get a quieter, on-demand experience.
From Automatic to On-Demand
Starting in version 2.1.215, Claude Code no longer decides on its own to run /verify or /code-review partway through a session. Previously, Claude could trigger either skill autonomously when it judged a change worth double-checking; now, both only run when a developer explicitly types /verify or /code-review.
Why It Matters
The change is a small diff in the changelog but a real shift in day-to-day behavior. Developers who had come to rely on Claude proactively double-checking its own work will need to build an explicit /verify or /code-review step into their habits or automation going forward. Conversely, developers who found unsolicited reviews interrupting their flow — especially in fast iteration loops — get a quieter session by default, with review available on request rather than imposed automatically.