Map entry points before a risky change
Claude Code handles this as a draft: Scripts, main files, and the test command in the README. Do not push.
- Steps
- 4
- Cost
- low
- Time
- Half an hour
Unverified · code.claude.com · 16 Oct 2026
Loading the catalog…
Claude Code summarizes breaking changes for a single dependency, applies the upgrade, and runs the existing tests. Major bumps stay behind a question.
Write both in the prompt. 'Upgrade everything' is how lockfiles become unreviewable.
You can split this into two turns if the model rushes. The list is the point of the session.
Claude Code can execute the test script. Read the output rather than trusting a summary that says all green.
Keep refactors out of the same diff so a rollback is possible.
These are editorial labels so you can compare playbooks. They are not measurements.
No. Status is unverified. Paste the prompt, keep the version that worked, and do not treat the time or cost lines as measurements.
The prompt tells the agent to stop on a major bump and to list call sites it can find. You decide whether the gap is acceptable.
Official documentation URL, checked when this seed was written. The prompt and steps are an original AI Playbook Gems playbook, not a quotation of a customer story, and have not been re-run.
Machine-readable copy: JSON
Claude Code handles this as a draft: Scripts, main files, and the test command in the README. Do not push.
Unverified · code.claude.com · 16 Oct 2026
Claude Code reads a single module, writes characterization tests, then changes structure only where those tests pass.
Unverified · code.claude.com · 15 Oct 2026
Claude Code handles this as a draft: Breaking changes that mention the version I am on. Do not run the upgrade.
Unverified · code.claude.com · 8 Oct 2026