Review a Change Before You Ship It
Review a diff for concrete failures in behavior, permissions, and data handling, with evidence for each finding.
- Actionable findings
- File and line evidence
- User impact first
When to use it
A change looks finished and you want a focused second look before release.
Bring this context
The diff or base commit, intended behavior, and affected user roles.
review-before-shipping.md
copy · customize · try itReview this change as if you will help support it after release.
Change to review: [diff, PR, or base commit]
Intended behavior: [what should improve]
People and roles affected: [users and permissions]
Known constraints: [compatibility, performance, data, or rollout constraints]
Read the diff and enough surrounding code to understand the real execution path. Focus on problems introduced by this change: incorrect results, unauthorized access, data loss, broken integrations, and failures users can trigger.
For each finding, include severity, file and line, the triggering input or sequence, expected versus actual behavior, and the smallest useful fix. Explain the evidence. Keep an unverified suspicion separate from a confirmed defect.
Look for missing tests where a concrete failure could slip through. Run available targeted checks when useful. Don't rewrite the implementation as part of this review.
Return findings in order of user impact. If you find no actionable issues, say so and list what you checked and what you couldn't verify. Don't fill the report with style preferences.Make this prompt yours
- 1. Download or copyCopy the prompt into your AI tool, or download a copy to keep.
- 2. Customize itReplace bracketed details with your context. Include a real example when you can.
- 3. Test it on real workTry a real task, inspect the output, and refine the prompt where the result misses the mark.
Research behind this prompt
An original DevLaunch adaptation, informed by these sources. Reviewed September 23, 2026; source publication dates vary. Test the result against your own work.
- OpenAI · Codex best practices ↗
Task context, clear constraints, and a concrete definition of done.