/review-code-fix
Iterative review-fix loop that keeps going until your code passes the quality bar.
When to use: Code-only review when you want to skip auto-scope-detection (backend-only PR, library code). Use
/review-fullinstead if: your diff has frontend changes — it'll dispatch to UX review too. Called by:/review-full(auto-dispatched on code diffs —/shipPhase R reaches this transitively).
How it works
Round 1: Review → list issues → fix Critical/Major/Warning → re-review
Round 2: Review again → fix remaining → re-review
Round 3: Final attempt → fix → final review
If still failing → report to user with remaining issues
Score Gate
The pass threshold is strictly greater than 9:
| Score | Result |
|---|---|
| 10 | Pass |
| 9.5 | Pass |
| 9.0 | Fail |
| 8.5 | Fail |
A 9.0 means at least one Major issue or two Warnings remain. That's not ship-ready.
<!-- CONFIGURE: Adjust the threshold to match your quality bar -->Severity Levels
| Severity | Score impact | Auto-fixed? |
|---|---|---|
| Critical (-3) | Security, data loss, broken build | Yes |
| Major (-1) | Bug, perf regression, missing tests | Yes |
| Warning (-0.5, max -2) | Convention violations | Yes |
| Suggestion (0) | Style preference, naming nits | No |
Fix Strategy
Fixes are applied by scope to avoid conflicts:
- Group issues by file/directory
- Fix each group
- Run lint + typecheck after each batch
- Re-review only after all fixes pass
Review Focus
- Type safety — no
any, proper null handling, explicit returns - Security — no secrets, input validation, injection prevention
- Performance — N+1 queries, missing indexes, bundle size
- Testing — coverage on changed code paths
- Conventions — naming, imports, file organization
Output Format
Summary: 1-3 sentences
Issues:
- [Critical] [file:line] description
- [Major] [file:line] description
- [Warning] [file:line] description
- [Suggestion] [file:line] description (not auto-fixed)
Score: X/10