-
Notifications
You must be signed in to change notification settings - Fork 12
Add --updated flag to review-plan skill #133
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
When using /review-plan a second time after making revisions, the agent would short-circuit instead of performing a fresh review. The --updated flag forces a complete re-review and adds a Delta Assessment section comparing the revised plan against prior review feedback. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Overall AssessmentExecutive Summary
MethodologyNone — no estimator/methodology changes in this PR. Code Quality
PerformanceNone. Maintainability
Tech DebtNone. SecurityNone. Documentation/TestsNone. |
Fix three issues raised by AI review: - Switch from substring to token-based --updated flag parsing to prevent false matches inside file paths - Replace "skip Delta Assessment" with "fill with unavailable message" to resolve contradiction with Step 5's "do NOT skip any section" rule - Restore explicit AskUserQuestion fallback prompt template Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
/ai-review |
|
🔁 AI review rerun (requested by @igerber) Head SHA: Overall assessment: Executive summary:
MethodologyNone. (Change is limited to Code Quality
PerformanceNone. MaintainabilityNone. Tech DebtNone. SecurityNone. Documentation/Tests
|
Move [--updated] before <path-to-plan-file> in the argument hint to match CLI conventions (flags before positional args) and align with the parsing instructions that already allow either ordering. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
/ai-review |
|
🔁 AI review rerun (requested by @igerber) Head SHA: Overall assessment: Executive summary
MethodologyNone. This PR only updates Code Quality
PerformanceNone. MaintainabilityNone. Tech DebtNone. SecurityNone. Documentation/TestsNone. |
Summary
--updatedflag to/review-planskill that forces a complete fresh re-review of revised plans--updatedis provided, the agent performs all 8 review dimensions without short-circuiting, and appends a Delta Assessment section comparing against prior review feedbackMethodology references (required if estimator / math changes)
Validation
.claude/commands/review-plan.md)Security / privacy
Generated with Claude Code