ldy26098
/
BMAD-METHOD
mirror of https://github.com/bmad-code-org/BMAD-METHOD.git
1
0
Fork 0
Code Packages Projects Releases Wiki Activity

fix: remove minimum 3 issues quota from code review workflow 

PROBLEM:
Code review workflow forced minimum 3 issues per review, causing:
- Forced nitpicking even when code was good
- Endless review cycles and developer fatigue
- Artificial bug introduction to meet quota

FIX:
Changed from "3-10 minimum" to "0-10 issues celebrate good code":
- Line 10: "Find 0-10 specific issues" (was "3-10 minimum")
- Lines 96-103: New smart validation
  * 0 issues = celebrate and proceed
  * <3 issues on complex story = optional deeper review (not forced)

SAFETY:
- Still adversarial (checks all ACs, tasks, security, tests)
- Still catches bad code (just doesn't punish good code)
- Context-aware (complex stories get gentle nudge)

TESTING:
- Tested in indie-lytics project
- Improved developer experience significantly
- No reduction in code quality

FIXES:
GitHub issue submitted by community member

Co-Authored-By: blade035 <blade035@hotmail.com>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
This commit is contained in:
blade035 2026-01-15 22:45:40 +03:00
parent 66e7d3a36d
commit ca126bccb2
1 changed files with 8 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
src/modules/bmm/workflows/4-implementation/code-review/instructions.xml
View File

@ -7,8 +7,7 @@
<critical>🔥 YOU ARE AN ADVERSARIAL CODE REVIEWER - Find what's wrong or missing! 🔥</critical> <critical>🔥 YOU ARE AN ADVERSARIAL CODE REVIEWER - Find what's wrong or missing! 🔥</critical>
<critical>Your purpose: Validate story file claims against actual implementation</critical> <critical>Your purpose: Validate story file claims against actual implementation</critical>
<critical>Challenge everything: Are tasks marked [x] actually done? Are ACs really implemented?</critical> <critical>Challenge everything: Are tasks marked [x] actually done? Are ACs really implemented?</critical>
<critical>Find 3-10 specific issues in every review minimum - no lazy "looks good" reviews - YOU are so much better than the dev agent <critical>Find 0-10 specific issues in every review - celebrate good code when you find it! If code is genuinely good, say "looks good" and move on</critical>
that wrote this slop</critical>
<critical>Read EVERY file in the File List - verify implementation against story requirements</critical> <critical>Read EVERY file in the File List - verify implementation against story requirements</critical>
<critical>Tasks marked complete but not done = CRITICAL finding</critical> <critical>Tasks marked complete but not done = CRITICAL finding</critical>
<critical>Acceptance Criteria not implemented = HIGH severity finding</critical> <critical>Acceptance Criteria not implemented = HIGH severity finding</critical>
@ -94,17 +93,13 @@
5. **Test Quality**: Are tests real assertions or placeholders? 5. **Test Quality**: Are tests real assertions or placeholders?
</action> </action>
<check if="total_issues_found lt 3"> <check if="total_issues_found eq 0">
<critical>NOT LOOKING HARD ENOUGH - Find more problems!</critical> <info>✅ No issues found - This code is ready for production! Great work!</info>
<action>Re-examine code for: <action>Skip additional issue finding, proceed to fix decision step</action>
- Edge cases and null handling </check>
- Architecture violations <check if="total_issues_found lt 3 AND story_complexity eq 'high'">
- Documentation gaps <warning>Only found {total_issues_found} issues for a complex story - consider deeper review</warning>
- Integration issues <action>Optional: Re-examine for edge cases, architecture issues, or integration problems</action>
- Dependency problems
- Git commit message quality (if applicable)
</action>
<action>Find at least 3 more specific, actionable issues</action>
</check> </check>
</step> </step>