feat: add super-dev-story workflow for enhanced quality
- New /super-dev-story command for comprehensive validation - Includes all dev-story steps PLUS: - Step 9.5: Post-dev gap analysis (verify completion) - Step 9.6: Automated code review (catch issues) - Auto-fixes issues and loops back if gaps/problems found - Max iteration safety (default 3 cycles) - Opt-in via separate command (not forced) - ~30% more tokens but prevents review rework cycles Applies to both BMM and BMGD modules
This commit is contained in:
Jonah Schulte
parent
dd25e12f96
commit
cff53fb3d8
|
|
@ -0,0 +1,283 @@
|
|||
# Super-Dev-Story Workflow
|
||||
|
||||
**Enhanced story development with comprehensive quality validation**
|
||||
|
||||
## What It Does
|
||||
|
||||
Super-dev-story is `/dev-story` on steroids - it includes ALL standard development steps PLUS additional quality gates:
|
||||
|
||||
```
|
||||
Standard dev-story:
|
||||
1-8. Development cycle → Mark "review"
|
||||
|
||||
Super-dev-story:
|
||||
1-8. Development cycle
|
||||
9.5. Post-dev gap analysis (verify work complete)
|
||||
9.6. Automated code review (catch issues)
|
||||
→ Fix issues if found (loop back to step 5)
|
||||
9. Mark "review" (only after all validation passes)
|
||||
```
|
||||
|
||||
## When to Use
|
||||
|
||||
### Use `/super-dev-story` for:
|
||||
|
||||
- ✅ Security-critical features (auth, payments, PII handling)
|
||||
- ✅ Complex business logic with many edge cases
|
||||
- ✅ Stories you want bulletproof before human review
|
||||
- ✅ High-stakes features (production releases, customer-facing)
|
||||
- ✅ When you want to minimize review cycles
|
||||
|
||||
### Use standard `/dev-story` for:
|
||||
|
||||
- Documentation updates
|
||||
- Simple UI tweaks
|
||||
- Configuration changes
|
||||
- Low-risk experimental features
|
||||
- When speed matters more than extra validation
|
||||
|
||||
## Cost vs Benefit
|
||||
|
||||
| Aspect | dev-story | super-dev-story |
|
||||
|--------|-----------|-----------------|
|
||||
| **Tokens** | 50K-100K | 80K-150K (+30-50%) |
|
||||
| **Time** | Normal | +20-30% |
|
||||
| **Quality** | Good | Excellent |
|
||||
| **Review cycles** | 1-3 iterations | 0-1 iterations |
|
||||
| **False completions** | Possible | Prevented |
|
||||
|
||||
**ROI:** Extra 30K tokens (~$0.09) prevents hours of rework and multiple review cycles
|
||||
|
||||
## What Gets Validated
|
||||
|
||||
### Step 9.5: Post-Dev Gap Analysis
|
||||
|
||||
**Checks:**
|
||||
- Tasks marked [x] → Code actually exists and works?
|
||||
- Required files → Actually created?
|
||||
- Claimed tests → Actually exist and pass?
|
||||
- Partial implementations → Marked complete prematurely?
|
||||
|
||||
**Catches:**
|
||||
- ❌ "Created auth service" → File doesn't exist
|
||||
- ❌ "Added tests with 90% coverage" → Only 60% actual
|
||||
- ❌ "Implemented login" → Function exists but incomplete
|
||||
|
||||
**Actions if issues found:**
|
||||
- Unchecks false positive tasks
|
||||
- Adds tasks for missing work
|
||||
- Loops back to implementation
|
||||
|
||||
### Step 9.6: Automated Code Review
|
||||
|
||||
**Reviews:**
|
||||
- ✅ Correctness (logic errors, edge cases)
|
||||
- ✅ Security (vulnerabilities, input validation)
|
||||
- ✅ Architecture (pattern compliance, SOLID principles)
|
||||
- ✅ Performance (inefficiencies, optimization opportunities)
|
||||
- ✅ Testing (coverage gaps, test quality)
|
||||
- ✅ Code Quality (readability, maintainability)
|
||||
|
||||
**Actions if issues found:**
|
||||
- Adds review findings as tasks
|
||||
- Loops back to implementation
|
||||
- Continues until issues resolved
|
||||
|
||||
## Usage
|
||||
|
||||
### Basic Usage
|
||||
|
||||
```bash
|
||||
# Load any BMAD agent
|
||||
/super-dev-story
|
||||
|
||||
# Follows same flow as dev-story, with extra validation
|
||||
```
|
||||
|
||||
### Specify Story
|
||||
|
||||
```bash
|
||||
/super-dev-story docs/sprint-artifacts/1-2-auth.md
|
||||
```
|
||||
|
||||
### Expected Flow
|
||||
|
||||
```
|
||||
1. Pre-dev gap analysis
|
||||
├─ "Approve task updates? [Y/A/n/e/s/r]"
|
||||
└─ Select option
|
||||
|
||||
2. Development (standard TDD cycle)
|
||||
└─ Implements all tasks
|
||||
|
||||
3. Post-dev gap analysis
|
||||
├─ Scans codebase
|
||||
├─ If gaps: adds tasks, loops back
|
||||
└─ If clean: proceeds
|
||||
|
||||
4. Code review
|
||||
├─ Analyzes all changes
|
||||
├─ If issues: adds tasks, loops back
|
||||
└─ If clean: proceeds
|
||||
|
||||
5. Story marked "review"
|
||||
└─ Truly complete!
|
||||
```
|
||||
|
||||
## Fix Iteration Safety
|
||||
|
||||
Super-dev has a **max iteration limit** (default: 3) to prevent infinite loops:
|
||||
|
||||
```yaml
|
||||
# workflow.yaml
|
||||
super_dev_settings:
|
||||
max_fix_iterations: 3 # Stop after 3 fix cycles
|
||||
fail_on_critical_issues: true # HALT if critical security issues
|
||||
```
|
||||
|
||||
If exceeded:
|
||||
```
|
||||
🛑 Maximum Fix Iterations Reached
|
||||
|
||||
Attempted 3 fix cycles.
|
||||
Manual intervention required.
|
||||
|
||||
Issues remaining:
|
||||
- [List of unresolved issues]
|
||||
```
|
||||
|
||||
## Examples
|
||||
|
||||
### Example 1: Perfect First Try
|
||||
|
||||
```
|
||||
/super-dev-story
|
||||
|
||||
Pre-gap: ✅ Tasks accurate
|
||||
Development: ✅ 8 tasks completed
|
||||
Post-gap: ✅ All work verified
|
||||
Code review: ✅ No issues
|
||||
|
||||
→ Story complete! (45 minutes, 85K tokens)
|
||||
```
|
||||
|
||||
### Example 2: Post-Dev Catches Incomplete Work
|
||||
|
||||
```
|
||||
/super-dev-story
|
||||
|
||||
Pre-gap: ✅ Tasks accurate
|
||||
Development: ✅ 8 tasks completed
|
||||
Post-gap: ⚠️ Tests claim 90% coverage, actual 65%
|
||||
|
||||
→ Adds task: "Increase test coverage to 90%"
|
||||
→ Implements missing tests
|
||||
→ Post-gap: ✅ Now 92% coverage
|
||||
→ Code review: ✅ No issues
|
||||
|
||||
→ Story complete! (52 minutes, 95K tokens)
|
||||
```
|
||||
|
||||
### Example 3: Code Review Finds Security Issue
|
||||
|
||||
```
|
||||
/super-dev-story
|
||||
|
||||
Pre-gap: ✅ Tasks accurate
|
||||
Development: ✅ 10 tasks completed
|
||||
Post-gap: ✅ All work verified
|
||||
Code review: 🚨 CRITICAL - SQL injection vulnerability
|
||||
|
||||
→ Adds task: "Fix SQL injection in user search"
|
||||
→ Implements parameterized queries
|
||||
→ Post-gap: ✅ Verified
|
||||
→ Code review: ✅ Security issue resolved
|
||||
|
||||
→ Story complete! (58 minutes, 110K tokens)
|
||||
```
|
||||
|
||||
## Comparison to Standard Workflow
|
||||
|
||||
### Standard Flow (dev-story)
|
||||
|
||||
```
|
||||
Day 1: Develop story (30 min)
|
||||
Day 2: Human review finds 3 issues
|
||||
Day 3: Fix issues (20 min)
|
||||
Day 4: Human review again
|
||||
Day 5: Approved
|
||||
|
||||
Total: 5 days, 2 review cycles
|
||||
```
|
||||
|
||||
### Super-Dev Flow
|
||||
|
||||
```
|
||||
Day 1: Super-dev-story
|
||||
- Development (30 min)
|
||||
- Post-gap finds 1 issue (auto-fix 5 min)
|
||||
- Code review finds 2 issues (auto-fix 15 min)
|
||||
- Complete (50 min total)
|
||||
|
||||
Day 2: Human review
|
||||
Day 3: Approved (minimal/no changes needed)
|
||||
|
||||
Total: 3 days, 1 review cycle
|
||||
```
|
||||
|
||||
**Savings:** 2 days, 1 fewer review cycle, higher initial quality
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### "Super-dev keeps looping forever"
|
||||
|
||||
**Cause:** Each validation finds new issues
|
||||
**Solution:** This indicates quality problems. Review max_fix_iterations setting or manually intervene.
|
||||
|
||||
### "Post-dev gap analysis keeps failing"
|
||||
|
||||
**Cause:** Dev agent marking tasks complete prematurely
|
||||
**Solution:** This is expected! Super-dev catches this. The loop ensures actual completion.
|
||||
|
||||
### "Code review too strict"
|
||||
|
||||
**Cause:** Reviewing for issues standard dev-story would miss
|
||||
**Solution:** This is intentional. For less strict review, use standard dev-story.
|
||||
|
||||
### "Too many tokens/too slow"
|
||||
|
||||
**Cause:** Multi-stage validation adds overhead
|
||||
**Solution:** Use standard dev-story for non-critical stories. Reserve super-dev for important work.
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **Reserve for important stories** - Don't use for trivial changes
|
||||
2. **Trust the process** - Fix iterations mean it's working correctly
|
||||
3. **Review limits** - Adjust max_fix_iterations if stories are complex
|
||||
4. **Monitor costs** - Track token usage vs review cycle savings
|
||||
5. **Learn patterns** - Code review findings inform future architecture
|
||||
|
||||
## Configuration Reference
|
||||
|
||||
```yaml
|
||||
# _bmad/bmgd/config.yaml or _bmad/bmgd/config.yaml
|
||||
|
||||
# Per-project settings
|
||||
super_dev_settings:
|
||||
post_dev_gap_analysis: true # Enable post-dev validation
|
||||
auto_code_review: true # Enable automatic code review
|
||||
fail_on_critical_issues: true # HALT on security vulnerabilities
|
||||
max_fix_iterations: 3 # Maximum fix cycles before manual intervention
|
||||
auto_fix_minor_issues: false # Auto-fix LOW severity without asking
|
||||
```
|
||||
|
||||
## See Also
|
||||
|
||||
- [dev-story workflow](../dev-story/) - Standard development workflow
|
||||
- [gap-analysis workflow](../gap-analysis/) - Standalone audit tool
|
||||
- [Gap Analysis Guide](../../../../docs/gap-analysis.md) - Complete documentation
|
||||
- [Super-Dev Mode Concept](../../../../docs/super-dev-mode.md) - Vision and roadmap
|
||||
|
||||
---
|
||||
|
||||
**Super-Dev-Story: Because "done" should mean DONE** ✅
|
||||
|
|
@ -0,0 +1,362 @@
|
|||
<workflow>
|
||||
<critical>The workflow execution engine is governed by: {project-root}/_bmad/core/tasks/workflow.xml</critical>
|
||||
<critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
|
||||
<critical>Communicate all responses in {communication_language} and language MUST be tailored to {user_skill_level}</critical>
|
||||
<critical>Generate all documents in {document_output_language}</critical>
|
||||
<critical>🚀 SUPER-DEV MODE: Enhanced quality workflow with post-implementation validation and automated code review</critical>
|
||||
<critical>This workflow ensures stories are TRULY complete through multi-stage validation before marking done</critical>
|
||||
<critical>⚙️ EXECUTION FLOW: First execute ALL dev-story steps (1-8), then continue with super-dev enhancements (9.5-9.6)</critical>
|
||||
|
||||
<!-- ═══════════════════════════════════════════════════════════════ -->
|
||||
<!-- STEPS 1-8: STANDARD DEV-STORY WORKFLOW -->
|
||||
<!-- ═══════════════════════════════════════════════════════════════ -->
|
||||
|
||||
<critical>🎯 EXECUTE DEV-STORY STEPS 1-8 FIRST</critical>
|
||||
<critical>Follow all instructions in: {project-root}/_bmad/bmgd/workflows/4-production/dev-story/instructions.xml</critical>
|
||||
<critical>Complete Steps 1 through 8 exactly as specified in dev-story workflow</critical>
|
||||
<critical>After Step 8 completes (all tasks checked), return here and continue with Step 9.5 below</critical>
|
||||
|
||||
<note>⚙️ Super-dev-story includes ALL standard dev-story steps (1-8):
|
||||
- Step 1: Find and load story
|
||||
- Step 1.5: Pre-dev gap analysis and task refinement
|
||||
- Step 2: Load project context
|
||||
- Step 3: Detect review continuation
|
||||
- Step 4: Mark story in-progress
|
||||
- Step 5: Implement task (red-green-refactor)
|
||||
- Step 6: Author comprehensive tests
|
||||
- Step 7: Run validations and tests
|
||||
- Step 8: Validate and mark task complete
|
||||
|
||||
See dev-story/instructions.xml for complete details of these steps.
|
||||
</note>
|
||||
|
||||
<!-- SUPER-DEV ENHANCEMENTS START HERE -->
|
||||
|
||||
<step n="9.5" goal="Post-development gap analysis">
|
||||
<critical>🔍 POST-DEV VALIDATION - Verify all work actually completed!</critical>
|
||||
<note>This catches incomplete implementations that were prematurely marked done</note>
|
||||
|
||||
<output>
|
||||
🔎 **Post-Development Gap Analysis**
|
||||
|
||||
All tasks marked complete. Verifying against codebase reality...
|
||||
</output>
|
||||
|
||||
<!-- Re-scan codebase with fresh eyes -->
|
||||
<action>Re-read story requirements and acceptance criteria</action>
|
||||
<action>Extract all tasks and subtasks that are marked [x] complete</action>
|
||||
<action>For each completed task, identify what should exist in codebase</action>
|
||||
|
||||
<!-- SCAN PHASE -->
|
||||
<action>Use Glob to find files that should have been created</action>
|
||||
<action>Use Grep to search for functions/classes that should exist</action>
|
||||
<action>Use Read to verify implementation completeness (not just existence)</action>
|
||||
<action>Run tests to verify claimed test coverage actually exists and passes</action>
|
||||
|
||||
<!-- ANALYSIS PHASE -->
|
||||
<action>Compare claimed work vs actual implementation:</action>
|
||||
|
||||
**POST-DEV VERIFICATION:**
|
||||
<action>✅ Verified Complete:
|
||||
- List tasks where code fully exists and works
|
||||
- Confirm tests exist and pass
|
||||
- Verify implementation matches requirements
|
||||
</action>
|
||||
|
||||
<action>❌ False Positives Detected:
|
||||
- List tasks marked [x] but code missing or incomplete
|
||||
- Identify claimed tests that don't exist or fail
|
||||
- Note partial implementations marked as complete
|
||||
</action>
|
||||
|
||||
<action>⚠️ Quality Issues:
|
||||
- Implementations that exist but don't meet requirements
|
||||
- Tests that exist but have poor coverage
|
||||
- Code that works but violates architecture patterns
|
||||
</action>
|
||||
|
||||
<!-- DECISION PHASE -->
|
||||
<check if="false positives found OR quality issues found">
|
||||
<output>
|
||||
⚠️ **Post-Dev Gaps Detected!**
|
||||
|
||||
**False Positives (marked done but not complete):**
|
||||
{{list_false_positives_with_details}}
|
||||
|
||||
**Quality Issues:**
|
||||
{{list_quality_issues_with_details}}
|
||||
|
||||
**Proposed Actions:**
|
||||
{{list_tasks_to_add_for_missing_work}}
|
||||
|
||||
---
|
||||
|
||||
These issues must be addressed before story can be marked complete.
|
||||
</output>
|
||||
|
||||
<action>Uncheck false positive tasks in story file</action>
|
||||
<action>Add new tasks for missing work to Tasks/Subtasks section</action>
|
||||
<action>Add note to Dev Agent Record: "Post-dev gap analysis found incomplete work - continuing implementation"</action>
|
||||
<action>Update Gap Analysis section with post-dev findings</action>
|
||||
<action>Set {{fix_iteration_count}} = {{fix_iteration_count}} + 1</action>
|
||||
|
||||
<check if="{{fix_iteration_count}} > {{max_fix_iterations}}">
|
||||
<output>🛑 **Maximum Fix Iterations Reached**
|
||||
|
||||
Attempted {{fix_iteration_count}} fix cycles.
|
||||
Manual intervention required.
|
||||
|
||||
Issues remaining:
|
||||
{{list_remaining_issues}}
|
||||
</output>
|
||||
<action>Add to Dev Agent Record: "HALTED - exceeded max fix iterations, manual review needed"</action>
|
||||
<action>HALT - require user intervention</action>
|
||||
</check>
|
||||
|
||||
<output>🔄 Adding missing work to task list and continuing implementation...</output>
|
||||
<goto step="5">Continue implementation with added tasks</goto>
|
||||
</check>
|
||||
|
||||
<check if="no gaps found">
|
||||
<output>✅ **Post-Dev Validation Passed**
|
||||
|
||||
All tasks verified complete against codebase.
|
||||
Proceeding to code review...
|
||||
</output>
|
||||
<action>Update Gap Analysis section with post-dev verification results</action>
|
||||
<action>Continue to Step 9.6</action>
|
||||
</check>
|
||||
</step>
|
||||
|
||||
<step n="9.6" goal="Automated code review">
|
||||
<critical>👀 AUTO CODE REVIEW - Independent quality validation</critical>
|
||||
<note>Fresh perspective catches issues the dev agent might miss</note>
|
||||
|
||||
<output>
|
||||
🔍 **Running Automated Code Review**
|
||||
|
||||
Analyzing implementation for issues...
|
||||
</output>
|
||||
|
||||
<!-- Identify files to review -->
|
||||
<action>Extract File List from Dev Agent Record</action>
|
||||
<action>Identify all files created or modified during implementation</action>
|
||||
|
||||
<!-- REVIEW PHASE: Use code-review workflow logic -->
|
||||
<action>Perform comprehensive code review checking:</action>
|
||||
<action>- **Correctness:** Logic errors, edge cases, error handling</action>
|
||||
<action>- **Architecture:** Compliance with patterns and standards</action>
|
||||
<action>- **Security:** Vulnerabilities, input validation, authentication</action>
|
||||
<action>- **Performance:** Inefficiencies, N+1 queries, memory leaks</action>
|
||||
<action>- **Testing:** Test coverage, edge cases, test quality</action>
|
||||
<action>- **Code Quality:** Readability, maintainability, documentation</action>
|
||||
|
||||
<!-- CATEGORIZE FINDINGS -->
|
||||
<action>Categorize all findings by severity:</action>
|
||||
<action>- CRITICAL: Security vulnerabilities, data loss, broken functionality</action>
|
||||
<action>- HIGH: Logic errors, missing error handling, test gaps</action>
|
||||
<action>- MEDIUM: Code quality issues, minor bugs, performance concerns</action>
|
||||
<action>- LOW: Style issues, documentation improvements, minor refactoring</action>
|
||||
|
||||
<!-- DECISION PHASE -->
|
||||
<check if="CRITICAL or HIGH severity issues found">
|
||||
<output>
|
||||
🚨 **Code Review Found Issues Requiring Fixes**
|
||||
|
||||
**Critical Issues ({{critical_count}}):**
|
||||
{{list_critical_issues}}
|
||||
|
||||
**High Priority Issues ({{high_count}}):**
|
||||
{{list_high_issues}}
|
||||
|
||||
{{if_medium_or_low_exist}}
|
||||
**Medium/Low Issues ({{med_low_count}}):**
|
||||
{{list_medium_low_issues}}
|
||||
{{endif}}
|
||||
|
||||
---
|
||||
|
||||
**These issues must be fixed before story completion.**
|
||||
</output>
|
||||
|
||||
<action>Add "Code Review Findings" section to story file</action>
|
||||
<action>Add review findings as new tasks in Tasks/Subtasks with [AI-Review] prefix</action>
|
||||
<action>Add to Dev Agent Record: "Code review found {{total_issue_count}} issues - continuing with fixes"</action>
|
||||
<action>Set {{fix_iteration_count}} = {{fix_iteration_count}} + 1</action>
|
||||
|
||||
<check if="{{fix_iteration_count}} > {{max_fix_iterations}}">
|
||||
<output>🛑 **Maximum Fix Iterations Reached**
|
||||
|
||||
Code review found issues on iteration {{fix_iteration_count}}.
|
||||
Manual review recommended.
|
||||
|
||||
Issues found:
|
||||
{{list_all_issues}}
|
||||
</output>
|
||||
<action>Add to Dev Agent Record: "HALTED - code review issues after max iterations, manual review needed"</action>
|
||||
<action>HALT - require user intervention</action>
|
||||
</check>
|
||||
|
||||
<output>🔧 Adding review findings to task list and implementing fixes...</output>
|
||||
<goto step="5">Implement fixes</goto>
|
||||
</check>
|
||||
|
||||
<check if="only MEDIUM or LOW severity issues found">
|
||||
<output>
|
||||
ℹ️ **Code Review Found Minor Issues**
|
||||
|
||||
**Medium Issues ({{medium_count}}):**
|
||||
{{list_medium_issues}}
|
||||
|
||||
**Low Priority Issues ({{low_count}}):**
|
||||
{{list_low_issues}}
|
||||
|
||||
---
|
||||
</output>
|
||||
|
||||
<ask>Auto-fix these minor issues?
|
||||
|
||||
Options:
|
||||
[Y] Yes - Add to task list and fix now
|
||||
[n] No - Document in story but don't fix (can address later)
|
||||
[s] Skip - Ignore these findings
|
||||
</ask>
|
||||
|
||||
<check if="user approves Y">
|
||||
<action>Add review findings as tasks with [AI-Review] prefix</action>
|
||||
<action>Add to Dev Agent Record: "Addressing {{issue_count}} minor code review findings"</action>
|
||||
<output>🔧 Implementing minor fixes...</output>
|
||||
<goto step="5">Implement fixes</goto>
|
||||
</check>
|
||||
|
||||
<check if="user says n">
|
||||
<action>Add "Code Review Findings" section documenting issues</action>
|
||||
<action>Add to Dev Agent Record: "Code review found {{issue_count}} minor issues - documented for future work"</action>
|
||||
<output>ℹ️ Issues documented in story. Proceeding to completion...</output>
|
||||
<action>Continue to Step 9</action>
|
||||
</check>
|
||||
|
||||
<check if="user says s">
|
||||
<output>⚠️ Skipping minor issues. Proceeding to completion...</output>
|
||||
<action>Continue to Step 9</action>
|
||||
</check>
|
||||
</check>
|
||||
|
||||
<check if="no issues found">
|
||||
<output>✅ **Code Review Passed**
|
||||
|
||||
No issues found. Implementation meets quality standards.
|
||||
</output>
|
||||
<action>Add to Dev Agent Record: "Code review completed - no issues found"</action>
|
||||
<action>Continue to Step 9</action>
|
||||
</check>
|
||||
</step>
|
||||
|
||||
<step n="9" goal="Story completion and mark for review" tag="sprint-status">
|
||||
<critical>🎯 FINAL VALIDATION - All quality gates must pass!</critical>
|
||||
|
||||
<action>Verify ALL tasks and subtasks are marked [x] (re-scan the story document now)</action>
|
||||
<action>Run the full regression suite (do not skip)</action>
|
||||
<action>Confirm File List includes every changed file</action>
|
||||
<action>Execute enhanced definition-of-done validation</action>
|
||||
|
||||
<!-- Enhanced Definition of Done for Super-Dev -->
|
||||
<action>Validate super-dev quality gates:
|
||||
- ✅ Pre-dev gap analysis completed and approved
|
||||
- ✅ All tasks/subtasks marked complete with [x]
|
||||
- ✅ Implementation satisfies every Acceptance Criterion
|
||||
- ✅ All tests pass (no regressions, new tests successful)
|
||||
- ✅ Post-dev gap analysis passed (no false positives)
|
||||
- ✅ Code review completed (critical/high issues resolved)
|
||||
- ✅ File List includes every new/modified/deleted file
|
||||
- ✅ Dev Agent Record contains implementation notes
|
||||
- ✅ Change Log includes summary of changes
|
||||
</action>
|
||||
|
||||
<action>Update the story Status to: "review"</action>
|
||||
|
||||
<!-- Mark story ready for review - sprint status conditional -->
|
||||
<check if="{sprint_status} file exists AND {{current_sprint_status}} != 'no-sprint-tracking'">
|
||||
<action>Load the FULL file: {sprint_status}</action>
|
||||
<action>Find development_status key matching {{story_key}}</action>
|
||||
<action>Verify current status is "in-progress" (expected previous state)</action>
|
||||
<action>Update development_status[{{story_key}}] = "review"</action>
|
||||
<action>Save file, preserving ALL comments and structure including STATUS DEFINITIONS</action>
|
||||
<output>✅ Story status updated to "review" in sprint-status.yaml</output>
|
||||
</check>
|
||||
|
||||
<check if="{sprint_status} file does NOT exist OR {{current_sprint_status}} == 'no-sprint-tracking'">
|
||||
<output>ℹ️ Story status updated to "review" in story file (no sprint tracking configured)</output>
|
||||
</check>
|
||||
|
||||
<!-- Final validation gates -->
|
||||
<action if="any task is incomplete">HALT - Complete remaining tasks before marking ready for review</action>
|
||||
<action if="regression failures exist">HALT - Fix regression issues before completing</action>
|
||||
<action if="File List is incomplete">HALT - Update File List with all changed files</action>
|
||||
<action if="post-dev gap analysis not completed">HALT - Run post-dev validation before completing</action>
|
||||
<action if="code review not completed">HALT - Run code review before completing</action>
|
||||
</step>
|
||||
|
||||
<step n="10" goal="Super-dev completion communication">
|
||||
<action>Prepare comprehensive summary in Dev Agent Record → Completion Notes</action>
|
||||
|
||||
<output>🎉 **SUPER-DEV STORY COMPLETE, {user_name}!**
|
||||
|
||||
**Story:** {{story_key}} - {{story_title}}
|
||||
**Status:** review (ready for human review)
|
||||
|
||||
---
|
||||
|
||||
**Quality Gates Passed:**
|
||||
✅ Pre-dev gap analysis - Tasks validated before work started
|
||||
✅ Development - All tasks completed with TDD
|
||||
✅ Post-dev gap analysis - Implementation verified complete
|
||||
✅ Code review - {{total_issues_found}} issues found and resolved
|
||||
✅ All tests passing - No regressions
|
||||
|
||||
**Implementation Summary:**
|
||||
- Files changed: {{file_count}}
|
||||
- Tests added: {{test_count}}
|
||||
- Issues fixed: {{review_issues_fixed}}
|
||||
- Fix iterations: {{fix_iteration_count}}/{{max_fix_iterations}}
|
||||
|
||||
**Story File:** {{story_file}}
|
||||
|
||||
---
|
||||
|
||||
**What Super-Dev Validated:**
|
||||
1. 🔍 Tasks matched codebase reality before starting
|
||||
2. 💻 Implementation completed per requirements
|
||||
3. ✅ No false positive completions (all work verified)
|
||||
4. 👀 Code quality and security validated
|
||||
5. 🧪 Comprehensive test coverage achieved
|
||||
|
||||
**Next Steps:**
|
||||
- Review the completed story
|
||||
- Verify business requirements met
|
||||
- Merge when approved
|
||||
|
||||
**Note:** This story went through enhanced quality validation.
|
||||
It should require minimal human review.
|
||||
</output>
|
||||
|
||||
<action>Based on {user_skill_level}, ask if user needs any explanations about:
|
||||
- What was implemented and how it works
|
||||
- Why certain technical decisions were made
|
||||
- Gap analysis or code review findings
|
||||
- Any patterns, libraries, or approaches used
|
||||
</action>
|
||||
|
||||
<check if="user asks for explanations">
|
||||
<action>Provide clear, contextual explanations tailored to {user_skill_level}</action>
|
||||
<action>Use examples and references to specific code when helpful</action>
|
||||
</check>
|
||||
|
||||
<output>💡 **Tip:** This story was developed with super-dev-story for enhanced quality.
|
||||
|
||||
For faster development (fewer validations), use standard `dev-story` workflow.
|
||||
For maximum quality and fewer review cycles, continue using `super-dev-story`.
|
||||
</output>
|
||||
</step>
|
||||
|
||||
</workflow>
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
name: super-dev-story
|
||||
description: "Enhanced story development with post-implementation validation and automated code review - ensures stories are truly complete before marking done"
|
||||
author: "BMad"
|
||||
|
||||
# Critical variables from config
|
||||
config_source: "{project-root}/_bmad/bmgd/config.yaml"
|
||||
output_folder: "{config_source}:output_folder"
|
||||
user_name: "{config_source}:user_name"
|
||||
communication_language: "{config_source}:communication_language"
|
||||
user_skill_level: "{config_source}:user_skill_level"
|
||||
document_output_language: "{config_source}:document_output_language"
|
||||
story_dir: "{config_source}:implementation_artifacts"
|
||||
date: system-generated
|
||||
|
||||
# Workflow components
|
||||
installed_path: "{project-root}/_bmad/bmgd/workflows/4-production/super-dev-story"
|
||||
instructions: "{installed_path}/instructions.xml"
|
||||
validation: "{installed_path}/checklist.md"
|
||||
|
||||
story_file: "" # Explicit story path; auto-discovered if empty
|
||||
implementation_artifacts: "{config_source}:implementation_artifacts"
|
||||
sprint_status: "{implementation_artifacts}/sprint-status.yaml"
|
||||
project_context: "**/project-context.md"
|
||||
|
||||
# Super-dev specific settings
|
||||
super_dev_settings:
|
||||
post_dev_gap_analysis: true
|
||||
auto_code_review: true
|
||||
fail_on_critical_issues: true
|
||||
max_fix_iterations: 3
|
||||
|
||||
standalone: true
|
||||
|
||||
web_bundle: false
|
||||
|
|
@ -0,0 +1,283 @@
|
|||
# Super-Dev-Story Workflow
|
||||
|
||||
**Enhanced story development with comprehensive quality validation**
|
||||
|
||||
## What It Does
|
||||
|
||||
Super-dev-story is `/dev-story` on steroids - it includes ALL standard development steps PLUS additional quality gates:
|
||||
|
||||
```
|
||||
Standard dev-story:
|
||||
1-8. Development cycle → Mark "review"
|
||||
|
||||
Super-dev-story:
|
||||
1-8. Development cycle
|
||||
9.5. Post-dev gap analysis (verify work complete)
|
||||
9.6. Automated code review (catch issues)
|
||||
→ Fix issues if found (loop back to step 5)
|
||||
9. Mark "review" (only after all validation passes)
|
||||
```
|
||||
|
||||
## When to Use
|
||||
|
||||
### Use `/super-dev-story` for:
|
||||
|
||||
- ✅ Security-critical features (auth, payments, PII handling)
|
||||
- ✅ Complex business logic with many edge cases
|
||||
- ✅ Stories you want bulletproof before human review
|
||||
- ✅ High-stakes features (production releases, customer-facing)
|
||||
- ✅ When you want to minimize review cycles
|
||||
|
||||
### Use standard `/dev-story` for:
|
||||
|
||||
- Documentation updates
|
||||
- Simple UI tweaks
|
||||
- Configuration changes
|
||||
- Low-risk experimental features
|
||||
- When speed matters more than extra validation
|
||||
|
||||
## Cost vs Benefit
|
||||
|
||||
| Aspect | dev-story | super-dev-story |
|
||||
|--------|-----------|-----------------|
|
||||
| **Tokens** | 50K-100K | 80K-150K (+30-50%) |
|
||||
| **Time** | Normal | +20-30% |
|
||||
| **Quality** | Good | Excellent |
|
||||
| **Review cycles** | 1-3 iterations | 0-1 iterations |
|
||||
| **False completions** | Possible | Prevented |
|
||||
|
||||
**ROI:** Extra 30K tokens (~$0.09) prevents hours of rework and multiple review cycles
|
||||
|
||||
## What Gets Validated
|
||||
|
||||
### Step 9.5: Post-Dev Gap Analysis
|
||||
|
||||
**Checks:**
|
||||
- Tasks marked [x] → Code actually exists and works?
|
||||
- Required files → Actually created?
|
||||
- Claimed tests → Actually exist and pass?
|
||||
- Partial implementations → Marked complete prematurely?
|
||||
|
||||
**Catches:**
|
||||
- ❌ "Created auth service" → File doesn't exist
|
||||
- ❌ "Added tests with 90% coverage" → Only 60% actual
|
||||
- ❌ "Implemented login" → Function exists but incomplete
|
||||
|
||||
**Actions if issues found:**
|
||||
- Unchecks false positive tasks
|
||||
- Adds tasks for missing work
|
||||
- Loops back to implementation
|
||||
|
||||
### Step 9.6: Automated Code Review
|
||||
|
||||
**Reviews:**
|
||||
- ✅ Correctness (logic errors, edge cases)
|
||||
- ✅ Security (vulnerabilities, input validation)
|
||||
- ✅ Architecture (pattern compliance, SOLID principles)
|
||||
- ✅ Performance (inefficiencies, optimization opportunities)
|
||||
- ✅ Testing (coverage gaps, test quality)
|
||||
- ✅ Code Quality (readability, maintainability)
|
||||
|
||||
**Actions if issues found:**
|
||||
- Adds review findings as tasks
|
||||
- Loops back to implementation
|
||||
- Continues until issues resolved
|
||||
|
||||
## Usage
|
||||
|
||||
### Basic Usage
|
||||
|
||||
```bash
|
||||
# Load any BMAD agent
|
||||
/super-dev-story
|
||||
|
||||
# Follows same flow as dev-story, with extra validation
|
||||
```
|
||||
|
||||
### Specify Story
|
||||
|
||||
```bash
|
||||
/super-dev-story docs/sprint-artifacts/1-2-auth.md
|
||||
```
|
||||
|
||||
### Expected Flow
|
||||
|
||||
```
|
||||
1. Pre-dev gap analysis
|
||||
├─ "Approve task updates? [Y/A/n/e/s/r]"
|
||||
└─ Select option
|
||||
|
||||
2. Development (standard TDD cycle)
|
||||
└─ Implements all tasks
|
||||
|
||||
3. Post-dev gap analysis
|
||||
├─ Scans codebase
|
||||
├─ If gaps: adds tasks, loops back
|
||||
└─ If clean: proceeds
|
||||
|
||||
4. Code review
|
||||
├─ Analyzes all changes
|
||||
├─ If issues: adds tasks, loops back
|
||||
└─ If clean: proceeds
|
||||
|
||||
5. Story marked "review"
|
||||
└─ Truly complete!
|
||||
```
|
||||
|
||||
## Fix Iteration Safety
|
||||
|
||||
Super-dev has a **max iteration limit** (default: 3) to prevent infinite loops:
|
||||
|
||||
```yaml
|
||||
# workflow.yaml
|
||||
super_dev_settings:
|
||||
max_fix_iterations: 3 # Stop after 3 fix cycles
|
||||
fail_on_critical_issues: true # HALT if critical security issues
|
||||
```
|
||||
|
||||
If exceeded:
|
||||
```
|
||||
🛑 Maximum Fix Iterations Reached
|
||||
|
||||
Attempted 3 fix cycles.
|
||||
Manual intervention required.
|
||||
|
||||
Issues remaining:
|
||||
- [List of unresolved issues]
|
||||
```
|
||||
|
||||
## Examples
|
||||
|
||||
### Example 1: Perfect First Try
|
||||
|
||||
```
|
||||
/super-dev-story
|
||||
|
||||
Pre-gap: ✅ Tasks accurate
|
||||
Development: ✅ 8 tasks completed
|
||||
Post-gap: ✅ All work verified
|
||||
Code review: ✅ No issues
|
||||
|
||||
→ Story complete! (45 minutes, 85K tokens)
|
||||
```
|
||||
|
||||
### Example 2: Post-Dev Catches Incomplete Work
|
||||
|
||||
```
|
||||
/super-dev-story
|
||||
|
||||
Pre-gap: ✅ Tasks accurate
|
||||
Development: ✅ 8 tasks completed
|
||||
Post-gap: ⚠️ Tests claim 90% coverage, actual 65%
|
||||
|
||||
→ Adds task: "Increase test coverage to 90%"
|
||||
→ Implements missing tests
|
||||
→ Post-gap: ✅ Now 92% coverage
|
||||
→ Code review: ✅ No issues
|
||||
|
||||
→ Story complete! (52 minutes, 95K tokens)
|
||||
```
|
||||
|
||||
### Example 3: Code Review Finds Security Issue
|
||||
|
||||
```
|
||||
/super-dev-story
|
||||
|
||||
Pre-gap: ✅ Tasks accurate
|
||||
Development: ✅ 10 tasks completed
|
||||
Post-gap: ✅ All work verified
|
||||
Code review: 🚨 CRITICAL - SQL injection vulnerability
|
||||
|
||||
→ Adds task: "Fix SQL injection in user search"
|
||||
→ Implements parameterized queries
|
||||
→ Post-gap: ✅ Verified
|
||||
→ Code review: ✅ Security issue resolved
|
||||
|
||||
→ Story complete! (58 minutes, 110K tokens)
|
||||
```
|
||||
|
||||
## Comparison to Standard Workflow
|
||||
|
||||
### Standard Flow (dev-story)
|
||||
|
||||
```
|
||||
Day 1: Develop story (30 min)
|
||||
Day 2: Human review finds 3 issues
|
||||
Day 3: Fix issues (20 min)
|
||||
Day 4: Human review again
|
||||
Day 5: Approved
|
||||
|
||||
Total: 5 days, 2 review cycles
|
||||
```
|
||||
|
||||
### Super-Dev Flow
|
||||
|
||||
```
|
||||
Day 1: Super-dev-story
|
||||
- Development (30 min)
|
||||
- Post-gap finds 1 issue (auto-fix 5 min)
|
||||
- Code review finds 2 issues (auto-fix 15 min)
|
||||
- Complete (50 min total)
|
||||
|
||||
Day 2: Human review
|
||||
Day 3: Approved (minimal/no changes needed)
|
||||
|
||||
Total: 3 days, 1 review cycle
|
||||
```
|
||||
|
||||
**Savings:** 2 days, 1 fewer review cycle, higher initial quality
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### "Super-dev keeps looping forever"
|
||||
|
||||
**Cause:** Each validation finds new issues
|
||||
**Solution:** This indicates quality problems. Review max_fix_iterations setting or manually intervene.
|
||||
|
||||
### "Post-dev gap analysis keeps failing"
|
||||
|
||||
**Cause:** Dev agent marking tasks complete prematurely
|
||||
**Solution:** This is expected! Super-dev catches this. The loop ensures actual completion.
|
||||
|
||||
### "Code review too strict"
|
||||
|
||||
**Cause:** Reviewing for issues standard dev-story would miss
|
||||
**Solution:** This is intentional. For less strict review, use standard dev-story.
|
||||
|
||||
### "Too many tokens/too slow"
|
||||
|
||||
**Cause:** Multi-stage validation adds overhead
|
||||
**Solution:** Use standard dev-story for non-critical stories. Reserve super-dev for important work.
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **Reserve for important stories** - Don't use for trivial changes
|
||||
2. **Trust the process** - Fix iterations mean it's working correctly
|
||||
3. **Review limits** - Adjust max_fix_iterations if stories are complex
|
||||
4. **Monitor costs** - Track token usage vs review cycle savings
|
||||
5. **Learn patterns** - Code review findings inform future architecture
|
||||
|
||||
## Configuration Reference
|
||||
|
||||
```yaml
|
||||
# _bmad/bmm/config.yaml or _bmad/bmgd/config.yaml
|
||||
|
||||
# Per-project settings
|
||||
super_dev_settings:
|
||||
post_dev_gap_analysis: true # Enable post-dev validation
|
||||
auto_code_review: true # Enable automatic code review
|
||||
fail_on_critical_issues: true # HALT on security vulnerabilities
|
||||
max_fix_iterations: 3 # Maximum fix cycles before manual intervention
|
||||
auto_fix_minor_issues: false # Auto-fix LOW severity without asking
|
||||
```
|
||||
|
||||
## See Also
|
||||
|
||||
- [dev-story workflow](../dev-story/) - Standard development workflow
|
||||
- [gap-analysis workflow](../gap-analysis/) - Standalone audit tool
|
||||
- [Gap Analysis Guide](../../../../docs/gap-analysis.md) - Complete documentation
|
||||
- [Super-Dev Mode Concept](../../../../docs/super-dev-mode.md) - Vision and roadmap
|
||||
|
||||
---
|
||||
|
||||
**Super-Dev-Story: Because "done" should mean DONE** ✅
|
||||
|
|
@ -0,0 +1,370 @@
|
|||
<workflow>
|
||||
<critical>The workflow execution engine is governed by: {project-root}/_bmad/core/tasks/workflow.xml</critical>
|
||||
<critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
|
||||
<critical>Communicate all responses in {communication_language} and language MUST be tailored to {user_skill_level}</critical>
|
||||
<critical>Generate all documents in {document_output_language}</critical>
|
||||
<critical>🚀 SUPER-DEV MODE: Enhanced quality workflow with post-implementation validation and automated code review</critical>
|
||||
<critical>This workflow ensures stories are TRULY complete through multi-stage validation before marking done</critical>
|
||||
<critical>⚙️ EXECUTION FLOW: First execute ALL dev-story steps (1-8), then continue with super-dev enhancements (9.5-9.6)</critical>
|
||||
|
||||
<!-- ═══════════════════════════════════════════════════════════════ -->
|
||||
<!-- STEPS 1-8: STANDARD DEV-STORY WORKFLOW -->
|
||||
<!-- ═══════════════════════════════════════════════════════════════ -->
|
||||
|
||||
<critical>🎯 EXECUTE DEV-STORY STEPS 1-8 FIRST</critical>
|
||||
<critical>Follow all instructions in: {project-root}/_bmad/bmm/workflows/4-implementation/dev-story/instructions.xml</critical>
|
||||
<critical>Complete Steps 1 through 8 exactly as specified in dev-story workflow</critical>
|
||||
<critical>After Step 8 completes (all tasks checked), return here and continue with Step 9.5 below</critical>
|
||||
|
||||
<note>⚙️ Super-dev-story includes ALL standard dev-story steps (1-8):
|
||||
|
||||
**Standard Development Flow:**
|
||||
- Step 1: Find and load story (sprint-status or user-provided path)
|
||||
- Step 1.5: ✅ PRE-DEV GAP ANALYSIS - Validate tasks against codebase
|
||||
- Step 2: Load project context and story information
|
||||
- Step 3: Detect review continuation (if resuming after code-review)
|
||||
- Step 4: Mark story in-progress in sprint-status
|
||||
- Step 5: Implement task following red-green-refactor cycle (TDD)
|
||||
- Step 6: Author comprehensive tests (unit, integration, e2e)
|
||||
- Step 7: Run validations and tests (regression suite)
|
||||
- Step 8: Validate and mark task complete (strict gates)
|
||||
|
||||
After completing Steps 1-8, super-dev mode adds ADDITIONAL quality validation below.
|
||||
|
||||
**For complete details of Steps 1-8, see:** {project-root}/_bmad/bmm/workflows/4-implementation/dev-story/instructions.xml
|
||||
</note>
|
||||
|
||||
<!-- ═══════════════════════════════════════════════════════════════ -->
|
||||
<!-- SUPER-DEV ENHANCEMENTS: POST-IMPLEMENTATION VALIDATION -->
|
||||
<!-- ═══════════════════════════════════════════════════════════════ -->
|
||||
|
||||
<!-- SUPER-DEV ENHANCEMENTS START HERE -->
|
||||
|
||||
<step n="9.5" goal="Post-development gap analysis">
|
||||
<critical>🔍 POST-DEV VALIDATION - Verify all work actually completed!</critical>
|
||||
<note>This catches incomplete implementations that were prematurely marked done</note>
|
||||
|
||||
<output>
|
||||
🔎 **Post-Development Gap Analysis**
|
||||
|
||||
All tasks marked complete. Verifying against codebase reality...
|
||||
</output>
|
||||
|
||||
<!-- Re-scan codebase with fresh eyes -->
|
||||
<action>Re-read story requirements and acceptance criteria</action>
|
||||
<action>Extract all tasks and subtasks that are marked [x] complete</action>
|
||||
<action>For each completed task, identify what should exist in codebase</action>
|
||||
|
||||
<!-- SCAN PHASE -->
|
||||
<action>Use Glob to find files that should have been created</action>
|
||||
<action>Use Grep to search for functions/classes that should exist</action>
|
||||
<action>Use Read to verify implementation completeness (not just existence)</action>
|
||||
<action>Run tests to verify claimed test coverage actually exists and passes</action>
|
||||
|
||||
<!-- ANALYSIS PHASE -->
|
||||
<action>Compare claimed work vs actual implementation:</action>
|
||||
|
||||
**POST-DEV VERIFICATION:**
|
||||
<action>✅ Verified Complete:
|
||||
- List tasks where code fully exists and works
|
||||
- Confirm tests exist and pass
|
||||
- Verify implementation matches requirements
|
||||
</action>
|
||||
|
||||
<action>❌ False Positives Detected:
|
||||
- List tasks marked [x] but code missing or incomplete
|
||||
- Identify claimed tests that don't exist or fail
|
||||
- Note partial implementations marked as complete
|
||||
</action>
|
||||
|
||||
<action>⚠️ Quality Issues:
|
||||
- Implementations that exist but don't meet requirements
|
||||
- Tests that exist but have poor coverage
|
||||
- Code that works but violates architecture patterns
|
||||
</action>
|
||||
|
||||
<!-- DECISION PHASE -->
|
||||
<check if="false positives found OR quality issues found">
|
||||
<output>
|
||||
⚠️ **Post-Dev Gaps Detected!**
|
||||
|
||||
**False Positives (marked done but not complete):**
|
||||
{{list_false_positives_with_details}}
|
||||
|
||||
**Quality Issues:**
|
||||
{{list_quality_issues_with_details}}
|
||||
|
||||
**Proposed Actions:**
|
||||
{{list_tasks_to_add_for_missing_work}}
|
||||
|
||||
---
|
||||
|
||||
These issues must be addressed before story can be marked complete.
|
||||
</output>
|
||||
|
||||
<action>Uncheck false positive tasks in story file</action>
|
||||
<action>Add new tasks for missing work to Tasks/Subtasks section</action>
|
||||
<action>Add note to Dev Agent Record: "Post-dev gap analysis found incomplete work - continuing implementation"</action>
|
||||
<action>Update Gap Analysis section with post-dev findings</action>
|
||||
<action>Set {{fix_iteration_count}} = {{fix_iteration_count}} + 1</action>
|
||||
|
||||
<check if="{{fix_iteration_count}} > {{max_fix_iterations}}">
|
||||
<output>🛑 **Maximum Fix Iterations Reached**
|
||||
|
||||
Attempted {{fix_iteration_count}} fix cycles.
|
||||
Manual intervention required.
|
||||
|
||||
Issues remaining:
|
||||
{{list_remaining_issues}}
|
||||
</output>
|
||||
<action>Add to Dev Agent Record: "HALTED - exceeded max fix iterations, manual review needed"</action>
|
||||
<action>HALT - require user intervention</action>
|
||||
</check>
|
||||
|
||||
<output>🔄 Adding missing work to task list and continuing implementation...</output>
|
||||
<goto step="5">Continue implementation with added tasks</goto>
|
||||
</check>
|
||||
|
||||
<check if="no gaps found">
|
||||
<output>✅ **Post-Dev Validation Passed**
|
||||
|
||||
All tasks verified complete against codebase.
|
||||
Proceeding to code review...
|
||||
</output>
|
||||
<action>Update Gap Analysis section with post-dev verification results</action>
|
||||
<action>Continue to Step 9.6</action>
|
||||
</check>
|
||||
</step>
|
||||
|
||||
<step n="9.6" goal="Automated code review">
|
||||
<critical>👀 AUTO CODE REVIEW - Independent quality validation</critical>
|
||||
<note>Fresh perspective catches issues the dev agent might miss</note>
|
||||
|
||||
<output>
|
||||
🔍 **Running Automated Code Review**
|
||||
|
||||
Analyzing implementation for issues...
|
||||
</output>
|
||||
|
||||
<!-- Identify files to review -->
|
||||
<action>Extract File List from Dev Agent Record</action>
|
||||
<action>Identify all files created or modified during implementation</action>
|
||||
|
||||
<!-- REVIEW PHASE: Use code-review workflow logic -->
|
||||
<action>Perform comprehensive code review checking:</action>
|
||||
<action>- **Correctness:** Logic errors, edge cases, error handling</action>
|
||||
<action>- **Architecture:** Compliance with patterns and standards</action>
|
||||
<action>- **Security:** Vulnerabilities, input validation, authentication</action>
|
||||
<action>- **Performance:** Inefficiencies, N+1 queries, memory leaks</action>
|
||||
<action>- **Testing:** Test coverage, edge cases, test quality</action>
|
||||
<action>- **Code Quality:** Readability, maintainability, documentation</action>
|
||||
|
||||
<!-- CATEGORIZE FINDINGS -->
|
||||
<action>Categorize all findings by severity:</action>
|
||||
<action>- CRITICAL: Security vulnerabilities, data loss, broken functionality</action>
|
||||
<action>- HIGH: Logic errors, missing error handling, test gaps</action>
|
||||
<action>- MEDIUM: Code quality issues, minor bugs, performance concerns</action>
|
||||
<action>- LOW: Style issues, documentation improvements, minor refactoring</action>
|
||||
|
||||
<!-- DECISION PHASE -->
|
||||
<check if="CRITICAL or HIGH severity issues found">
|
||||
<output>
|
||||
🚨 **Code Review Found Issues Requiring Fixes**
|
||||
|
||||
**Critical Issues ({{critical_count}}):**
|
||||
{{list_critical_issues}}
|
||||
|
||||
**High Priority Issues ({{high_count}}):**
|
||||
{{list_high_issues}}
|
||||
|
||||
{{if_medium_or_low_exist}}
|
||||
**Medium/Low Issues ({{med_low_count}}):**
|
||||
{{list_medium_low_issues}}
|
||||
{{endif}}
|
||||
|
||||
---
|
||||
|
||||
**These issues must be fixed before story completion.**
|
||||
</output>
|
||||
|
||||
<action>Add "Code Review Findings" section to story file</action>
|
||||
<action>Add review findings as new tasks in Tasks/Subtasks with [AI-Review] prefix</action>
|
||||
<action>Add to Dev Agent Record: "Code review found {{total_issue_count}} issues - continuing with fixes"</action>
|
||||
<action>Set {{fix_iteration_count}} = {{fix_iteration_count}} + 1</action>
|
||||
|
||||
<check if="{{fix_iteration_count}} > {{max_fix_iterations}}">
|
||||
<output>🛑 **Maximum Fix Iterations Reached**
|
||||
|
||||
Code review found issues on iteration {{fix_iteration_count}}.
|
||||
Manual review recommended.
|
||||
|
||||
Issues found:
|
||||
{{list_all_issues}}
|
||||
</output>
|
||||
<action>Add to Dev Agent Record: "HALTED - code review issues after max iterations, manual review needed"</action>
|
||||
<action>HALT - require user intervention</action>
|
||||
</check>
|
||||
|
||||
<output>🔧 Adding review findings to task list and implementing fixes...</output>
|
||||
<goto step="5">Implement fixes</goto>
|
||||
</check>
|
||||
|
||||
<check if="only MEDIUM or LOW severity issues found">
|
||||
<output>
|
||||
ℹ️ **Code Review Found Minor Issues**
|
||||
|
||||
**Medium Issues ({{medium_count}}):**
|
||||
{{list_medium_issues}}
|
||||
|
||||
**Low Priority Issues ({{low_count}}):**
|
||||
{{list_low_issues}}
|
||||
|
||||
---
|
||||
</output>
|
||||
|
||||
<ask>Auto-fix these minor issues?
|
||||
|
||||
Options:
|
||||
[Y] Yes - Add to task list and fix now
|
||||
[n] No - Document in story but don't fix (can address later)
|
||||
[s] Skip - Ignore these findings
|
||||
</ask>
|
||||
|
||||
<check if="user approves Y">
|
||||
<action>Add review findings as tasks with [AI-Review] prefix</action>
|
||||
<action>Add to Dev Agent Record: "Addressing {{issue_count}} minor code review findings"</action>
|
||||
<output>🔧 Implementing minor fixes...</output>
|
||||
<goto step="5">Implement fixes</goto>
|
||||
</check>
|
||||
|
||||
<check if="user says n">
|
||||
<action>Add "Code Review Findings" section documenting issues</action>
|
||||
<action>Add to Dev Agent Record: "Code review found {{issue_count}} minor issues - documented for future work"</action>
|
||||
<output>ℹ️ Issues documented in story. Proceeding to completion...</output>
|
||||
<action>Continue to Step 9</action>
|
||||
</check>
|
||||
|
||||
<check if="user says s">
|
||||
<output>⚠️ Skipping minor issues. Proceeding to completion...</output>
|
||||
<action>Continue to Step 9</action>
|
||||
</check>
|
||||
</check>
|
||||
|
||||
<check if="no issues found">
|
||||
<output>✅ **Code Review Passed**
|
||||
|
||||
No issues found. Implementation meets quality standards.
|
||||
</output>
|
||||
<action>Add to Dev Agent Record: "Code review completed - no issues found"</action>
|
||||
<action>Continue to Step 9</action>
|
||||
</check>
|
||||
</step>
|
||||
|
||||
<step n="9" goal="Story completion and mark for review" tag="sprint-status">
|
||||
<critical>🎯 FINAL VALIDATION - All quality gates must pass!</critical>
|
||||
|
||||
<action>Verify ALL tasks and subtasks are marked [x] (re-scan the story document now)</action>
|
||||
<action>Run the full regression suite (do not skip)</action>
|
||||
<action>Confirm File List includes every changed file</action>
|
||||
<action>Execute enhanced definition-of-done validation</action>
|
||||
|
||||
<!-- Enhanced Definition of Done for Super-Dev -->
|
||||
<action>Validate super-dev quality gates:
|
||||
- ✅ Pre-dev gap analysis completed and approved
|
||||
- ✅ All tasks/subtasks marked complete with [x]
|
||||
- ✅ Implementation satisfies every Acceptance Criterion
|
||||
- ✅ All tests pass (no regressions, new tests successful)
|
||||
- ✅ Post-dev gap analysis passed (no false positives)
|
||||
- ✅ Code review completed (critical/high issues resolved)
|
||||
- ✅ File List includes every new/modified/deleted file
|
||||
- ✅ Dev Agent Record contains implementation notes
|
||||
- ✅ Change Log includes summary of changes
|
||||
</action>
|
||||
|
||||
<action>Update the story Status to: "review"</action>
|
||||
|
||||
<!-- Mark story ready for review - sprint status conditional -->
|
||||
<check if="{sprint_status} file exists AND {{current_sprint_status}} != 'no-sprint-tracking'">
|
||||
<action>Load the FULL file: {sprint_status}</action>
|
||||
<action>Find development_status key matching {{story_key}}</action>
|
||||
<action>Verify current status is "in-progress" (expected previous state)</action>
|
||||
<action>Update development_status[{{story_key}}] = "review"</action>
|
||||
<action>Save file, preserving ALL comments and structure including STATUS DEFINITIONS</action>
|
||||
<output>✅ Story status updated to "review" in sprint-status.yaml</output>
|
||||
</check>
|
||||
|
||||
<check if="{sprint_status} file does NOT exist OR {{current_sprint_status}} == 'no-sprint-tracking'">
|
||||
<output>ℹ️ Story status updated to "review" in story file (no sprint tracking configured)</output>
|
||||
</check>
|
||||
|
||||
<!-- Final validation gates -->
|
||||
<action if="any task is incomplete">HALT - Complete remaining tasks before marking ready for review</action>
|
||||
<action if="regression failures exist">HALT - Fix regression issues before completing</action>
|
||||
<action if="File List is incomplete">HALT - Update File List with all changed files</action>
|
||||
<action if="post-dev gap analysis not completed">HALT - Run post-dev validation before completing</action>
|
||||
<action if="code review not completed">HALT - Run code review before completing</action>
|
||||
</step>
|
||||
|
||||
<step n="10" goal="Super-dev completion communication">
|
||||
<action>Prepare comprehensive summary in Dev Agent Record → Completion Notes</action>
|
||||
|
||||
<output>🎉 **SUPER-DEV STORY COMPLETE, {user_name}!**
|
||||
|
||||
**Story:** {{story_key}} - {{story_title}}
|
||||
**Status:** review (ready for human review)
|
||||
|
||||
---
|
||||
|
||||
**Quality Gates Passed:**
|
||||
✅ Pre-dev gap analysis - Tasks validated before work started
|
||||
✅ Development - All tasks completed with TDD
|
||||
✅ Post-dev gap analysis - Implementation verified complete
|
||||
✅ Code review - {{total_issues_found}} issues found and resolved
|
||||
✅ All tests passing - No regressions
|
||||
|
||||
**Implementation Summary:**
|
||||
- Files changed: {{file_count}}
|
||||
- Tests added: {{test_count}}
|
||||
- Issues fixed: {{review_issues_fixed}}
|
||||
- Fix iterations: {{fix_iteration_count}}/{{max_fix_iterations}}
|
||||
|
||||
**Story File:** {{story_file}}
|
||||
|
||||
---
|
||||
|
||||
**What Super-Dev Validated:**
|
||||
1. 🔍 Tasks matched codebase reality before starting
|
||||
2. 💻 Implementation completed per requirements
|
||||
3. ✅ No false positive completions (all work verified)
|
||||
4. 👀 Code quality and security validated
|
||||
5. 🧪 Comprehensive test coverage achieved
|
||||
|
||||
**Next Steps:**
|
||||
- Review the completed story
|
||||
- Verify business requirements met
|
||||
- Merge when approved
|
||||
|
||||
**Note:** This story went through enhanced quality validation.
|
||||
It should require minimal human review.
|
||||
</output>
|
||||
|
||||
<action>Based on {user_skill_level}, ask if user needs any explanations about:
|
||||
- What was implemented and how it works
|
||||
- Why certain technical decisions were made
|
||||
- Gap analysis or code review findings
|
||||
- Any patterns, libraries, or approaches used
|
||||
</action>
|
||||
|
||||
<check if="user asks for explanations">
|
||||
<action>Provide clear, contextual explanations tailored to {user_skill_level}</action>
|
||||
<action>Use examples and references to specific code when helpful</action>
|
||||
</check>
|
||||
|
||||
<output>💡 **Tip:** This story was developed with super-dev-story for enhanced quality.
|
||||
|
||||
For faster development (fewer validations), use standard `dev-story` workflow.
|
||||
For maximum quality and fewer review cycles, continue using `super-dev-story`.
|
||||
</output>
|
||||
</step>
|
||||
|
||||
</workflow>
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
name: super-dev-story
|
||||
description: "Enhanced story development with post-implementation validation and automated code review - ensures stories are truly complete before marking done"
|
||||
author: "BMad"
|
||||
|
||||
# Critical variables from config
|
||||
config_source: "{project-root}/_bmad/bmm/config.yaml"
|
||||
output_folder: "{config_source}:output_folder"
|
||||
user_name: "{config_source}:user_name"
|
||||
communication_language: "{config_source}:communication_language"
|
||||
user_skill_level: "{config_source}:user_skill_level"
|
||||
document_output_language: "{config_source}:document_output_language"
|
||||
story_dir: "{config_source}:implementation_artifacts"
|
||||
date: system-generated
|
||||
|
||||
# Workflow components
|
||||
installed_path: "{project-root}/_bmad/bmm/workflows/4-implementation/super-dev-story"
|
||||
instructions: "{installed_path}/instructions.xml"
|
||||
validation: "{installed_path}/checklist.md"
|
||||
|
||||
story_file: "" # Explicit story path; auto-discovered if empty
|
||||
implementation_artifacts: "{config_source}:implementation_artifacts"
|
||||
sprint_status: "{implementation_artifacts}/sprint-status.yaml"
|
||||
project_context: "**/project-context.md"
|
||||
|
||||
# Super-dev specific settings
|
||||
super_dev_settings:
|
||||
post_dev_gap_analysis: true
|
||||
auto_code_review: true
|
||||
fail_on_critical_issues: true
|
||||
max_fix_iterations: 3
|
||||
|
||||
standalone: true
|
||||
|
||||
web_bundle: false
|
||||
Loading…
Reference in New Issue