APAW/.kilo/commands/feature.md

description, mode, model, color, permission

description	mode	model	color	permission
Full feature development pipeline from requirements to release	feature	openrouter/qwen/qwen3-coder:free	#059669	read edit write bash glob grep task allow allow allow allow allow allow * deny

Feature Command

Executes the complete development pipeline for implementing new features, following TDD and quality gates.

Pipeline Flow

Requirements → History → Design → Tests → Implementation → Review → Performance → Security → Release

Workflow

Step 1: Requirements Refinement

Agent: @RequirementRefiner

• Transform vague ideas into strict User Stories
• Define INVEST criteria (Independent, Negotiable, Valuable, Estimable, Small, Testable)
• Document acceptance criteria as checkboxes
• Identify stakeholders and user personas
• Create user story format:

  As a [user type]
  I want [goal]
  So that [benefit]
  

Step 2: History Check

Agent: @HistoryMiner

• Search for duplicate or similar past work
• Query: git log --all --oneline --grep="<feature>"
• Code search: git log -p --all -S "<pattern>"
• Review closed PRs for related work
• Identify reusable solutions
• Document lessons learned from past attempts

Step 3: System Design

Agent: @SystemAnalyst

• Design technical specification
• Create architecture diagram (ASCII or markdown)
• Define data models and schemas
• Specify API contracts
• Identify integration points
• Document security considerations
• Create design document:

  ## Technical Design
  
  ### Architecture
  [Diagram description]
  
  ### Components
  - Component A: [Purpose]
  - Component B: [Purpose]
  
  ### Data Flow
  1. [Step 1]
  2. [Step 2]
  
  ### API Design
  [Endpoints, contracts]
  

Step 4: Test Creation (TDD)

Agent: @SDETEngineer

• Write tests BEFORE implementation
• Create test file near source file
• Cover unit tests:
  • Happy path scenarios
  • Edge cases (empty, null, boundaries)
  • Error conditions
• Create integration tests if needed
• Ensure tests are deterministic and repeatable
• Run tests to confirm they fail (red phase)
• Test structure:

  describe('FeatureName', () => {
    describe('methodName', () => {
      it('should [expected behavior] when [condition]', () => {
        // Arrange
        // Act
        // Assert
      });
    });
  });
  

Step 5: Implementation

Agent: @LeadDeveloper

• Implement minimum code to pass tests
• Follow existing code patterns and conventions
• Use early returns to reduce nesting
• Handle edge cases and errors
• No comments unless explicitly requested
• Check package.json/cargo.toml for dependencies
• Use existing utilities when available
• Run tests frequently (red-green-refactor)
• Commit atomically with clear messages

Step 6: Code Review

Agent: @CodeSkeptic

• Review all changes adversarially
• Check for:
  • Correctness and edge cases
  • Security vulnerabilities (XSS, SQL injection, secrets)
  • Performance issues (N+1 queries, memory leaks)
  • Maintainability (naming, DRY)
• Generate review report:

  ## Code Review Report
  
  ### Critical Issues
  - [Issue]: [File:line] - [Description] - [Suggestion]
  
  ### Warnings
  - [Issue]: [File:line] - [Description]
  
  ### Approved ✓
  - [List approved aspects]
  

• If FAIL: Route to @TheFixer → Return to Step 6
• If PASS: Continue to Step 7

Step 7: Performance Review

Agent: @PerformanceEngineer

• Check for performance bottlenecks
• Analyze time and space complexity
• Review database query efficiency
• Identify unnecessary computations
• Check for proper use of caching
• Suggest optimizations only if needed
• Report format:

  ## Performance Report
  
  ### Queries
  - [Query]: [Complexity] - [Optimization suggestion if needed]
  
  ### Algorithms
  - [Function]: [Time complexity] - [Improvement if critical]
  
  ### Status
  - PASS / FAIL with reasons
  

Step 8: Security Audit

Agent: @SecurityAuditor

• Scan for vulnerabilities:
  • Input validation
  • Authentication/Authorization
  • Data exposure
  • Injection attacks
  • Sensitive data handling
• Check for hardcoded secrets
• Verify proper error handling
• Review dependencies for known CVEs
• Report format:

  ## Security Audit
  
  ### Vulnerabilities Found
  - Severity: [Critical/High/Medium/Low]
  - Type: [Vulnerability type]
  - Location: [File:line]
  - Remediation: [Fix recommendation]
  
  ### Status
  - PASS / FAIL with reasons
  

Step 9: Release Preparation

Agent: @ReleaseManager

• Run linting and type checking
• Verify all tests pass
• Check code coverage thresholds
• Create/update changelog
• Prepare commit messages
• Only commit if user explicitly requests
• Commit message format:

  feat: [brief description of feature]
  
  [Detailed explanation if needed]
  

Quality Gates

Each step must PASS before proceeding:

Gate	Criteria
Requirements	All acceptance criteria defined
History	No duplicate work identified
Design	Technical spec reviewed
Tests	All tests written and failing
Implementation	All tests passing
Review	No critical issues remaining
Performance	No critical bottlenecks
Security	No critical vulnerabilities

Rollback Points

If issues arise, roll back to:

• Design issues → Return to Step 3
• Test failures → Return to Step 5
• Security issues → Return to Step 5
• Performance issues → Evaluate necessity

Final Output

# Feature Complete: [Name]

## Summary
- Requirements: ✓ [Count] criteria defined
- History: ✓ No duplicates found
- Design: ✓ [Document link]
- Tests: ✓ [Count] tests passing
- Implementation: ✓ Complete
- Review: ✓ All issues resolved
- Performance: ✓ Optimized
- Security: ✓ No vulnerabilities

## Files Modified
- [List of all modified files]

## Tests Added
- [List of test files]

## Next Steps
- [Release instructions or follow-up tasks]