원클릭으로
reality
Codebase analysis and architecture validation - what's actually there vs documented
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Codebase analysis and architecture validation - what's actually there vs documented
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Quality bug fixes (P1/P2). Full TDD cycle, branch from master via feature/, no production deploy.
Execute ONE executable leaf workstream with TDD, guard enforcement, and ws-verdict output
Deployment orchestration. Creates PR to master (after @oneshot) or merges for release.
System design with progressive disclosure, produces workstream files
Feature planning orchestrator (discovery -> idea -> ux -> design -> workstream tree)
Emergency P0 fixes. Fast-track production deployment with minimal changes. Branch from master, immediate deploy.
| name | reality |
| description | Codebase analysis and architecture validation - what's actually there vs documented |
| version | 2.0.0 |
| changes | ["Converted to LLM-agnostic format","Removed tool-specific API references","Focus on WHAT, not HOW to invoke"] |
Analyze what's actually in your codebase (vs. what's documented).
When user invokes @reality:
# Detect language/framework
if [ -f "go.mod" ]; then PROJECT_TYPE="go"
elif [ -f "pyproject.toml" ] || [ -f "requirements.txt" ]; then PROJECT_TYPE="python"
elif [ -f "pom.xml" ] || [ -f "build.gradle" ]; then PROJECT_TYPE="java"
elif [ -f "package.json" ]; then PROJECT_TYPE="nodejs"
else PROJECT_TYPE="unknown"
fi
Analysis:
Output: Health Score X/100 + Top 5 Issues
Spawn 8 parallel expert analyses using Task tool with subagent_type:
Task(subagent_type="general-purpose", prompt="Analyze ARCHITECTURE...")
Task(subagent_type="general-purpose", prompt="Analyze CODE QUALITY...")
Task(subagent_type="general-purpose", prompt="Analyze TESTING...")
Task(subagent_type="general-purpose", prompt="Analyze SECURITY...")
Task(subagent_type="general-purpose", prompt="Analyze PERFORMANCE...")
Task(subagent_type="general-purpose", prompt="Analyze DOCUMENTATION...")
Task(subagent_type="general-purpose", prompt="Analyze TECHNICAL DEBT...")
Task(subagent_type="general-purpose", prompt="Analyze STANDARDS...")
Expert agents:
Create comprehensive report with:
| Mode | Duration | Purpose |
|---|---|---|
@reality --quick | 5-10 min | Health check + top issues |
@reality --deep | 30-60 min | Comprehensive with 8 experts |
@reality --focus=security | Varies | Security expert deep dive |
@reality --focus=architecture | Varies | Architecture expert deep dive |
@reality --focus=testing | Varies | Testing expert deep dive |
@reality --focus=performance | Varies | Performance expert deep dive |
## Reality Check: {project_name}
### Quick Stats
- Language: {detected}
- Size: {LOC} lines, {N} files
- Architecture: {layers detected}
- Tests: {coverage if available}
### Top 5 Issues
1. {issue} - {severity}
- Location: {file:line}
- Impact: {why it matters}
- Fix: {recommendation}
### Health Score: {X}/100
If PRODUCT_VISION.md exists, compare reality to vision with Vision vs Reality Gap analysis:
| Feature | PRD Status | Reality Status | Gap |
|---|---|---|---|
| Feature 1 | P0 | Implemented | None |
| Feature 2 | P1 | Partial | Missing X |
| Feature 3 | P0 | Not found | Not started |
@reality --quick # Quick health check
@reality --deep # Deep analysis
@reality --focus=security # Security only
@reality --deep --output=docs/reality/check.md # Save report
@vision - Strategic planning@feature - Feature planning@idea - Requirements gathering