analyze_codebase_health
Analyze codebase health by detecting code clones, dead symbols, god files, architecture violations, and naming issues. Get a health score, grade, and actionable recommendations.
Instructions
Analyze the health of the ingested codebase.
Runs 5 analysis passes over all fragments in the current session:
Clone Detection — SimHash pairwise scan for Type-1/2/3 code clones
Dead Symbol Analysis — defined but never referenced symbols
God File Detection — files with > μ+2σ reverse dependencies
Architecture Violation Detection — cross-layer imports
Naming Convention Analysis — Python/Rust/React convention breaks
Returns a JSON HealthReport with: - code_health_score [0–100] and health_grade (A/B/C/D/F) - Per-dimension scores: duplication, dead_code, coupling, arch, naming - clone_pairs, dead_symbols, god_files, arch_violations, naming_issues - summary (human-readable) and top_recommendation (most impactful action)
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |