Modularity Reviewer — Data & AI agent for Claude Code
Inferential modularity review grounded in the deterministic coupling data.
How to install Modularity Reviewer
Installs to ~/.claude/agents/cwijayasundara-claude_harness_eng_v5-modularity-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/cwijayasundara/claude_harness_eng_v5/HEAD/.claude/agents/modularity-reviewer.md -o ~/.claude/agents/cwijayasundara-claude_harness_eng_v5-modularity-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Modularity Reviewer does
name: modularity-reviewer description: Inferential modularity review grounded in the deterministic coupling data. Reads specs/brownfield/modularity-pack.md (hubs, cycles, duplication candidates) and judges each against the source — semantic duplication, misplaced responsibility, argument clumps, and whether a high-fan-in module is a real god module or a legitimate factory/schema. Use in /brownfield --full, or periodically as a slow-cadence maintainability sensor. model: claude-opus-5 tools:
Alternatives in Data & AI
- Reverse SQL Analyst — Spécialiste des PROCÉDURES STOCKÉES du reverse base de données (rung 1) — et des packages Oracle (1 package = 193 ★
- Geo AI Scorer — Use only for an explicitly requested experimental content-quality review alongside the deterministic geoptimiz 81 ★
- AI Image Director — Desk Studio's AI Image Director 41 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Slop Investigator
Deep-dive investigator for "AI slop" in one specific area of a codebase. Reads project conventions (CLAUDE.md,
Logo Critic
Blind, independent scorer for logo candidates, especially AI-generated ones. Use after any generation round or
Screenshot Critic
Independent design critic that judges a UI from screenshots only, never code, history, or rationale. Returns t
Classify Memory
Step agent that classifies each chunk in the chunk manifest against the data class index. Reads specs/data-cla
Ce CLI Agent Readiness Reviewer
Reviews CLI source code, plans, or specs for AI agent readiness using a severity-based rubric focused on wheth
Ingest Discovery Scanner
LLM leg of the discovery scan in the 9-pass ingestion protocol. Reads one converted source in full and adds to
Related Skills
Evaluate Mmi Cmd
MMI評価エージェント - Modularity Maturity Indexによるモジュール成熟度評価(Cohesion/Coupling/Independence/Reusability)。
Hef.Baseline
Reverse-engineer specs from existing code for brownfield projects
Sdd Baseline.Prompt
Seed openspec/specs/ with baseline specs of existing behavior (brownfield repos, resumable batches).