メニュー
Read-only scan for files ≥1000 LoC and functions/methods ≥150 LoC across image-scoring-backend and image-scoring-gallery. Produces a markdown or JSON report with refactor priority hints. Use when the user asks for a codebase size audit, large file scan, god-module review, or refactoring hotspot analysis.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Bump semver + promote CHANGELOG Unreleased via compiled harness. Use for /release, version bumps, or tagging. Runs scripts/agent_skills/release_bump.py; LLM only when Unreleased is ambiguous. Never commit/push unless the user asks.
Vexlum Scoring MCP — compact search+dispatch on is-be-mcp / is-be-live and gallery is-ui-mcp / is-ui-live.
Choose CLI tools and safe patterns before repo work. Install checklist, bounded search/read commands, and confirmation gates. Use when navigating the codebase, running shell commands, or setting up agent tooling on Windows, WSL2, or macOS.
Inspect JSON, YAML, and API responses with jq, yq, dasel, curl, and httpie. Use for package.json, config.json, and backend health checks. Never output secrets or full credential-bearing config.
Backend build, test, lint, and verify workflows via WSL pytest, ruff, doctor, and docker compose. Use before claiming work complete or opening a PR. Do not invent ad hoc Python commands outside documented venvs.
Choose and run the right search tool: rg vs grep vs ast-grep vs fd vs fzf. Bounded repo navigation with ripgrep, fd, tree, bat, and structural search. Use when finding symbols, files, syntax patterns, or deciding which CLI search to use before reading or editing code.
| name | codebase-size-audit |
| description | Read-only scan for files ≥1000 LoC and functions/methods ≥150 LoC across image-scoring-backend and image-scoring-gallery. Produces a markdown or JSON report with refactor priority hints. Use when the user asks for a codebase size audit, large file scan, god-module review, or refactoring hotspot analysis. |
Read-only. Do not edit production code unless the user explicitly asks to implement refactors after reviewing the report.
| Threshold | Value | Meaning |
|---|---|---|
--file-min | 1000 | Flag whole source files at or above this line count |
--fn-min | 150 | Flag functions/methods at or above this span |
Skips: node_modules, venvs, dist*, __pycache__, FirebirdLinux, static bundles, generated *.generated.ts.
From image-scoring-backend root (Python 3.10+; no venv required):
# Backend only
python scripts/audit/codebase_size_audit.py
# Gallery sibling (adjust path if clones differ)
python scripts/audit/codebase_size_audit.py --root ../image-scoring-gallery
# Save combined workflow — backend then gallery
python scripts/audit/codebase_size_audit.py -o .agent/scratch/audit-backend.md
python scripts/audit/codebase_size_audit.py --root ../image-scoring-gallery -o .agent/scratch/audit-gallery.md
JSON for tooling:
python scripts/audit/codebase_size_audit.py --format json -o .agent/scratch/audit-backend.json
Custom thresholds:
python scripts/audit/codebase_size_audit.py --file-min 800 --fn-min 120
After running the script, present:
# Codebase size audit — YYYY-MM-DD
## Backend (≥1000 LoC files)
| Lines | Path | Notes |
...
## Gallery (≥1000 LoC files)
...
## Top functions (≥150 LoC) — both repos
Top 10–15 by line count with path and symbol.
## Batch 1 status (if re-auditing)
- api.py / mcp_server.py / main.ts — note post-extraction line counts vs prior audit.
## Suggested next extractions (safe-first)
1. …
2. …
Safe extraction (low contract risk):
api_helpers, mcp/tools/*); keep import paths stable.electron/ipc/register*.ts; never rename IPC channel strings or change preload without coordinated PR.Defer (higher risk):
modules/db_legacy.py domain decomposition — schema/connector coupling.create_api_router domain routers — OpenAPI route order and test matrix.electron/db.ts — IPC result shapes tied to renderer.ImageViewer.tsx / AppContent.tsx — extract hooks incrementally with Vitest coverage.Cross-repo: file issues on GitHub Project board before large refactors; cite docs/project/00-backlog-workflow.md.
pytest API + MCP subsets per AGENTS.md.npm run test:run, npx tsc -p electron/tsconfig.json --noEmit.