frogger: Command for Claude Code

.claude/commands/refactor-audit.md

refactor-audit is a command for Claude Code from ultra-ai-dle/frogger. It costs 0 tokens per session (1,024 once invoked), scanned A, original, MIT.

A refactoring check that verifies exported types, function signatures, API data, worker messages, and component inputs still agree after changes. An exported interface is a type or function shape that other parts of the program can use.

In plain words
What is it for?
Use it before or after refactoring to inspect shared types, store state, API request and response shapes, worker messages, or visualization component inputs.
Why use it?
A small interface change can break code several layers away, such as a store, API, background worker, or visualization. This check traces those connections and looks for incompatibilities.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is ultra-ai-dle/frogger's own configuration. It tells Claude Code how to work on frogger itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything frogger configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ultra-ai-dle/frogger. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ultra-ai-dle/frogger/develop/.claude/commands/refactor-audit.md
Clone the repo
git clone --depth 1 https://github.com/ultra-ai-dle/frogger

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for refactor-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/ultra-ai-dle/frogger/refactor-audit/github.svg)](https://agentmods.dev/commands/ultra-ai-dle/frogger/refactor-audit)
Your own site
<a href="https://agentmods.dev/commands/ultra-ai-dle/frogger/refactor-audit"><img src="https://agentmods.dev/badge/commands/ultra-ai-dle/frogger/refactor-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for refactor-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/ultra-ai-dle/frogger/refactor-audit"><img src="https://agentmods.dev/badge/commands/ultra-ai-dle/frogger/refactor-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01024
Opus 5.5 $0.00000 $0.00410
Sonnet 5.5 $0.00000 $0.00205
Haiku 4.5 $0.00000 $0.00102

Measured 27d ago against content hash 1aac1b4c1a1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refactor-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 27d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/refactor-audit.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/refactor-audit — Export 타입/시그니처 호환성 검증

목적

리팩토링 전후로 public interface(export된 타입, 함수 시그니처)가 깨지지 않았는지 검증한다. src/types/prova.ts 타입이 Store → API → Worker → Visualization 전체를 관통하므로, 한 곳의 변경이 연쇄적으로 영향을 미치는지 추적한다.

입력

  • $ARGUMENTS — (선택) 검사 범위 지정 (예: types, store, api, worker, viz). 미지정 시 전체 검사.

실행 절차

  1. 변경 파일 식별: git diff main...HEAD --name-only로 변경된 파일 목록을 수집한다.

  2. 타입 경계 추적 (types):

    • src/types/prova.ts에서 export된 타입/인터페이스 목록을 추출한다.
    • 각 타입을 import하는 파일을 grep으로 찾아 의존성 그래프를 만든다.
    • 변경된 타입이 있으면, 해당 타입을 사용하는 모든 파일이 여전히 호환되는지 확인한다.
  3. Store 인터페이스 (store):

    • src/store/useProvaStore.ts의 export된 상태/액션 시그니처를 확인한다.
    • 제거되거나 변경된 상태 필드가 있으면, 이를 참조하는 컴포넌트를 추적한다.
  4. API 라우트 계약 (api):

    • /api/analyze, /api/java/execute의 request body 파싱 + response 구조를 확인한다.
    • 클라이언트에서 호출하는 코드의 기대 구조와 일치하는지 크로스체크한다.
  5. Worker 메시지 포맷 (worker):

    • Worker의 postMessage 페이로드 구조가 메인 스레드의 onmessage 핸들러 기대와 일치하는지 확인한다.
    • WorkerDonePayload 타입과 실제 Worker 코드의 정합성을 검증한다.
  6. 시각화 컴포넌트 props (viz):

    • GraphPanel, GridLinearPanel, ThreeDVolumePanel이 받는 props/store 데이터가 변경된 타입과 호환되는지 확인한다.
  7. 후처리 보강 모듈 (lib):

    • src/lib/ 아래 enrichment 함수들이 prova.ts 타입에 의존하므로 호환성을 확인한다.
    • 대상: partitionPivotEnrichment.ts, tagNormalize.ts, graphModeInference.ts
    • 특히 AnalyzeMetadata, LinearPivotSpec, SpecialVarKind 등의 필드명/enum 변경 시 영향 추적.
  8. AI 프롬프트 ↔ 타입 동기화 (prompt):

    • app/api/analyze/route.ts 내 프롬프트 문자열이 타입 필드명을 하드코딩하고 있다.
    • 타입 필드명이 변경되면 프롬프트도 함께 수정해야 한다.
    • Gemini structured output 스키마(route.ts 내 JSON schema)도 prova.ts 타입과 일치해야 한다.
    • 프롬프트 변경이 감지되면 /prompt-diff 실행을 권고한다.
  9. 빌드 검증: npx tsc --noEmit으로 타입 에러가 없는지 확인한다.

  10. 결과 보고:

    • 경계별 호환성 상태를 표로 출력한다.
    • 깨진 경계가 있으면 어떤 파일의 어떤 라인이 문제인지 구체적으로 보고한다.

의존성 경계 맵

prova.ts (타입 정의)
  ├── useProvaStore.ts (Store — 상태 + 액션)
  │     ├── page.tsx (메인 페이지)
  │     ├── GraphPanel.tsx
  │     ├── GridLinearPanel.tsx
  │     └── TimelineControls.tsx
  ├── /api/analyze/route.ts (AI 분류 + Gemini 스키마 + 프롬프트 필드명)
  ├── /api/java/execute/route.ts (Java 원격 실행 ���록시)
  ├── src/lib/ (enrichment 모듈)
  │     ├── partitionPivotEnrichment.ts
  │     ├── tagNormalize.ts
  │     └── graphModeInference.ts
  ├── merge.ts (trace 병합)
  ├── runtime.ts (실행 런타임)
  └── Worker files (pyodide.worker.js, js.worker.js) — tsc 범위 밖, 수동 확인 필요

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 27d ago First seen · 69 lines · 0 tokens per session scan A 1aac1b4c1a1d

Subscribe to this mod's changes

refactor-audit is a command published in the GitHub repository ultra-ai-dle/frogger (8 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,024 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.