Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add msbaek/msbaek-claude-plugins --skill extract-method-objectgit clone --depth 1 https://github.com/msbaek/msbaek-claude-pluginsWrote 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.
[](https://agentmods.dev/skills/msbaek/msbaek-claude-plugins/extract-method-object)<a href="https://agentmods.dev/skills/msbaek/msbaek-claude-plugins/extract-method-object"><img src="https://agentmods.dev/badge/skills/msbaek/msbaek-claude-plugins/extract-method-object/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.
<a href="https://agentmods.dev/skills/msbaek/msbaek-claude-plugins/extract-method-object"><img src="https://agentmods.dev/badge/skills/msbaek/msbaek-claude-plugins/extract-method-object.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.02734 |
| Opus 5.5 | $0.00042 | $0.01094 |
| Sonnet 5.5 | $0.00021 | $0.00547 |
| Haiku 4.5 | $0.00011 | $0.00273 |
Grade A, and why
extract-method-object 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract Method Object Skill
지역 변수가 상호 의존해 Extract Method가 어려운 거대 메서드를 별도 클래스로 추출.
GOAL
- 성공 = 지역 변수가 상호 의존하는 긴 메서드가 Method Object로 추출되어 커밋 완료됨
- 50줄 이상의 복잡한 메서드가 식별됨
- 지역 변수가 메서드 전역에 걸쳐 상호 의존해 Extract Method 불가
- 후보 보고 후 Method Object 패턴 적용 (Tidy 계열 — 승인 없이)
- 모든 테스트 통과
CONSTRAINTS
- 계열: Tidy — 후보 보고 후 승인 없이 적용 (
../../references/refactoring-procedure.md§0·§3-A)
Hard Rules
- 동작 변경 금지 — 구조 개선만 수행
- 테스트 수정 금지 — 구조 변경이 테스트를 실패시키면 되돌리기
- 커밋 단위 — 1파일 x 1기법 = 1커밋 (논리적으로 연결된 파일은 함께)
- git add -A 금지 — 변경된 파일만 명시적으로 추가
적용 패턴
Extract Method Object 리팩토링 단계:
-
메서드를 클래스로 변환
- 새 클래스 생성 (메서드명 + "er" 또는 명사형)
- 원본 메서드를 invoke() 또는 execute() 메서드로 이동
-
지역 변수를 필드로 변환
- 메서드 내 지역 변수들을 클래스 필드로 변환
- 읽기 전용 변수는 final 필드로
-
외부 의존성을 생성자 파라미터로 전달
- 원본 클래스의 필드 참조를 생성자 파라미터로
- 필요한 최소한의 의존성만 전달
-
작은 메서드로 분해
- 큰 invoke() 메서드를 의미 있는 작은 private 메서드들로 분해
- 각 메서드는 단일 책임 수행
Before/After 예시
// Before: 지역 변수가 상호 의존하는 거대 메서드 (50+ lines)
public class RefundService {
public List<RefundDiff> refundDiff() {
// 지역 변수 선언
Map<String, Cost> costMap = new HashMap<>();
Map<String, AcmeCost> acmeCostMap = new HashMap<>();
List<RefundDiff> differences = new ArrayList<>();
// 복잡한 로직이 50줄 이상...
for (Cost cost : costs) {
costMap.put(cost.getItemId(), cost);
}
for (AcmeCost acmeCost : acmeCosts) {
acmeCostMap.put(acmeCost.getItemId(), acmeCost);
}
for (OrderItem item : orderItems) {
Cost cost = costMap.get(item.getItemId());
AcmeCost acmeCost = acmeCostMap.get(item.getItemId());
if (cost != null && acmeCost != null) {
double diff = cost.getAmount() - acmeCost.getAmount();
if (Math.abs(diff) > 0.01) {
differences.add(new RefundDiff(item, diff));
}
}
}
return differences;
}
}
// After: Method Object로 추출
public class RefundService {
public List<RefundDiff> refundDiff() {
return new RefundDifferenceCalculator(costs, acmeCosts).invoke(orderItems);
}
}
class RefundDifferenceCalculator {
private final List<Cost> costs;
private final List<AcmeCost> acmeCosts;
private Map<String, Cost> costMap;
private Map<String, AcmeCost> acmeCostMap;
private List<RefundDiff> differences;
RefundDifferenceCalculator(List<Cost> costs, List<AcmeCost> acmeCosts) {
this.costs = costs;
this.acmeCosts = acmeCosts;
}
List<RefundDiff> invoke(List<OrderItem> orderItems) {
buildCostMaps();
calculateDifferences(orderItems);
return differences;
}
private void buildCostMaps() {
costMap = costs.stream()
.collect(Collectors.toMap(Cost::getItemId, c -> c));
acmeCostMap = acmeCosts.stream()
.collect(Collectors.toMap(AcmeCost::getItemId, c -> c));
}
private void calculateDifferences(List<OrderItem> orderItems) {
differences = new ArrayList<>();
for (OrderItem item : orderItems) {
findAndAddDifference(item);
}
}
private void findAndAddDifference(OrderItem item) {
Cost cost = costMap.get(item.getItemId());
AcmeCost acmeCost = acmeCostMap.get(item.getItemId());
if (cost != null && acmeCost != null) {
addDifferenceIfSignificant(item, cost, acmeCost);
}
}
private void addDifferenceIfSignificant(OrderItem item, Cost cost, AcmeCost acmeCost) {
double diff = cost.getAmount() - acmeCost.getAmount();
if (Math.abs(diff) > 0.01) {
differences.add(new RefundDiff(item, diff));
}
}
}
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.
- 1mo ago Changed · -4 lines · +71 tokens per session 427e2db2d3dc
- 1mo ago Changed · +2 tokens per session fe5f1c10508e
- 1mo ago First seen · 265 lines · 32 tokens per session scan A cb351bf9d148
extract-method-object is a skill published in the GitHub repository msbaek/msbaek-claude-plugins (8 stars, last pushed 5d ago), licensed MIT. It adds 105 tokens to every session and 2,734 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…