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 agentmods add commands/jhlee0409/claude-plugins/explaingit clone --depth 1 https://github.com/jhlee0409/claude-pluginsWhat 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 | $0.00008 | $0.02274 |
| Opus 5 | $0.00004 | $0.01137 |
| Sonnet 5 | $0.00002 | $0.00455 |
| Haiku 4.5 | $0.00001 | $0.00227 |
Grade A, and why
explain 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 2d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fsdarch:explain
FSD 개념을 프로젝트 맥락에서 설명합니다. 학습 곡선을 낮추고 팀 내 이해도를 통일합니다.
Syntax
/fsdarch:explain <topic>
Available Topics
| Topic | Description |
|---|---|
layers |
7개 레이어와 각각의 역할 |
feature-vs-widget |
Feature와 Widget의 차이 |
entity-vs-feature |
Entity와 Feature의 차이 |
public-api |
Public API 패턴과 이유 |
segments |
ui, model, api, lib 세그먼트 |
cross-imports |
Cross-import 금지 규칙 |
hierarchy |
레이어 계층 규칙 |
shared |
Shared 레이어 사용법 |
slices |
슬라이스 분리 기준 |
<custom> |
자유 질문 (FSD 관련) |
Execution Flow
Step 1: Parse Topic
- 미리 정의된 토픽인지 확인
- 아니면 자유 질문으로 처리
Step 2: Load Project Context
.fsd-architect.json로드 (있으면)- 현재 프로젝트 구조 분석
- 실제 예시 준비
Step 3: Generate Explanation
- 개념 설명 (이론)
- 프로젝트 예시 (실제)
- 관련 규칙
- 추가 학습 자료
Step 4: Display Result
토픽별 맞춤형 출력.
Examples
Example 1: Feature vs Widget
/fsdarch:explain feature-vs-widget
═══════════════════════════════════════════════════════════════
FEATURE vs WIDGET
═══════════════════════════════════════════════════════════════
📚 핵심 개념
Feature (기능)
→ 사용자 시나리오 단위의 기능
→ "사용자가 ~할 수 있다"로 설명 가능
→ 비즈니스 로직 포함 가능
→ 다른 Feature와 독립적
Widget (위젯)
→ 여러 Feature를 조합한 UI 블록
→ 자체 비즈니스 로직 최소화
→ 페이지에서 재사용되는 "덩어리"
───────────────────────────────────────────────────────────────
🎯 결정 기준
"이것이 독립적인 사용자 행동인가?"
→ YES: Feature (예: "로그인", "장바구니 추가", "리뷰 작성")
→ NO: Widget (예: "헤더", "사이드바", "제품 카드 그리드")
"다른 기능과 조합되어야 하는가?"
→ YES: Widget (예: HeaderWidget = auth + cart + search 조합)
→ NO: Feature
───────────────────────────────────────────────────────────────
📁 당신의 프로젝트 예시
Features (현재 8개):
├── auth/ → 사용자가 "로그인할 수 있다"
├── cart/ → 사용자가 "장바구니를 관리할 수 있다"
├── checkout/ → 사용자가 "결제할 수 있다"
├── favorites/ → 사용자가 "찜 목록을 관리할 수 있다"
└── ...
Widgets (현재 3개):
├── header/ → auth + cart + search 조합
├── product-card/ → product entity + favorites feature 조합
└── sidebar/ → navigation + user-info 조합
───────────────────────────────────────────────────────────────
⚠️ 흔한 실수
1. Feature가 너무 큼
✗ features/user/ (너무 포괄적)
✓ features/user-profile/, features/user-settings/
2. Widget에 비즈니스 로직
✗ widgets/header/model/authLogic.ts
✓ features/auth/ 에서 로직, widget은 조합만
3. Feature 간 의존성
✗ features/auth → features/cart
✓ widgets/auth-cart 에서 조합
───────────────────────────────────────────────────────────────
📚 더 알아보기
• https://feature-sliced.design/docs/reference/layers#features
• https://feature-sliced.design/docs/reference/layers#widgets
═══════════════════════════════════════════════════════════════
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.
- 2d ago First seen · 339 lines · 8 tokens per session scan A 8e9e551a2c6a
explain is a command published in the GitHub repository jhlee0409/claude-plugins (4 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 2,274 once invoked, about $0.0000 per session on Opus 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 commands, from other repositories
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
index
Command "index" from MadaraUchiha-314/the-loop, covering commands, the control plane, daemon commands, repo-scoped commands and maintenance.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.