explain

explain is a skill for Claude Code, Codex from Dannykkh/skill-olympus. It costs 76 tokens per session (1,659 once invoked), scanned A, original, MIT.

A code-explanation skill that uses plain-language analogies, step-by-step descriptions, and Mermaid diagrams. It can explain a file, a feature, or where a module fits in the wider codebase.

In plain words
What is it for?
Use it to learn a file, trace a feature such as login or payments, or map callers, sibling modules, and the surrounding project structure.
Why use it?
It makes unfamiliar code easier to understand and helps developers see both local behavior and broader relationships between modules.

Skill for Claude CodeCodex

Part of the skill-olympus plugin — 95 skills, 6 commands, 42 agents shipped together

Install

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.

agentmods
npx agentmods add skills/dannykkh/skill-olympus/explain
Any agent
npx skills add Dannykkh/skill-olympus --skill explain
Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Made for: Claude Code, Codex.

Or install skill-olympus, the plugin that ships this one along with the rest of its 95 skills, 6 commands, 42 agents.

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 explain

README.md
[![agentmods](https://agentmods.dev/badge/skills/dannykkh/skill-olympus/explain.svg)](https://agentmods.dev/skills/dannykkh/skill-olympus/explain)
Your own site
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/explain"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/explain.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00076 $0.01659
Opus 5 $0.00038 $0.00830
Sonnet 5 $0.00015 $0.00332
Haiku 4.5 $0.00008 $0.00166

Measured yesterday against content hash b0e29808ae4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

skills/explain/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explain (Learning Harness)

코드를 읽고 3가지 모드로 설명합니다:

  • 파일/기능 모드: 비유 + 3단계 설명 + Mermaid 다이어그램 (이게 무엇인지)
  • 줌아웃 모드: 호출자/형제 모듈/상위 맵 (이게 어디에 속하는지)

입력 판단

1. 파일 단위 (상세 설명)

@file 경로가 제공된 경우. 해당 파일의 핵심 로직을 설명.

/explain @src/auth/login.ts

2. 기능 단위

텍스트로 기능명이 제공된 경우. 코드베이스를 탐색하여 관련 파일들을 찾고 흐름을 설명.

/explain "로그인 기능"
/explain "결제 흐름"

기능 단위인 경우 현재 CLI가 네이티브 위임을 제공하면 읽기 전용 탐색 역할에 관련 파일과 호출 흐름 조사를 맡깁니다. 이 역할은 파일을 수정하지 않고 근거 경로와 핵심 흐름만 반환합니다. 특정 에이전트 이름이나 spawn 인자 형식을 요구하지 않습니다. 위임 기능이 없거나 실패하면 메인 컨텍스트에서 rg/Read로 같은 탐색을 순차 수행합니다. 설명 작성과 최종 근거 확인은 메인 컨텍스트가 담당합니다.

3. 줌아웃 모드 (Zoom-out)

"이게 뭘 하는지"가 아니라 "이게 어디에 속하는지"가 궁금할 때.

/explain --zoom-out @src/auth/middleware.ts
/explain --map @src/auth/middleware.ts
/explain @src/auth/middleware.ts 줌아웃

트리거 표현: "줌아웃", "한 단계 위", "전체 구조에서 어디", "위에서 보여줘", "맵", "zoom out", "broader context".

출력: 비유 X, 상세 설명 X. 다음 4가지만:

  1. 호출자(Callers) — 이 모듈을 부르는 곳 (Grep으로 import/usage 찾기)
  2. 형제(Siblings) — 같은 디렉토리/모듈의 다른 파일들과 각자의 역할
  3. 상위 맵 — 한 단계 위(부모 디렉토리 또는 기능 묶음) 구조
  4. 추천 다음 행동 — "이 코드를 이해하려면 X부터 읽으세요"

자세한 줌아웃 모드 워크플로우는 zoom-out.md를 참조.

설명 프로세스

1. 코드 분석

파일 단위: 대상 파일을 읽고 구조 파악. 기능 단위: 읽기 전용 탐색 역할 또는 메인 컨텍스트 순차 탐색으로 관련 파일 확인 → 핵심 파일들을 읽고 흐름 파악.

2. 3단계 설명 작성

A. 한 줄 요약

이 코드가 하는 일을 한 문장으로.

## 한 줄 요약
이 파일은 사용자 인증 토큰을 발급하고 갱신하는 서비스입니다.
B. 실제 비유

비개발자도 이해할 수 있는 현실 세계 비유로 설명.

## 비유로 이해하기
호텔 체크인 데스크와 같습니다:
- **로그인** = 신분증(ID/PW)을 보여주고 룸키(토큰)를 받는 것
- **토큰 갱신** = 룸키 유효기간이 지나서 프론트에서 새 키를 받는 것
- **로그아웃** = 체크아웃하면서 룸키를 반납하는 것

비유 작성 규칙:

  • 일상에서 누구나 아는 상황 사용 (호텔, 도서관, 우체국 등)
  • 코드의 각 핵심 요소를 비유의 요소에 1:1 매핑
  • 비유가 깨지는 부분이 있으면 솔직히 "여기서 비유는 한계가 있습니다" 명시
C. 왜 필요한가

이 코드가 시스템에서 어떤 역할을 하는지, 없으면 어떤 문제가 생기는지.

## 왜 필요한가
- 인증 없이는 누구나 다른 사용자의 데이터에 접근 가능
- 토큰 갱신 없으면 사용자가 매번 로그인해야 함
- 이 서비스가 모든 API 요청의 관문 역할

3. Mermaid 다이어그램

코드의 핵심 흐름을 Mermaid 다이어그램으로 시각화.

파일 단위: 주요 함수 간 호출 흐름 또는 상태 변화. 기능 단위: 파일/모듈 간 데이터 흐름.

Read the full file on GitHub · 173 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 173 lines · 76 tokens per session scan A b0e29808ae4a

Subscribe to this mod's changes

explain is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 1,659 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

continuous-learning

Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.

a5c-ai/babysitter · 25 tokens

career-path-planner

Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.

travisjneuman/.claude · 41 tokens

case-interview-practice

Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.

travisjneuman/.claude · 39 tokens

course-material-creator

Create custom educational materials including syllabi, lesson plans, assessments, reading lists, and learning objectives. Use when building course curricula, training programs, workshops, or educational content.

travisjneuman/.claude · 40 tokens

debate-practice-coach

Interactive debate and argument practice with structured feedback, counterargument generation, logical fallacy identification, and scoring rubrics. Use when preparing for debates, improving persuasion skills, or practicing argumentation.

travisjneuman/.claude · 45 tokens

replay-learnings

Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about".

rohitg00/pro-workflow · 61 tokens