wrap-up

wrap-up is a skill for Claude Code from CaesiumY/dding-dong. It costs 29 tokens per session (2,868 once invoked), scanned A, original, MIT.

A session-closing tool that updates README.md and CLAUDE.md from the current source code. It can update both files or only one of them.

In plain words
What is it for?
Use it at the end of a coding session or after changing the source code. It analyzes the project and synchronizes the selected documentation files.
Why use it?
It reduces the risk that project documentation describes old commands, settings, or events after code changes. It is meant for completed changes, not for designing or implementing new features.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the dding-dong plugin — 12 skills, 4 hooks shipped together

Good fit Use it at the end of a coding session or after changing the source code. It analyzes the project and synchronizes the selected documentation files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/caesiumy/dding-dong/wrap-up
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.

Any agent
npx skills add CaesiumY/dding-dong --skill wrap-up
Clone the repo
git clone --depth 1 https://github.com/CaesiumY/dding-dong

Made for: Claude Code.

Or install dding-dong, the plugin that ships this one along with the rest of its 12 skills, 4 hooks.

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 wrap-up

README.md
[![agentmods](https://agentmods.dev/badge/skills/caesiumy/dding-dong/wrap-up.svg)](https://agentmods.dev/skills/caesiumy/dding-dong/wrap-up)
Your own site
<a href="https://agentmods.dev/skills/caesiumy/dding-dong/wrap-up"><img src="https://agentmods.dev/badge/skills/caesiumy/dding-dong/wrap-up.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,868 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 $0.00029 $0.02868
Opus 5 $0.00015 $0.01434
Sonnet 5 $0.00006 $0.00574
Haiku 4.5 $0.00003 $0.00287

Measured 7d ago against content hash 2a4d989ea055, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

wrap-up 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 7d 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/skills/wrap-up/SKILL.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dding-dong 세션 마무리

소스코드를 진실의 원천(source of truth)으로 삼아 README.md와 CLAUDE.md를 자동 동기화합니다.

사용 시점

  • 소스코드를 변경한 후 문서를 동기화할 때
  • 코딩 세션을 마무리할 때
  • 새 커맨드/이벤트/설정을 추가한 후

사용하지 말 것

  • 소스코드 변경 없이 문서만 직접 편집할 때
  • 새 기능 설계/구현 도중 (구현 완료 후 실행)

인수 처리

$ARGUMENTS를 파싱하여 동작을 결정합니다:

인수 동작
(없음) README.md + CLAUDE.md 모두 동기화
--readme-only README.md만 동기화
--claude-only CLAUDE.md만 동기화

워크플로우

3단계 Task 기반 서브에이전트 워크플로우를 실행합니다. 진행 상황을 한국어로 안내합니다.

Stage 1: 소스코드 분석 (Explorer)

"소스코드를 분석하고 있습니다..." 를 출력하고 Task를 스폰합니다.

아래 프롬프트로 하나의 Task(explorer)를 실행합니다:

Task(prompt=<아래 프롬프트>, description="dding-dong 소스코드 분석")

Explorer 프롬프트:

dding-dong 프로젝트의 소스코드를 분석하여 문서 동기화에 필요한 데이터를 추출합니다.
프로젝트 루트: (현재 작업 디렉토리)

아래 소스 파일들을 Read로 읽고, 각 항목별로 구조화된 분석 결과를 반환하세요.

## 분석 대상

| 소스 파일 | 추출 대상 |
|-----------|-----------|
| scripts/core/config.mjs | DEFAULT_CONFIG 객체 전체, 환경변수 오버라이드 목록(DDING_DONG_*), 설정 경로 상수(CONFIG_DIR, CONFIG_FILE, STATE_FILE), 스코프 병합 순서 |
| scripts/core/platform.mjs | detectPlatform() 반환값 목록, detectAudioPlayer() 플랫폼별 우선순위, detectNotifier() 플랫폼별 우선순위 |
| scripts/core/player.mjs | resolveSound() 팩 탐색 경로 순서(사용자 팩 -> 내장 팩), 플랫폼별 재생 명령어와 인수, rotation 모드별 동작(random vs sequential), _linuxArgs() 플레이어별 인수 |
| scripts/core/notifier.mjs | 플랫폼별 알림 전송 분기(macOS/Linux/WSL), WSL 폴백 체인(wsl-notify-send -> WinRT PowerShell -> terminal bell) |
| scripts/core/messages.mjs | 지원 언어 목록, 이벤트별 메시지 키-값 |
| hooks/hooks.json | 등록된 훅 이벤트 타입과 timeout 값, 각 훅의 command 경로 |
| hooks/*.mjs | 훅 파일 목록, 각 훅이 매핑하는 이벤트 타입, _common.mjs의 runHook() 동작 흐름 |
| sounds/default/manifest.json | manifest 스키마(필수/선택 필드), 이벤트별 파일 매핑, rotation 모드 |
| commands/*.md | 모든 커맨드 이름과 description (frontmatter에서 추출) |

## 출력 형식

아래 섹션별로 정리하여 반환하세요. 각 섹션은 마크다운 헤딩으로 구분합니다.

### 1. 설정 (Config)
- DEFAULT_CONFIG 객체 (JSON 그대로)
- 환경변수 오버라이드 테이블 (변수명 | 설명)
- 설정 파일 경로 테이블 (파일 | 경로)
- 스코프 병합 순서: Default <- Global <- Project <- Project Local <- ENV

### 2. 크로스 플랫폼
- 플랫폼별 사운드 재생 테이블 (플랫폼 | 도구 | 비고)
- 플랫폼별 알림 전송 테이블 (플랫폼 | 도구 | 폴백)
- Linux 오디오 플레이어 우선순위 체인

### 3. 사운드 팩
- manifest.json 필드 테이블 (필드 | 필수 | 설명)
- 팩 탐색 순서 (사용자 팩 경로 -> 내장 팩 경로)
- rotation 모드 테이블 (모드 | 동작)

### 4. 이벤트 & 훅
- 이벤트 타입 목록
- 훅 파일 -> 이벤트 매핑 테이블
- hooks.json 구조 요약

### 5. 메시지
- 지원 언어
- 이벤트별 메시지 테이블 (이벤트 | 한국어 | 영어)

### 6. 커맨드
- 커맨드 목록 테이블 (커맨드 | description)

### 7. Data Flow
- notify.mjs의 전체 흐름: Hook event -> hooks/*.mjs -> _common.mjs runHook() -> notify() -> loadConfig() -> isQuietHours() -> isCoolingDown() -> playSound() + sendNotification() -> saveState()
- _common.mjs의 stdin 파싱 -> notify() 호출 -> optional stdout 응답 흐름

### 8. 디렉토리 구조
- Glob으로 프로젝트 전체 파일 트리를 확인하고, 주요 디렉토리/파일 목록을 트리 형태로 출력
- .claude-plugin/, commands/, hooks/, scripts/, sounds/ 각 디렉토리의 역할 한 줄 설명

### 9. Critical Design Rules
- hooks/*.mjs에서 발견되는 패턴: stop hook MUST respond, exit(0) on error, detached+unref
- ESM only (.mjs), No npm dependencies, env var overrides, sound pack resolution order

Read the full file on GitHub · 280 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. 7d ago First seen · 280 lines · 29 tokens per session scan A 2a4d989ea055

Subscribe to this mod's changes

wrap-up is a skill published in the GitHub repository CaesiumY/dding-dong (2 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 2,868 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

engram

Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…

techtheist/engram · 78 tokens

engram-digest

Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…

techtheist/engram · 98 tokens

persona-triggers

A detailed guide for matching Korean and English trigger phrases to working viewpoints, such as security, testing, design, operations, and AI. A trigger phrase is wording in a request that activates a particular response approach.

sodam-ai/SoDam-Persona · 91 tokens

persona-format

A Korean-language response format for coding, debugging, and implementation work. It asks for structured reasoning, multiple expert viewpoints, a recommended solution, execution steps, verification, and prevention of repeat problems.

sodam-ai/SoDam-Persona · 71 tokens

persona-marketer

A review guide for marketing and sales work, including copywriting, content, search visibility, advertising, landing pages, and customer retention. It looks at the work from the viewpoint of an experienced marketer and salesperson.

sodam-ai/SoDam-Persona · 94 tokens

persona-safety

A safety guide for coding, user-interface, security, deployment, deletion, and force-push work. It requires extra checks for secrets, sensitive data, risky changes, cleanup paths, and mobile layouts.

sodam-ai/SoDam-Persona · 69 tokens