webtoon-harness: Skill for Claude Code

.claude/skills/webtoon-assembly/SKILL.md

webtoon-assembly is a skill for Claude Code from revfactory/webtoon-harness. It costs 228 tokens per session (4,608 once invoked), scanned A, original, MIT.

A research agent that tracks current Korean webtoon genres and recurring story patterns, such as time travel, reincarnation, revenge, and fantasy hunters.

In plain words
What is it for?
Collecting recent web signals, recording sources, explaining why patterns may appeal to readers, and mapping genre combinations and story tropes.
Why use it?
It helps creators distinguish repeated market signals from isolated examples and identify what may be rising, established, or declining.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument; mentions Codex.

This is revfactory/webtoon-harness's own configuration. It tells Claude Code how to work on webtoon-harness 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 webtoon-harness configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is { src: "../../05_panels/ep{NN}/panel_001.png", alt: "panel 001", gap: 0 }.

Reuse

Borrowing it

Nothing to install: this file belongs to revfactory/webtoon-harness. 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/revfactory/webtoon-harness/main/.claude/skills/webtoon-assembly/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/revfactory/webtoon-harness

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 webtoon-assembly

README.md
[![agentmods](https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-assembly/github.svg)](https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-assembly)
Your own site
<a href="https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-assembly"><img src="https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-assembly/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 webtoon-assembly

Your own site · 80×15
<a href="https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-assembly"><img src="https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-assembly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 228 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,608 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00228 $0.04608
Opus 5 $0.00114 $0.02304
Sonnet 5 $0.00046 $0.00922
Haiku 4.5 $0.00023 $0.00461

Measured 9d ago against content hash 3ae845a84bd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

webtoon-assembly 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 9d 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/webtoon-assembly/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

웹툰 조립·검수 방법론 (webtoon-assembly)

렌더가 끝난 패널을 "읽히는 웹툰"으로 만드는 마지막 공정이다. 조립(세로 스크롤 뷰어) → 레터링(말풍선) → QA/검수 → 연속성 관리 → 최종 패키징까지를 다룬다. 특정 회차에 맞추지 말고 어느 회차에든 적용되게 일반화해 쓴다. {NN} = 2자리 회차 번호.

핵심 원칙(왜 이렇게 하나):

  • 순서가 서사다. 패널은 panel_001 → panel_050+ 순서가 곧 독서 흐름이며 긴장 곡선·반전 타이밍이 여기에 실린다. 순서를 깨면 이야기가 깨진다.
  • 모바일 세로 스크롤이 기본 매체다. 독자는 손가락으로 내려 읽는다. 데스크톱도 중앙 정렬된 모바일 폭으로 본다.
  • 가독성이 작화를 이긴다. 말풍선이 얼굴/핵심 작화를 가리면 독자는 이탈한다. 대사 위주 웹툰일수록 더 그렇다.
  • 검수는 증명이다. "좋아 보인다"가 아니라 측정값과 교차 비교로 합격을 증명한다.

1. 세로 스크롤 뷰어 조립법 (episode-compositor)

왜: 패널을 한 줄기 세로 스트립으로 이어, 손가락 스크롤만으로 끊김 없이 읽게 만든다.

이 하네스의 말풍선은 in-image 베이크다. 말풍선·한글 대사가 패널 PNG에 이미 그려져 있으므로, 조립은 텍스트 오버레이 없이 패널을 순서대로 잇는 순수 이미지 스트립이다. lettering.md는 오버레이 데이터가 아니라 (a) 패널 간 간격·리듬 힌트, (b) QA가 베이크된 텍스트를 대조할 기준으로만 쓴다.

골격은 assets/viewer-template.html을 쓴다. 외부 의존성 없는 단일 HTML이라 어디서든 열어 검수할 수 있다. 처음부터 새로 짜지 말고 템플릿의 METAPANELS 데이터 배열만 채운다.

절차

  1. _workspace/05_panels/ep{NN}/의 PNG를 파일명 오름차순(panel_001 → …)으로 수집한다(panel-validator 통과본).
  2. 템플릿의 PANELS 배열을 채운다. 한 항목 = 한 패널(말풍선 데이터 없음):
    { src: "../../05_panels/ep{NN}/panel_001.png", alt: "panel 001", gap: 0 }
    
    • src는 결과 파일(06_assembly/ep{NN}/index.html) 기준 상대경로(../../05_panels/...). 또는 패널을 동일 폴더로 복사해 참조해도 된다.
    • gap은 다음 패널과의 간격(px): 0=무봉제(연속 컷), 양수=장면 전환/시간 경과/침묵 컷("쿵"). lettering.md의 리듬 힌트와 샷리스트 SCENE BREAK를 근거로 정한다.
  3. 패널을 원본 비율로 온전히 배치한다(베이크된 말풍선이 잘리지 않게).
  4. 브라우저로 열어 스크롤·이음새·말풍선 가독을 육안 확인한다. 베이크 말풍선이 깨졌으면 오버레이로 덮지 말고 panel-validator/panel-artist에 재렌더를 요청한다(이중 표기 금지).

구조·스타일 규칙 (템플릿에 반영됨)

  • 반응형 폭(모바일 우선): --max-w: 720px 중앙 정렬. 폭은 100%로 채우고 높이는 auto.
  • 패널 간 이음새: --panel-gap로 제어. 0px=무봉제 연결(한 장면의 연속 컷), 양수=칸 분리(장면 전환·시간 경과). 의미에 맞게 쓴다.
  • lazy-load: <img loading="lazy" decoding="async">. 50+ 패널 회차의 초기 로딩·메모리 부담을 줄인다.
  • 결손 표시: 이미지 로드 실패 시 칸을 비우지 않고 경고 플레이스홀더를 보여준다(img.onerror). 누락을 숨기지 않아야 검수가 잡는다.
  • 데이터/표현 분리: 패널·말풍선은 데이터 배열, 스타일은 CSS. 재조립·수정 시 데이터만 갈아끼운다.

결손·순서 처리

  • 번호가 비면(panel_007 없음) 당겨 붙이지 말고 그 자리에 결손을 표시하고 panel-artist에 재렌더를 요청한다. 순서가 어긋나면 반전 타이밍이 무너진다.
  • 0바이트/손상 PNG도 결손으로 취급한다.

Read the full file on GitHub · 170 lines

Files

What ships with it

2 files 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. 9d ago First seen · 170 lines · 228 tokens per session scan A 3ae845a84bd5

Subscribe to this mod's changes

webtoon-assembly is a skill published in the GitHub repository revfactory/webtoon-harness (313 stars, last pushed 2mo ago), licensed MIT. It adds 228 tokens to every session and 4,608 once invoked, about $0.0011 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 2026-08-30.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens