webtoon-harness: Skill for Claude Code

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

webtoon-scenario is a skill for Claude Code from revfactory/webtoon-harness. It costs 209 tokens per session (4,206 once invoked), scanned A, original, MIT.

A Korean-language writing guide for planning and scripting serialized webtoons, including their story premise, characters, episode structure, twists, clues, dialogue, and panel breakdowns.

In plain words
What is it for?
Use it to create loglines, settings, character designs, series arcs, episode maps, cliffhangers, dialogue-led scripts, and detailed webtoon shot lists.
Why use it?
It helps turn an idea into episodes that maintain tension and make readers want to keep scrolling. It explains how to connect twists to earlier clues and divide each episode into at least 50 panels.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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 →

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-scenario/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-scenario

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-scenario"><img src="https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-scenario.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 209 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,206 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 $0.00209 $0.04206
Opus 5 $0.00105 $0.02103
Sonnet 5 $0.00042 $0.00841
Haiku 4.5 $0.00021 $0.00421

Measured 10d ago against content hash e85e412c3c1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

webtoon-scenario 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 10d 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-scenario/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

웹툰 시나리오 작성 방법론

웹툰 시나리오팀(concept-architect ~ script-editor) 전 에이전트의 공용 작법서다. 이 스킬은 무엇을 쓸지가 아니라 어떻게 쓸지를 정의한다. 특정 작품에 오버피팅하지 말고 어떤 장르·소재가 와도 동일한 절차로 적용한다.

0. 먼저 알아야 할 4대 품질 원칙 (Why-first)

웹툰은 세로 스크롤로 손가락이 멈추면 이탈한다. 그래서 모든 결정은 다음 4축을 만족시키기 위해 존재한다.

  1. 대사 위주 — 독자는 설명을 읽으러 오지 않는다. 정보·감정·반전을 캐릭터의 입과 행동으로 전달하라. 내레이션은 시공간 점프 등 꼭 필요할 때만.
  2. 고긴장 유지 — 매 패널은 "다음 패널을 보게 만드는 미끼"다. 회차 내내 긴장이 우상향하고 끝은 클리프행어로 닫는다.
  3. 매 회차 반전 — 회차마다 최소 1개, 독자의 예측을 뒤집는 순간을 둔다. 반전은 우연이 아니라 앞에 심은 복선의 회수여야 한다.
  4. 회차당 50+ 패널 — 비트시트/샷리스트 단계에서 패널 50개 이상을 보장한다. 부족하면 비트를 더 쪼갠다(아래 §8).

이 4축은 서로 강화한다: 대사로 긴장을 쌓고, 긴장의 정점에서 반전을 터뜨리고, 그 호흡을 패널로 잘게 나눈다.

1. 하이콘셉트 만드는 법 (concept-architect)

하이콘셉트 = 한 문장으로 "이거 봐야겠다"가 되는 후크. 다음 순서로 만든다.

  • What-if 압축: "만약 ___라면?"으로 세계의 핵심 비틀기를 한 문장에. (예: "죽으면 하루 전으로 돌아가는 형사가, 자기를 죽인 범인을 쫓는다.")
  • 친숙함 70% + 신선함 30%: 독자가 아는 장르 코드 위에 단 하나의 낯선 변수를 얹는다. 전부 낯설면 진입이 막히고, 전부 친숙하면 안 본다.
  • 로그라인 공식: [결함 있는 주인공]이 [목표]를 위해 [강한 적대/제약]과 맞서다가 [반전 가능성]에 직면한다.
  • 시리즈 훅(엔진): 회차가 무한히 나오게 하는 반복 가능한 갈등 구조를 명시한다. (회귀물=루프, 헌터물=등급 상승, 로맨스=관계의 진전/후퇴) 이 엔진이 약하면 시리즈가 5화에서 멈춘다.
  • 타깃·플랫폼 적합도: trend-brief.md의 인기 트로프/이탈 요인과 대조해 "왜 지금 이게 먹히는가"를 한 단락으로 정당화한다.

출력: 하이콘셉트 1줄, 로그라인 1줄, 시리즈 훅(엔진) 설명, 톤/장르, 비교작(comps) 2~3개, 핵심 차별점.

2. 세계관 설계 (worldbuilder)

세계관은 백과사전이 아니라 갈등을 만드는 규칙 세트다. 이야기에 쓰일 것만 정한다.

  • 핵심 규칙 3~5개: 세계가 작동하는 법칙. 특히 대가/제약을 명확히(능력에는 비용이 있어야 긴장이 산다).
  • 금기와 위반의 결과: 깨면 안 되는 선과 깼을 때의 대가 → 이것이 후반 반전의 연료.
  • 세력·계층·자원: 누가 무엇을 두고 다투는가. 갈등의 구조적 원천.
  • 미스터리 우물: 처음부터 다 밝히지 말고 "나중에 회수할 빈칸"을 의도적으로 남긴다(twist 연료).
  • 감각 디테일: 비주얼팀이 그릴 수 있게 색/건축/의상/날씨 등 시각 톤을 구체화.

3. 캐릭터 설계 + 외형 토큰화 (character-designer)

캐릭터는 (a) 드라마 엔진이자 (b) 비주얼팀의 일관성 토큰 소스다. 두 역할을 모두 채운다.

드라마 측면

  • 욕망(want) vs 진짜 필요(need), 치명적 결함, 비밀, 관계망(우호/적대/로맨스), 캐릭터 아크(어떻게 변하는가).
  • 말투 시그니처: 각 캐릭터가 대사만 봐도 누군지 알게 어휘·문장 길이·말버릇을 다르게.

외형 토큰(필수, 비주얼팀이 그대로 복붙해 일관성 유지) — 각 주요 캐릭터마다 고정 키워드로:

  • 헤어(색/길이/스타일), 눈(색/형태), 체형/키, 피부톤, 연령대
  • 기본 복장 12벌(실루엣/색 팔레트), 식별 특징(흉터·문신·안경·액세서리 등 **항상 보이는 12개**)
  • 표정 디폴트(무표정/미소 등), 색 팔레트 3색
  • 한 줄 토큰 예: 세이/16세 여/단발 은발/홍채 보라/마른 체형/검은 후드+붉은 머플러/왼눈 밑 점/무표정

Read the full file on GitHub · 160 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. 10d ago First seen · 160 lines · 209 tokens per session scan A e85e412c3c1a

Subscribe to this mod's changes

webtoon-scenario is a skill published in the GitHub repository revfactory/webtoon-harness (313 stars, last pushed 2mo ago), licensed MIT. It adds 209 tokens to every session and 4,206 once invoked, about $0.0010 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