webtoon-panel-render

webtoon-panel-render is a skill for Claude Code, Codex from revfactory/webtoon-harness. It costs 280 tokens per session (4,878 once invoked), scanned A, original, MIT.

A rendering workflow for generating webtoon panel images in batches, using character reference sheets, fixed location details, in-image lettering, and repeated quality checks.

In plain words
What is it for?
Use it to render a 50-plus-panel episode, keep characters and locations consistent, include speech bubbles and effects inside the artwork, and validate the results.
Why use it?
It reduces changes in character appearance and backgrounds between panels. It also checks generated panels and regenerates those that fail the required visual criteria.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also runs codex exec. Also seen: reads .claude/ paths; positional $N argument; mentions Codex.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/robin/Downloads/webtoon-new.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

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-panel-render

README.md
[![agentmods](https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-panel-render.svg)](https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-panel-render)
Your own site
<a href="https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-panel-render"><img src="https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-panel-render.svg" alt="Measured on agentmods" height="20"></a>
Per session 280 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,878 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 5.1 $0.00280 $0.04878
Opus 5 $0.00140 $0.02439
Sonnet 5 $0.00056 $0.00976
Haiku 4.5 $0.00028 $0.00488

Measured 6d ago against content hash 76a460cd76f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

webtoon-panel-render 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 6d 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-panel-render/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Webtoon Panel Render — 레퍼런스 → 베이크 렌더 → 검증 루프

웹툰 한 회차의 50+ 패널을 codex-image로 동시 5장씩 빠르게 렌더링하는 스킬. prompt-smith가 만든 패널 프롬프트 목록을 입력으로, 일관성을 지키며 PNG를 양산하고 검증한다.

이 스킬은 ~/.claude/skills/codex-image의 병렬 패턴 위에 웹툰 특화 일관성·검증·동시성 규약을 얹은 것이다. codex 호출 방식의 원본은 codex-image SKILL.md를 따른다.

핵심 4원칙(EP01 제작 피드백 반영):

  1. 레퍼런스 먼저(일관성). 패널을 그리기 전에 캐릭터 다각도/표정 레퍼런스 시트를 먼저 렌더해 외형 기준(SSOT)을 확정한다. 텍스트 토큰만으로는 매번 다른 얼굴이 나온다.
  2. 모든 텍스트 in-image 베이크(후작업 절대 금지). 말풍선 대사·효과음·화면 UI·환경 문자 등 모든 텍스트를 이미지 생성 시 작화에 함께 그린다(HTML 오버레이도, 포토샵 타이핑도, 어떤 후작업 합성도 없다). 그래서 "no text" 부정 프롬프트를 쓰지 않는다. 또한 결과가 베이크처럼 보여야 한다 — 텍스트는 작화와 같은 손그림 잉크 톤으로 녹아들어야 하고, 깨끗한 디지털 폰트를 평평하게 얹은 "붙여넣기" 느낌이면 실패(통합 레터링, EP01 P30·P33 피드백).
  3. 배경 씬 단위 고정. 씬별 장소 토큰(LOC_*)을 모든 패널에 주입해 배경 급변(도로→실내 등)을 막는다.
  4. 검증-재생성 루프. panel-validator가 패널을 6축으로 검사하고 미달분을 기준 만족까지 되돌려 재렌더한다.

사전 점검 (회차당 1회)

codex --version                                # 0.128+ 권장
codex login status                             # "Logged in using ChatGPT" 확인
codex features list | grep image_generation    # stable/true 확인

미로그인이면 사용자에게 codex login 실행을 요청한다. 렌더 도중 멈추지 않도록 시작 전에 확인한다.

0단계 — 캐릭터 레퍼런스 시트 먼저 렌더 (ref-sheet-artist)

패널보다 먼저, 주요 캐릭터의 다각도/표정 레퍼런스 시트를 렌더해 시리즈 외형 기준을 확정한다. 이것이 모든 패널 일관성과 검증의 닻이다.

  • 입력: _workspace/04_visual/character-sheets.md(불변 토큰), style-bible.md(작화 스타일).
  • 캐릭터마다 2장 권장:
    • refs/{IDTAG}_turnaround.png — 정면/3-4/측면/후면 전신, 중립 단색 배경, 균일 조명, 무표정.
    • refs/{IDTAG}_expressions.png — 핵심 표정 3~4종 클로즈업.
  • 레퍼런스 프롬프트 규약:
    • 글로벌 작화 스타일 토큰 + 캐릭터 불변 토큰 + "character reference sheet, multiple angles (front, 3/4, side, back), full body, neutral grey background, even flat lighting, model sheet".
    • 식별 표식(점/흉터/팔찌 등)을 또렷이, 좌/우 위치 고정.
    • 레퍼런스만은 텍스트 없이: no text, no labels, no speech bubbles, no watermark(깨끗한 외형 도감이어야 기준이 된다 — 패널의 in-image 말풍선과 반대).
  • 저장: _workspace/04_visual/refs/(회차 폴더가 아니라 시리즈 자산, 다음 회차 재사용). refs/INDEX.md에 캐릭터별 경로+핵심 외형 한 줄+확정 여부 기록.
  • 렌더 후 0바이트/손상/md5 중복 확인, 각도 간 동일인 여부 육안 점검. 흔들리면 재렌더(최대 3회). 확정 시 prompt-smith·panel-validator에 INDEX.md 인계.
  • 후속 회차: refs/가 이미 있으면 재렌더하지 않고 재사용한다(시리즈 일관성). 신규 캐릭터만 추가 렌더.

Read the full file on GitHub · 182 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. 6d ago First seen · 182 lines · 280 tokens per session scan A 76a460cd76f0

Subscribe to this mod's changes

webtoon-panel-render is a skill published in the GitHub repository revfactory/webtoon-harness (312 stars, last pushed 2mo ago), licensed MIT. It adds 280 tokens to every session and 4,878 once invoked, about $0.0014 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens