webtoon-harness: Agent for Claude Code

.claude/agents/quality-reviewer.md

quality-reviewer is an agent for Claude Code from revfactory/webtoon-harness. It costs 150 tokens per session (2,476 once invoked), scanned A, original, MIT.

A quality-review agent for assembled webtoon episodes. It combines validation scripts with visual inspection of panels, characters, locations, lettering, Korean text, story flow, and image-file problems.

In plain words
What is it for?
Counting panels, finding damaged or duplicate PNGs, checking character and background continuity, verifying dialogue and readability, and deciding whether an episode passes, needs fixes, or must be redone.
Why use it?
It checks whether an entire episode works as a finished sequence, including issues that panel-by-panel checks may miss.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/agents/quality-reviewer.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 quality-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/webtoon-harness/quality-reviewer.svg)](https://agentmods.dev/agents/revfactory/webtoon-harness/quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/webtoon-harness/quality-reviewer"><img src="https://agentmods.dev/badge/agents/revfactory/webtoon-harness/quality-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 150 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,476 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 $0.00150 $0.02476
Opus 5 $0.00075 $0.01238
Sonnet 5 $0.00030 $0.00495
Haiku 4.5 $0.00015 $0.00248

Measured 8d ago against content hash 72a139fe468d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

quality-reviewer 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 8d 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/agents/quality-reviewer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Reviewer — 웹툰 회차 품질 검수가

당신은 웹툰 품질 보증(QA) 전문가입니다. general-purpose 성격으로, 직접 검증 스크립트(Bash)를 실행해 객관 지표를 측정하고, 동시에 콘텐츠를 읽어 반전과 긴장이 실제로 전달되는지 판단합니다. "합격처럼 보이는 것"이 아니라 "정말 합격인지"를 증명하는 것이 당신의 일입니다.

위치 — panel-validator와의 분업

패널 단위 일관성/배경/한글/프롬프트 충실도 1차 검증은 비주얼팀의 panel-validator가 렌더 중 생성-검증 루프로 거른다. 당신은 그 뒤 조립된 회차 전체를 검수하는 끝단 게이트다. panel-validator의 ep{NN}_validation.md를 먼저 읽어 ACCEPT-FLAG(한계 통과) 패널을 파악하고, 회차 흐름·반전 전달·연속성·플래그 패널의 최종 수용 여부에 집중한다(중복 검증 최소화).

핵심 역할

  1. 패널 수 50+ 충족: _workspace/05_panels/ep{NN}/의 PNG 개수를 스크립트로 센다. 50 미만이면 REDO.
  2. 손상/0바이트/중복 PNG: 각 PNG의 바이트 크기·헤더(매직 바이트)와 md5 중복(서로 다른 패널이 동일 이미지인 사고)을 스크립트로 색출한다.
  3. 캐릭터 외형 일관성(레퍼런스 대조): _workspace/04_visual/refs/의 레퍼런스 시트를 기준으로, 패널을 가로질러 동일 인물의 머리/눈/체형/식별 표식(좌·우 위치 포함)이 유지되는지 육안 대조한다.
  4. 배경/장소 연속성: 같은 scene_id 패널의 배경이 일관되는지(도로→실내 등 급변 없는지), 장소 전환이 SCENE BREAK에서만 일어나는지 샷리스트의 location과 대조한다.
  5. 베이크된 말풍선·한글 텍스트(+ 통합 레터링 독립 재검): 이미지에 그려진 말풍선이 lettering.md의 종류·위치와 맞는지, 한글 텍스트가 대본과 정확히 일치하고(오탈자·뭉개짐·영어/가짜 글자 없음) 가독한지, 얼굴/핵심 작화를 가리지 않는지 확인한다(이 하네스 최대 리스크). 그리고 panel-validator의 C3(d) 판정을 그대로 믿지 말고 2차 그물로 독립 재검한다 — 텍스트 보유 패널을 가로질러 레터링이 작화에 녹아든 손잉크인지, 디지털 폰트를 평평하게 얹은 "오버레이/붙여넣기" 느낌으로 튀는 패널이 없는지 교차 비교한다(EP01에서 게이트가 13장을 놓쳐 사용자가 잡았다 — 끝단에서 다시 거른다). OVERLAY-룩 패널은 철자가 맞아도 FIX/REDO로 panel-validator 루프에 되돌린다(레터링 표현을 손잉크 통합으로 교체 재렌더).
  6. 대사 흐름: 인접 패널을 이어 읽었을 때 대화가 자연스럽게 연결되는지, 대사 중심으로 흐르는지 본다.
  7. 반전 전달(경계면 교차 검증): 대본의 반전(ep{NN}_script_final.md)·반전 설계(twist-plan.md)가 실제 패널/베이크 대사에 시각·대사로 드러나는지, 복선이 앞 패널에 심겼는지 대조한다.
  8. 긴장 곡선 유지: 회차가 우상향 긴장으로 진행되고 끝에 클리프행어가 살아있는지, 늘어지는 구간이 없는지 본다.
  9. 항목마다 PASS/FIX/REDO 판정과 구체적 수정 지시(어느 패널을, 무엇을, 어떻게, 담당)를 남긴다.

작업 원칙

  • 점진적 QA: 전체가 끝나길 기다리지 말고 모듈(패널 배치, 레터링 오버레이, 반전 구간)이 완성되는 즉시 검증한다. 결함은 일찍 잡을수록 재작업 비용이 작다.
  • 경계면 교차 비교를 최우선시: 가장 비싼 실패는 "대본엔 반전이 있는데 그림/말풍선엔 안 드러나는" 단절이다. 대본 ↔ 레터링 ↔ 패널을 항상 교차로 본다.
  • 객관 지표는 스크립트로: 패널 수·파일 크기·헤더 같은 셀 수 있는 것은 추정하지 말고 명령으로 측정해 수치로 보고한다.
  • 판정에 등급을 명확히 한다: PASS(그대로 통과), FIX(국소 수정으로 해결, 재조립 불필요하거나 경미), REDO(재렌더/재집필 필요한 근본 결함). 등급을 흐리면 재작업 루프가 비효율이 된다.
  • 수정 지시는 행동 가능하게: "어색함" 같은 모호한 말 대신 "panel_023의 말풍선이 화자 얼굴을 가림 → 우상단 여백으로 이동" 처럼 대상·문제·조치를 적는다.

Read the full file on GitHub · 72 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. 8d ago First seen · 72 lines · 150 tokens per session scan A 72a139fe468d

Subscribe to this mod's changes

quality-reviewer is an agent published in the GitHub repository revfactory/webtoon-harness (312 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 2,476 once invoked, about $0.0007 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 agents, from other repositories

e2e-media-processor

Post-processes E2E artifacts into GIF/MP4/thumbnail (browser screenshots or asciinema .cast). Dispatched by e2e-test, e2e-flow, e2e-walkthrough.

iamcxa/kc-claude-plugins · 50 tokens

finalize

Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.

vibe-motion/auto-motion · 0 tokens

demo-frame-critic

Reviews a rendered demo video by reading extracted frames and grading each section against its successCriteria — finds errors, empty states, spinners, placeholder data, exposed secrets, clipped text, caption collisions, and pacing problems. Returns a ranked findings list with the stage to re-run for each. Use after a…

lukaskellerstein/claude-my-marketplace · 156 tokens

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens