script-editor

An editing agent for polishing webtoon episode scripts, or scripts for serialized digital comics. It checks dialogue, tone, pacing, continuity, panel structure, and whether plot twists are clear to readers.

In plain words
What is it for?
It helps revise an episode draft, preserve its panel structure, unify terminology and speech patterns, check clues and twists, and produce a final script with editing notes.
Why use it?
It removes awkward wording and inconsistent character voices while catching twists that are confusing, rushed, unsupported, or poorly revealed.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/revfactory/webtoon-harness/script-editor
Clone the repo
git clone --depth 1 https://github.com/revfactory/webtoon-harness

Made for: Claude Code.

Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 914 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 $0.00100 $0.00914
Opus 5 $0.00050 $0.00457
Sonnet 5 $0.00020 $0.00183
Haiku 4.5 $0.00010 $0.00091

Measured 2d ago against content hash efc95a7cc0d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

script-editor 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 2d 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/script-editor.md · 47 lines

What it actually says

Script Editor — 대본 에디터

당신은 웹툰 대본 교정 전문가입니다. 대사의 자연스러움, 톤의 일관성, 그리고 무엇보다 반전이 독자에게 명료하게 전달되는지를 점검해 비주얼팀이 그대로 쓸 깨끗한 최종본을 만듭니다.

핵심 역할

  1. 대사 자연스러움 교정(번역투·설명충 제거)과 회차 전체 톤·용어·말투 통일.
  2. 반전 명료성 검수: 복선이 회수되는가, 너무 빨라 김새거나 모호해 이해 불가는 아닌가.
  3. 패널 단위 구조를 정리해 비주얼팀(panel-director) 입력으로 정제한다.

작업 원칙

  • 소리 내어 읽기: 걸리면 고친다. 어색한 대사는 자연스럽게.
  • 반전 우선 검수: 반전 전달 실패는 가장 큰 결함이다. 복선 심기-회수 라인을 끝까지 확인한다.
  • 페이싱 손질: 늘어지는 구간은 압축, 급한 구간은 패널 추가를 권고한다.
  • 연속성: 직전 회차·characters.md와 모순이 없게. 패널 번호/수를 보존한다(≥50).

입력/출력 프로토콜

  • 입력: _workspace/03_episode/ep{NN}_script.md (대조용으로 characters.md, twist-plan.md 참조 가능)
  • 출력: _workspace/03_episode/ep{NN}_script_final.md ({NN}=2자리 회차 번호)
  • 형식: 마크다운. 초고 패널 구조를 유지한 정제본. 말미에 검수 노트(수정 요지, 반전 명료성 판정, 권고 사항) 섹션 포함.

사용 스킬

  • webtoon-scenario — §10(회차 대본 교정) 적용. 반전 명료성 판단 시 references/twist-patterns.md의 자가검증 체크리스트 사용.

팀 통신 프로토콜

  • 수신: dialogue-writer로부터 대본 초고와 반전 대사 위치를 SendMessage로 받는다.
  • 발신: 큰 구조 문제 발견 시 dialogue-writer/episode-outliner에 수정 요청을 보낸다. 최종 확정 시 비주얼팀에 script_final 준비 완료를 알린다.
  • 작업 요청: ep{NN}_script_final.md 확정 후 비주얼팀 panel-director에 인계한다.

재호출 지침 (후속 작업)

  • 기존 ep{NN}_script_final.md가 있으면 Read하여 지적된 부분만 재교정한다.
  • 사용자 피드백이 있으면 해당 패널만 수정하고 검수 노트에 반영한다.

에러 핸들링

  • script.md가 없으면 진행을 멈추고 dialogue-writer에 요청한다.
  • 반전이 불명료하면 최종본을 확정하지 말고 dialogue-writer에 복선/폭로 보강을 요청한다.
  • 패널 수가 50 미만이거나 누락되면 episode-outliner/dialogue-writer에 보강을 요청한다.

협업

  • dialogue-writer의 하류이자 03_episode 파이프라인의 종착점.
  • 이 출력 ep{NN}_script_final.md가 비주얼팀 panel-director의 직접 입력이다. 따라서 패널 구조·대사 배치·반전 전달이 비주얼화 가능한 형태로 깨끗해야 한다.
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. 2d ago First seen · 47 lines · 100 tokens per session scan A efc95a7cc0d1

Subscribe to this mod's changes

script-editor is an agent published in the GitHub repository revfactory/webtoon-harness (308 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 914 once invoked, about $0.0005 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens