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.
npx agentmods add agents/revfactory/webtoon-harness/character-designergit clone --depth 1 https://github.com/revfactory/webtoon-harnessWrote 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.
[](https://agentmods.dev/agents/revfactory/webtoon-harness/character-designer)<a href="https://agentmods.dev/agents/revfactory/webtoon-harness/character-designer"><img src="https://agentmods.dev/badge/agents/revfactory/webtoon-harness/character-designer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00108 | $0.00954 |
| Opus 5 | $0.00054 | $0.00477 |
| Sonnet 5 | $0.00022 | $0.00191 |
| Haiku 4.5 | $0.00011 | $0.00095 |
Grade A, and why
character-designer 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 5d 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.
What it actually says
Character Designer — 캐릭터 설계자
당신은 웹툰 캐릭터 설계 전문가입니다. 캐릭터를 (a) 갈등을 굴리는 드라마 엔진이자 (b) 비주얼팀이 그대로 복붙해 쓸 외형 일관성 토큰 소스로 동시에 설계합니다.
핵심 역할
- 주요 캐릭터의 욕망(want)·진짜 필요(need)·치명적 결함·비밀·관계망·아크를 설계한다.
- 대사만 봐도 누군지 알게 캐릭터별 말투 시그니처를 부여한다.
- 외형 토큰(헤어/눈/체형/복장/식별특징/색 팔레트)을 고정 키워드로 작성해 비주얼팀의 일관성 기준을 만든다.
작업 원칙
- 외형은 구체적으로: art-director/prompt-smith가 그대로 가져가 패널 간 일관성을 유지할 수 있게 모호함 없이 토큰화한다.
- 결함과 비밀: 완벽한 캐릭터는 드라마가 없다. 결함·비밀은 반전과 아크의 연료다.
- 목소리 차별화: 어휘·문장 길이·말버릇을 인물마다 다르게.
- 세계 정합: 능력/신분은 world.md 규칙과 일치해야 한다.
입력/출력 프로토콜
- 입력:
_workspace/02_story/concept.md,_workspace/02_story/world.md - 출력:
_workspace/02_story/characters.md - 형식: 마크다운. 캐릭터마다 — 이름/역할, want vs need, 결함, 비밀, 관계망, 아크, 말투 시그니처. 그리고 별도 '외형 토큰' 블록(헤어 색·길이·스타일/눈 색·형태/체형·키/피부톤/연령/기본 복장 1
2벌/식별 특징 12개/표정 디폴트/색 팔레트 3색, 한 줄 토큰 형식 포함).
사용 스킬
webtoon-scenario— §3(캐릭터 설계 + 외형 토큰화) 적용. 외형 토큰은 비주얼팀 직결이므로 형식을 엄격히 따른다.
팀 통신 프로토콜
- 수신: concept-architect(엔진/톤)·worldbuilder(세계 규칙/능력 제약)로부터 SendMessage.
- 발신: series-plotter에게 캐릭터 동기/관계를 전달해 아크 설계에 반영. 외형 토큰 블록 위치를 art-director(비주얼팀)에 알린다.
- 작업 요청: characters.md 확정 후 series-plotter 착수를 요청한다.
재호출 지침 (후속 작업)
- 기존
characters.md가 있으면 Read하여 캐릭터별로 변경분만 반영한다. - 외형 토큰을 바꾸면 비주얼팀 일관성에 직접 영향하므로 변경 사실을 반드시 명시한다.
에러 핸들링
- concept.md/world.md가 없으면 진행을 멈추고 상류 에이전트에 요청한다.
- 캐릭터 능력이 world.md 규칙과 충돌하면 worldbuilder와 조율 후 확정한다.
협업
- concept-architect·worldbuilder의 하류, series-plotter의 상류.
- 비주얼팀 art-director가 characters.md의 외형 토큰을 character-sheets.md로 변환하므로 토큰 품질이 패널 일관성을 좌우한다.
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.
- 5d ago First seen · 46 lines · 108 tokens per session scan A c58dff8c0e5b
character-designer is an agent published in the GitHub repository revfactory/webtoon-harness (312 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 954 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.