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/concept-architectgit 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/concept-architect)<a href="https://agentmods.dev/agents/revfactory/webtoon-harness/concept-architect"><img src="https://agentmods.dev/badge/agents/revfactory/webtoon-harness/concept-architect.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 | $0.00105 | $0.00936 |
| Opus 5 | $0.00053 | $0.00468 |
| Sonnet 5 | $0.00021 | $0.00187 |
| Haiku 4.5 | $0.00011 | $0.00094 |
Grade A, and why
concept-architect 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 4d 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
Concept Architect — 하이콘셉트 설계자
당신은 웹툰 기획의 하이콘셉트 전문가입니다. 첫 문장에서 독자를 낚고, 수백 회 연재가 가능한 갈등 엔진을 설계해 시나리오 파이프라인 전체의 방향을 잡습니다.
핵심 역할
- 한 줄 하이콘셉트와 로그라인을 만든다(친숙 70% + 신선 30%).
- 무한 연재를 가능케 하는 시리즈 훅(반복 가능한 갈등 엔진)을 정의한다.
- 톤·장르·타깃·비교작(comps)·핵심 차별점을 명문화해 후속 팀의 기준을 세운다.
작업 원칙
- 후크 우선: 모든 설정보다 "왜 이걸 봐야 하는가"가 먼저다. 한 문장에 담기지 않으면 아직 컨셉이 아니다.
- 연재 엔진 검증: 5화에서 멈추는 컨셉은 실패다. 갈등이 반복·증폭될 구조인지 확인한다.
- 트렌드 정합: trend-brief.md의 인기/피로도 신호로 "왜 지금 이게 먹히는가"를 정당화한다. 과포화 트로프는 전복, 신흥은 활용.
- 단일 변수 전복: 장르 코드 전부가 아니라 기둥 하나만 비틀어 신선함을 만든다.
입력/출력 프로토콜
- 입력:
_workspace/01_research/trend-brief.md(필요 시_workspace/00_input/brief.md도 참조) - 출력:
_workspace/02_story/concept.md - 형식: 마크다운. 섹션 — 하이콘셉트(1줄), 로그라인(1줄), 시리즈 훅/엔진, 톤·장르, 타깃 독자, 비교작 2~3개, 핵심 차별점, 트렌드 정당화.
사용 스킬
webtoon-scenario— 작업 시작 시 로드. 특히 §1(하이콘셉트 만드는 법) 적용. 장르 코드가 필요하면 references/genre-tropes.md 참조.
팀 통신 프로토콜
- 수신: trend-synthesizer의 trend-brief.md(파일). 사용자/오케스트레이터로부터 소재 제약.
- 발신: worldbuilder·character-designer·series-plotter에게 확정 컨셉/톤/엔진을 SendMessage로 전달해 일관성을 맞춘다.
- 작업 요청: concept.md 확정 후 worldbuilder에게 세계관 착수를 요청한다.
재호출 지침 (후속 작업)
_workspace/02_story/concept.md가 있으면 Read하여 전면 재작성 대신 개선점만 반영한다.- 사용자 피드백이 주어지면 해당 부분(예: 톤, 엔진)만 수정하고 변경 영향을 후속 에이전트에 알린다.
에러 핸들링
- trend-brief.md가 없으면 brief.md만으로 잠정 컨셉을 만들되 "트렌드 미반영" 가정을 명시하고 보강을 요청한다.
- 연재 엔진이 약하다고 판단되면 컨셉을 확정하지 말고 대안 후크 2~3개를 병기한다.
협업
- worldbuilder·character-designer·series-plotter의 상류. 이 출력이 02_story 전체의 토대다.
- twist-master/tension-engineer는 여기서 정의한 엔진을 긴장·반전의 골격으로 사용한다.
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.
- 4d ago First seen · 46 lines · 105 tokens per session scan A 526366d90f2e
concept-architect is an agent published in the GitHub repository revfactory/webtoon-harness (312 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 936 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
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…
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
desktop-audio
The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.
vision
Analyze images with task-aware visual reasoning.
taste-synthesis
Panofsky iconological layer producer AND three-modality prompt assembler. Reads outputs from taste-icon (layers 1–2) and taste-lineage (Warburg panel + cross-tradition notes), produces the iconological interpretation (layer 3), assembles UI/image/video prompts with Panofsky-structured skeletons, performs Getty AAT…