design-big

design-big is a skill for Claude Code from MJbae/awesome-novel-studio. It costs 164 tokens per session (6,460 once invoked), scanned A, original, Apache-2.0.

A workflow for planning an entire web novel, including its concept, characters, plot, and hooks. It also researches specialist subject matter before producing the design.

In plain words
What is it for?
Use it to create a bootstrap document, character sheet, and plot-hook guide for a novel, with optional research and staged handling of existing designs.
Why use it?
Planning a long novel can involve several connected decisions, and changing one area can affect the others. This workflow divides the work among focused design roles and supports redesigning or revising existing planning documents.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the awesome-novel-studio plugin — 10 skills, 18 agents shipped together

Good fit Use it to create a bootstrap document, character sheet, and plot-hook guide for a novel, with optional research and staged handling of existing designs.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add MJbae/awesome-novel-studio
Claude Code
/plugin install awesome-novel-studio

Made for: Claude Code.

Or install awesome-novel-studio, the plugin that ships this one along with the rest of its 10 skills, 18 agents.

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 design-big

README.md
[![agentmods](https://agentmods.dev/badge/skills/mjbae/awesome-novel-studio/design-big/github.svg)](https://agentmods.dev/skills/mjbae/awesome-novel-studio/design-big)
Your own site
<a href="https://agentmods.dev/skills/mjbae/awesome-novel-studio/design-big"><img src="https://agentmods.dev/badge/skills/mjbae/awesome-novel-studio/design-big/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-big

Your own site · 80×15
<a href="https://agentmods.dev/skills/mjbae/awesome-novel-studio/design-big"><img src="https://agentmods.dev/badge/skills/mjbae/awesome-novel-studio/design-big.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,460 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 $0.00164 $0.06460
Opus 5 $0.00082 $0.03230
Sonnet 5 $0.00033 $0.01292
Haiku 4.5 $0.00016 $0.00646

Measured 12d ago against content hash 453d715cdc64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-big 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 12d 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.

skills/design-big/SKILL.md · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Novel Design Big — 큰 설계 오케스트레이터

웹소설의 전체 소설 설계를 수행한다. AI가 장르 DNA 프레임워크로 뼈대를 세우고, domain-researcher 서브에이전트가 자동 리서치로 전문 분야의 살을 붙이는 구조.

실행 모드: 에이전트 팀

에이전트 구성

팀원 에이전트 파일 역할 스킬 출력
concept-builder ${CLAUDE_PLUGIN_ROOT}/agents/concept-builder.md 부트스트랩 설계 bootstrap 부트스트랩 문서
character-architect ${CLAUDE_PLUGIN_ROOT}/agents/character-architect.md 캐릭터 설계 character 캐릭터 시트
plot-hook-engineer ${CLAUDE_PLUGIN_ROOT}/agents/plot-hook-engineer.md 플롯/훅 설계 plot-hook 플롯 훅 가이드

domain-researcher는 팀원이 아닌 서브에이전트로, Phase 1.5에서 팀 구성(TeamCreate) 전에 실행된다.

공유 레퍼런스

  • genre-dna-framework.md 위치: ${CLAUDE_PLUGIN_ROOT}/skills/design/references/genre-dna-framework.md (라우터 하위 — big/small 공용)

워크플로우

Phase 0: 기존 설계 확인 (선택)

프로젝트 루트에 기존 큰 설계 산출물({작품가제}_부트스트랩.md, {작품가제}_캐릭터시트.md, {작품가제}_플롯훅가이드.md)이 존재할 때만 실행. 없으면 Phase 1로 직행.

  1. 프로젝트 루트에서 기존 큰 설계 산출물을 Glob으로 확인
  2. 기존 산출물이 발견되면 사용자에게 모드 선택 요청:
기존 큰 설계 문서가 발견되었습니다:
- {발견된 파일 목록}

다음 중 선택해주세요:
1. **전체 재설계** — 기존 문서를 _workspace/_backup/에 백업 후 처음부터 다시 설계
2. **부분 수정** — 특정 영역만 재실행 (예: 부트스트랩만, 캐릭터만, 플롯만)
3. **자료 보강 후 재설계** — 새 리서치 자료를 추가한 뒤 기존 설계를 업그레이드
  1. 모드별 처리:
    • 전체 재설계: 기존 산출물을 _workspace/_backup/{timestamp}/에 복사 → Phase 1부터 진행
    • 부분 수정: 수정 대상 에이전트만 재실행. 나머지 산출물은 유지. Phase 2에서 해당 에이전트만 팀에 포함.
    • 자료 보강 후 재설계: 기존 _workspace/00_concept_analysis.md에서 컨셉 복원 → Phase 1 스킵 → Phase 1.5부터 진행

Phase 1: 컨셉 분석 및 방향 수립

  1. 제안서 자동 연결 (강화):
    • 프로젝트 루트에서 *_제안서.md 패턴을 Glob으로 탐색한다
    • 발견되면 Read하여 제안서의 컨셉, 장르, 플랫폼, 차별화 포인트, 로그라인을 자동 추출한다
    • 추출된 플랫폼은 반드시 아래 허용 플랫폼 집합으로 검증한다:
      • 문피아, 네이버시리즈, 카카오페이지, 리디, 조아라, 노벨피아
    • Munpia, munpia, 문 피아, 카카페, KakaoPage, 리디북스, NovelPia 등 허용 별칭은 canonical name으로 정규화한다
    • 허용되지 않는 플랫폼 또는 모호한 별칭이면 자동 반영하지 않고, 사용자에게 제안서 수정 또는 플랫폼 재선택을 요청한다
    • 추출된 정보로 Phase 1의 컨셉 분석을 사전 채운다 (사용자에게 확인 요청)
    • 제안서의 _workspace/00_research/ 디렉토리도 확인하여 기존 R1/R2/R5 리서치가 있으면 Phase 1.5에서 재활용한다
    • 제안서가 없으면: 사용자 입력에서 직접 분석 (기존 동작)
    제안서 '{파일명}'을(를) 발견했습니다.
    다음 컨셉으로 큰 설계를 진행합니다:
    - 장르: {제안서에서 추출}
    - 컨셉: {제안서에서 추출}
    - 플랫폼: {제안서에서 추출}
    - 차별화: {제안서에서 추출}
    
    수정하실 부분이 있으면 말씀해주세요. 없으면 바로 진행합니다.
    
  2. 사용자 입력 분석 — 소설 컨셉, 직업, 분위기, 차별화 방향 파악
    • 타겟 플랫폼이 명시되지 않았으면 한국 플랫폼 6개 중 하나를 확인한다
    • 타겟 플랫폼이 비지원 값이면 자동 치환하지 않고 재선택을 요청한다
  3. ${CLAUDE_PLUGIN_ROOT}/skills/design/references/genre-dna-framework.md를 읽어 장르 DNA 프레임워크 확인
  4. 프로젝트 루트의 참고 문서 확인 (존재 시)
  5. 컨셉 방향 요약을 사용자에게 제시하여 확인:
    • 주인공 직업/전문 분야
    • 서사 기점 (시대, 계기)
    • 핵심 차별화 포인트
    • 타겟 플랫폼 (문피아, 네이버시리즈, 카카오페이지, 리디, 조아라, 노벨피아 중 1개)
    • 예상 톤 & 무드
    • 유사 작품군 2~3개 (리더가 genre-dna 차별화 전략 + 업계 상식으로 제안)
  6. {작품가제} 확정 — 사용자에게 작품 가제를 확인한다. 이 가제가 이후 모든 파일명의 접두사로 사용된다.
  7. Phase 1 결과를 _workspace/00_concept_analysis.md에 저장 — 새 대화 시작 시에도 컨셉을 복원할 수 있도록 한다. 저장 내용: 작품가제, 전문 분야, 서사 기점, 차별화 포인트, 유사 작품군, 톤 & 무드.
  8. 사용자 확인 후 → Phase 1.5로 진행

Read the full file on GitHub · 416 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. 12d ago First seen · 416 lines · 164 tokens per session scan A 453d715cdc64

Subscribe to this mod's changes

design-big is a skill published in the GitHub repository MJbae/awesome-novel-studio (147 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 164 tokens to every session and 6,460 once invoked, about $0.0008 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

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

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens