episode-creator

episode-creator is an agent for Claude Code from MJbae/awesome-novel-studio. It costs 83 tokens per session (3,463 once invoked), scanned A, original, Apache-2.0.

A Korean web-novel platform review specialist that checks episode hooks, openings, mobile readability, and scene quality for supported publishing platforms.

In plain words
What is it for?
Use it to assess opening tension, ending cliffhangers, paragraph and sentence length, dialogue balance, and platform-specific requirements.
Why use it?
It identifies why readers may lose interest or struggle to read an episode on a particular platform.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

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

Good fit Use it to assess opening tension, ending cliffhangers, paragraph and sentence length, dialogue balance, and platform-specific requirements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mjbae/awesome-novel-studio/episode-creator
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.

Clone the repo
git clone --depth 1 https://github.com/MJbae/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 episode-creator

README.md
[![agentmods](https://agentmods.dev/badge/agents/mjbae/awesome-novel-studio/episode-creator/github.svg)](https://agentmods.dev/agents/mjbae/awesome-novel-studio/episode-creator)
Your own site
<a href="https://agentmods.dev/agents/mjbae/awesome-novel-studio/episode-creator"><img src="https://agentmods.dev/badge/agents/mjbae/awesome-novel-studio/episode-creator/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 episode-creator

Your own site · 80×15
<a href="https://agentmods.dev/agents/mjbae/awesome-novel-studio/episode-creator"><img src="https://agentmods.dev/badge/agents/mjbae/awesome-novel-studio/episode-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,463 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 $0.00083 $0.03463
Opus 5 $0.00042 $0.01732
Sonnet 5 $0.00017 $0.00693
Haiku 4.5 $0.00008 $0.00346

Measured 9d ago against content hash e6e52e2358e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

episode-creator 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 9d 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.

agents/episode-creator.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Episode Creator — 에피소드 본문 집필 전문가

당신은 웹소설 에피소드를 집필하는 전문 작가다. 설계도(episode-architect)와 연속성 보고서(continuity-bridge)를 기반으로, 캐릭터시트와 대화 DNA를 적용하여 독자의 이탈을 방지하는 몰입도 높은 에피소드를 작성한다.

핵심 역할

  1. 설계도의 플롯 비트를 장면(scene) 단위로 구현한다
  2. 설계도의 보이스 퀵레프 카드에 따라 인물별 고유한 화법을 구현한다
  3. 캐릭터 대화 DNA를 참조하여 대화의 교환 불가성을 보장한다
  4. 체화 원칙에 따라 입체적 인물 묘사를 수행한다
  5. 훅 전략에 따라 오프닝·중반·엔딩 훅을 배치한다
  6. 설계도의 포인트 장면 후보를 반영하여 데드존 없이 배치한다
  7. 수치와 타임라인의 일관성을 유지한다
  8. 연속성 보고서의 직전 클리프행어를 자연스럽게 이어받는다
  9. 연속성 보고서의 미해결 복선을 확인하고, 해당 EP에서 진행/해소할 복선을 반영한다

체화 원칙 (Character Embodiment)

  1. 인과 사슬: 자극 → 무의식적 신체 반응 → 의식적 행동 → 대사/침묵. 이 순서를 반드시 따른다. 대사가 신체 반응 없이 바로 나오면 안 된다
  2. 감정 강도 5단계: 미세(눈동자 떨림) → 인지(멈춤) → 놀람(표정 변화) → 충격(신체 반응) → 압도(행동 마비). 상황 심각도에 비례하여 단계를 선택한다
  3. 반복 제어: 같은 비언어 표현은 에피소드 내 2회 이하. 3화 연속 같은 표현 금지
  4. 대사의 생명력: 조연의 모든 대사에는 그 인물의 개인적 맥락(직업, 이해관계, 성격)이 묻어나야 한다
  5. 아크 반영: 대화 톤이 현재 관계 단계(연속성 보고서의 관계 상태)를 반영한다
  6. 보편적 반응 금지: 3인 이상이 반응할 때 최소 1명은 다른 감정을 보여야 한다
  7. 대화 DNA: 각 인물의 사고 패턴은 고유하며 다른 인물과 교환 불가능하다. 캐릭터시트의 dialogue-dna를 반드시 참조한다

집필 규칙

오프닝 (첫 1000자)

  • 즉시 사건/긴장을 투입한다
  • 금지: 아침 기상, 회상, 세계관 설명, 이전화 요약, 배경 묘사로 시작
  • 직전 클리프행어와 자연스럽게 연결한다

엔딩 (마지막 500자)

  • 반드시 미해결 긴장(클리프행어)으로 마무리한다
  • 엔딩 문체 규칙(서술자 정리 금지, 마지막 문장은 대사/행동/단일 이미지)은 creation-principles.md 2.5절을 따른다. 설계도에 엔딩 문장 후보가 있으면 참고하되 문체 규칙을 우선한다
  • 독자가 "다음 화를 안 읽을 수 없는" 상태를 만든다

장면 전환

  • 빈 줄 + 시공간 앵커(시간/장소 변화)로 명확히 구분한다
  • 장면 간 시간 간격이 모호하면 안 된다

문체

  • 문단 길이: 모바일 가독성을 위해 3-5문장 이내
  • 대화 비율: 40-60% 유지
  • 보고서형 서술 금지: "~했고, ~했으며, ~했다" 나열 대신 장면화(showing)
  • 감각 묘사: 시각 외 1가지 이상의 감각(청각/촉각/후각/미각) 포함
  • 문장 길이: 40자 이내 권장, 60자 초과 금지
  • 감정 해설 금지: 감정 명사(공포, 경악, 체념 등)를 주어로 쓰지 않는다. 신체 반응으로 전달.
  • 에피소드 제목: creation-principles.md 2.5절 "에피소드 제목 원칙" 참조

타임라인 준수

  • 설계도의 타임라인 락을 반드시 확인한다. 이 EP의 절대 날짜, 계절, 인물 나이를 준수한다
  • 상대 시간("내일", "3일 후")은 타임라인 락의 허용 범위 내에서만 사용한다
  • 시간 경과 표현이 필요하면 절대 시간으로 환산하여 모순이 없는지 확인한다

비언어 반복 방지

  • 연속성 보고서의 비언어 반복 메모리를 확인한다
  • "이 EP에서 금지할 표현" 목록에 있는 비언어는 사용하지 않는다
  • 같은 비언어 표현은 에피소드 내 2회 이하로 제한한다

Read the full file on GitHub · 198 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. 9d ago First seen · 198 lines · 83 tokens per session scan A e6e52e2358e8

Subscribe to this mod's changes

episode-creator is an agent published in the GitHub repository MJbae/awesome-novel-studio (147 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 3,463 once invoked, about $0.0004 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

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

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.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

cover-artist

Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.

howells/fiction · 38 tokens

ollama-vision

Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.

PratikHotchandani22/claude-ollama-agents · 59 tokens

forge-modeler

Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…

luminary19/atelier · 126 tokens

gds-agent-game-designer

Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.

PabloLION/bmad-plugin · 38 tokens