What is fantasy-novel-harness CLAUDE.md?

A set of instructions for an AI-assisted system that turns a fantasy novel idea or draft into a structured, illustrated book. It defines writing stages, agent roles, project files, and checks.

Use it to plan a fantasy world, characters, magic, plot, chapters, illustrations, and final book files such as Markdown, PDF, or DOCX.

It gives the agent a fixed writing process and consistency checks, reducing the risk of missing story planning, breaking established details, or producing incomplete output.

How ellie1004/fantasy-novel-harness configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ellie1004/fantasy-novel-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ellie1004/fantasy-novel-harness/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ellie1004/fantasy-novel-harness

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ellie1004/fantasy-novel-harness/claude-md/github.svg)](https://agentmods.dev/instructions/ellie1004/fantasy-novel-harness/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ellie1004/fantasy-novel-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/ellie1004/fantasy-novel-harness/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ellie1004/fantasy-novel-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/ellie1004/fantasy-novel-harness/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,529 This file is loaded in full into every session.

When invoked 6,529 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.06529	$0.06529
Opus 5	$0.03265	$0.03265
Sonnet 5	$0.01306	$0.01306
Haiku 4.5	$0.00653	$0.00653

Measured 10d ago against content hash 21d592ba725d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fantasy-novel-harness CLAUDE.md 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 10d 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.md · 593 lines

How it starts

The opening of the file, as written. The whole thing — 593 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🏗️ Fantasy Novel Harness Engineering System

삽화가 포함된 판타지 소설 자동 집필 시스템

하네스 엔지니어링(Harness Engineering): AI 에이전트의 행동을 '제안(Suggestion)'이 아닌 '기계적 강제(Mechanical Enforcement)'로 제어하는 시스템 설계 방법론. CLAUDE.md는 에이전트에게 방향성을 제시하는 제안이며, 절대 어겨서는 안 되는 규칙은 Hooks·Linter·CI/CD로 강제한다.

📌 프로젝트 개요

이 프로젝트는 사용자가 자유롭게 작성한 판타지 소설 원고(또는 아이디어)를 입력하면, AI 에이전트가 다음을 자동으로 수행하는 엔드투엔드 소설 집필 시스템이다:

원고 분석 → 세계관·캐릭터·플롯을 구조화
10단계 집필 워크플로우 → 체계적 소설 완성
삽화 자동 생성 → 주요 장면을 일러스트레이션으로 시각화
최종 출력 → 삽화가 포함된 완성 소설 (.docx / .md / .pdf)

누구나 이 레포를 클론하고 Claude Code 또는 Cursor CLI에서 실행하면, 한 권의 멋진 삽화 판타지 소설을 만들 수 있다.

🗂️ 프로젝트 구조

fantasy-novel-harness/
├── CLAUDE.md                          # ← 지금 이 파일 (에이전트 제안)
├── AGENTS.md                          # 멀티 에이전트 역할 정의
├── .claude/
│   └── settings.json                  # 훅 설정 (기계적 강제)
├── .cursor/
│   └── rules/
│       ├── novel-workflow.mdc         # Cursor용 소설 집필 규칙
│       └── illustration.mdc          # Cursor용 삽화 생성 규칙
├── hooks/
│   ├── pre-write-validator.sh         # PreToolUse: 집필 전 일관성 검증
│   ├── post-write-quality.sh          # PostToolUse: 산문 품질 자동 체크
│   ├── illustration-guard.sh          # PreToolUse: 삽화 프롬프트 검증
│   └── stop-final-check.sh            # Stop: 최종 완성도 체크
├── scripts/
│   ├── analyze-manuscript.py          # 원고 분석 스크립트
│   ├── generate-illustration.py       # 삽화 생성 스크립트
│   ├── consistency-checker.py         # 일관성 검증 스크립트
│   ├── prose-diagnostics.py           # 산문 진단 스크립트
│   └── build-novel.py                 # 최종 소설 빌드 스크립트
├── templates/
│   ├── world-bible.md                 # 세계관 바이블 템플릿
│   ├── character-sheet.md             # 캐릭터 시트 템플릿
│   ├── voice-dna.md                   # 음성 DNA 카드 템플릿
│   ├── plot-outline.md                # 플롯 아웃라인 템플릿
│   ├── prose-profile.md               # 문체 프로필 템플릿
│   ├── chapter-draft.md               # 챕터 초안 템플릿
│   └── illustration-spec.md           # 삽화 스펙 템플릿
├── output/
│   ├── drafts/                        # 챕터별 초안
│   ├── illustrations/                 # 생성된 삽화 이미지
│   ├── design-docs/                   # 세계관·캐릭터·플롯 문서
│   └── final/                         # 최종 완성본
├── input/
│   └── manuscript.md                  # 사용자 원고 입력 위치
├── tests/
│   ├── test-consistency.py            # 일관성 테스트
│   ├── test-prose-quality.py          # 산문 품질 테스트
│   └── test-illustration-spec.py      # 삽화 스펙 테스트
├── package.json                       # Node.js 의존성
├── requirements.txt                   # Python 의존성
├── LICENSE                            # MIT License
└── README.md                          # 사용 가이드

Read the full file on GitHub · 593 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.

10d ago First seen · 593 lines · 6,529 tokens per session scan A 21d592ba725d

Subscribe to this mod's changes

fantasy-novel-harness CLAUDE.md is an instructions file published in the GitHub repository ellie1004/fantasy-novel-harness (4 stars, last pushed 5mo ago), licensed MIT. It adds 6,529 tokens to every session, about $0.0326 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 2026-08-31.

Creative and media Writing and docs

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

fantasy-novel-harness: Instructions file for Claude Code