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.
curl -O https://raw.githubusercontent.com/ellie1004/fantasy-novel-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/ellie1004/fantasy-novel-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/instructions/ellie1004/fantasy-novel-harness/agents-md)<a href="https://agentmods.dev/instructions/ellie1004/fantasy-novel-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/ellie1004/fantasy-novel-harness/agents-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.
<a href="https://agentmods.dev/instructions/ellie1004/fantasy-novel-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/ellie1004/fantasy-novel-harness/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01007 | $0.01007 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
fantasy-novel-harness AGENTS.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 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Fantasy Novel Harness Multi-Agent Architecture
이 파일은 Claude Code, Cursor, Codex CLI 등 모든 AI 코딩 도구에서 읽힌다.
Agent Roles
📖 Story Architect
- Role: 원고를 분석하고 세계관·캐릭터·플롯을 구조화한다
- Trigger:
input/manuscript.md파일이 존재할 때 자동 활성화 - Reads:
input/manuscript.md,templates/*.md - Writes:
output/design-docs/world-bible.md,output/design-docs/characters.md,output/design-docs/voice-dna.md,output/design-docs/plot-outline.md,output/design-docs/magic-system.md - Rules:
- 원고에 이미 존재하는 설정을 최대한 존중한다
- 빈 부분만 설계로 채운다
- 사용자 확인 없이 원고의 핵심 설정을 변경하지 않는다
✍️ Prose Writer
- Role: 문체를 설정하고 챕터를 집필·리라이팅한다
- Trigger: Step 5~8에서 활성화
- Reads:
output/design-docs/*.md(모든 설계 문서) - Writes:
output/design-docs/prose-profile.md,output/drafts/chapter-*-draft.md,output/drafts/chapter-*-revised.md - Rules:
- 문체 프로필(prose-profile.md)을 반드시 적용한다
- 음성 DNA(voice-dna.md)에 따라 캐릭터 대사를 작성한다
- 장면마다 최소 3가지 감각 묘사를 포함한다
- 삽화 배치 예정 장면은 특히 상세한 시각 묘사를 넣는다
🎨 Illustrator
- Role: 주요 장면을 선정하고 삽화를 생성한다
- Trigger: Step 6 완료 후 자동 활성화 (Step 6.5)
- Reads:
output/drafts/chapter-*-draft.md,output/design-docs/world-bible.md,output/design-docs/characters.md - Writes:
output/illustrations/chapter-*-scene-*.svg,output/illustrations/chapter-*-scene-*.png,output/design-docs/illustration-specs.md - Rules:
- 세계관 바이블의 시각 설정을 엄격히 준수한다
- 캐릭터 외모를 characters.md와 일관되게 유지한다
- 삽화 직전 문단의 묘사와 시각적으로 일치해야 한다
🔍 Quality Auditor
- Role: 산문 진단, 베타 리더 시뮬레이션, 일관성 검증을 수행한다
- Trigger: Step 7, Step 9에서 활성화
- Reads: 모든 산출물
- Writes: 진단 리포트 (대화창 텍스트)
- Rules:
- 다른 에이전트의 산출물을 독립적으로 검증한다
- 긴급 이슈 발견 시 해당 에이전트에게 수정을 요청한다
- 품질 기준 미달 시 Stop 훅에서 완료를 차단한다
Workflow Sequence
User Input (manuscript.md)
↓
[Story Architect] Phase 0: 원고 분석 → analysis-report.md
↓
[Story Architect] Step 1~4: 세계관 → 마법 → 캐릭터 → 플롯
↓
[Prose Writer] Step 5: 문체 프로필 설정
↓
[Prose Writer] Step 6: 챕터 집필
↓
[Illustrator] Step 6.5: 삽화 장면 선정 및 생성
↓
[Quality Auditor] Step 7: 산문 진단
↓
[Prose Writer] Step 8: 리라이팅
↓
[Quality Auditor] Step 9: 베타 리더 시뮬레이션
↓
[All Agents] Step 10: 최종 빌드
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.
- 9d ago First seen · 85 lines · 1,007 tokens per session scan A ad9f17922d32
fantasy-novel-harness AGENTS.md is an instructions file published in the GitHub repository ellie1004/fantasy-novel-harness (4 stars, last pushed 5mo ago), licensed MIT. It adds 1,007 tokens to every session, about $0.0050 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.
Other instructions, from other repositories
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.