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 skills add Xiaoyangy/novel-studio --skill novel-writegit clone --depth 1 https://github.com/Xiaoyangy/novel-studioWrote 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/skills/xiaoyangy/novel-studio/novel-write)<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/novel-write"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/novel-write/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/skills/xiaoyangy/novel-studio/novel-write"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/novel-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.00814 |
| Opus 5 | $0.00037 | $0.00407 |
| Sonnet 5 | $0.00015 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
novel-write 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.
What it actually says
novel-write：单句需求跑一次 pipeline 创作
把用户的创作要求作为 prompt 交给 novel-studio --pipeline，由 pipeline 编排写作、评审、
重写和导出。章节落盘到 output/novel/chapters/*.md。无 TTY，可在 CI / 远程 agent 中运行。
--headless --prompt只保留为兼容别名，命令层会转入 pipeline。新任务一律直接调用--pipeline，不要绕过流水线。
前置条件
- 已完成首次配置（见
skills/README.md）。headless 不支持首次引导。
执行
# 直接传文本
novel-studio --pipeline --prompt "写一个赛博朋克背景、主角是义体黑客的长篇开篇"
# 从文件读 prompt（长需求/含换行时推荐）
novel-studio --pipeline --prompt-file ./requirement.md
# 从 stdin 读
echo "需求文本" | novel-studio --pipeline --prompt-file -
参数
| 参数 | 说明 |
|---|---|
--prompt <text> |
单句创作需求；与 --prompt-file 互斥 |
--prompt-file <path> |
从文件读需求，- 表示 stdin |
--stages <list> |
可选，默认 write,review,rewrite,deliver |
--config <path> |
可选，指定配置文件 |
产物
- 章节：
output/novel/chapters/*.md - 写法资产：
output/novel/meta/writing_assets.json（可编辑、复用、由弧摘要持续沉淀） - 人工感写法参考：内置
assets/references/human-feel-craft.md会随reference_pack.references.human_feel_craft注入，迁移《同桌是只假装高冷的猫》的物件回扣、主观误判、短对话和现实支架，避免正文只靠解释和模板情绪推进。 - reference-library 写作技巧总纲：内置
assets/references/refer-writing-techniques-digest.md会随reference_pack.references.writing_techniques_digest注入，来自data/reference-library/writing-craft19 篇逐篇提炼，约束全书设计、大纲、人物、单章目标/阻力/代价/新增信息、事件余波和中文标点功能。 - 本书世界：
output/novel/book_world.json（地图、地点、路线、势力图谱） - 资源账本：
output/novel/meta/resource_ledger.json（已入账事实与待确认提案分离） - RAG trace：
output/novel/meta/rag/retrieval_trace.jsonl（召回命中原因） - 运行日志：项目目录下
headless.log
失败排查
- 报「首次启动需要先在交互终端运行一次 novel-studio 完成配置引导」→ 先在交互终端跑一次
novel-studio完成 stdin 配置，或手写~/.novel-studio/config.json。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 54 lines · 75 tokens per session scan A d9315af7c72a
novel-write is a skill published in the GitHub repository Xiaoyangy/novel-studio (102 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 814 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.
Other skills, from other repositories
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-cover
A novel-cover generator that creates a cover with the book title and author name. It chooses a visual style from the book information and can use Codex's image-generation tool.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
html-artifact
Create polished single-file HTML artifacts for plans, reports, explainers, code reviews, lightweight dashboards, prototypes, and one-off editing tools. Use when the user asks for a standalone HTML file, single HTML, HTML artifact, interactive report, shareable local artifact, Alpine.js artifact, custom CSS artifact…
ocr
A decision guide for choosing between OCR, which reads text from an image, and visual description, which explains what a scene or object shows. It also covers cases where both kinds of understanding are needed.
video-generation
Guide to video generation in MassGen. Use when creating videos from text prompts or images across Grok, Google Veo, and OpenAI Sora backends.