novel-cocreate

novel-cocreate is a skill for Claude Code, Codex from Xiaoyangy/novel-studio. It costs 92 tokens per session (551 once invoked), scanned A, original, Apache-2.0.

A conversational planning workflow for turning a vague book idea into a detailed writing brief. The agent asks questions over several turns and saves the finished brief for later novel creation.

In plain words
What is it for?
Clarifying genre, theme, audience, plot direction, voice, and boundaries before starting a novel, either interactively or as the first stage of a full pipeline.
Why use it?
It helps when the author has only a rough idea and a single prompt would leave important choices unclear. The saved brief can be used directly by the larger writing workflow.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Clarifying genre, theme, audience, plot direction, voice, and boundaries before starting a novel, either interactively or as the first stage of a full pipeline.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiaoyangy/novel-studio/novel-cocreate
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.

Any agent
npx skills add Xiaoyangy/novel-studio --skill novel-cocreate
Clone the repo
git clone --depth 1 https://github.com/Xiaoyangy/novel-studio

Made for: Claude Code, Codex.

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 novel-cocreate

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/novel-cocreate/github.svg)](https://agentmods.dev/skills/xiaoyangy/novel-studio/novel-cocreate)
Your own site
<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/novel-cocreate"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/novel-cocreate/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 novel-cocreate

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/novel-cocreate"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/novel-cocreate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 551 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00092 $0.00551
Opus 5 $0.00046 $0.00275
Sonnet 5 $0.00018 $0.00110
Haiku 4.5 $0.00009 $0.00055

Measured 11d ago against content hash d3723efad908, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

novel-cocreate 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 11d 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/novel-cocreate/SKILL.md · 40 lines

What it actually says

novel-cocreate:共创规划(多轮澄清)

与 AI 多轮对话澄清需求:AI 主动追问 + 给 1-3 条引导建议,逐轮把模糊想法收敛成一份高质量的 "整本书创作指令"草稿。定稿后落盘 meta/cocreate-prompt.txt,可直接进入 pipeline 创作。 等价于把一次性 --pipeline --prompt 的"一句话"升级成"聊出来的完整指令"。

前置条件

  • 已完成首次配置(见 skills/README.md),且 LLM 可用(先 novel-check)。
  • 需要交互终端(stdin):这是多轮 REPL,不适合纯管道。

执行

# 给个初始想法开始(也可不带,进入后再输入)
novel-studio --cocreate "我想写一个赛博朋克背景、主角是义体黑客的悬疑长篇"

# 定稿后立即进入创作
novel-studio --cocreate "..." --start

对话中的命令

输入 作用
直接回复 回答 AI 的追问,推进澄清
/draft 查看当前累积的创作指令草稿
/done 草稿成形后定稿(落盘 + 退出 / 进入创作)
/quit 放弃本次共创

产物与衔接

  • 创作指令草稿:output/novel/meta/cocreate-prompt.txt
  • 不带 --start 时,可稍后用 novel-studio --pipeline --prompt-file output/novel/meta/cocreate-prompt.txt 创作
  • 也可作为 --pipeline 的首阶段:novel-studio --pipeline --stages cocreate,write,review,rewrite,deliver
Files

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.

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. 11d ago First seen · 40 lines · 92 tokens per session scan A d3723efad908

Subscribe to this mod's changes

novel-cocreate is a skill published in the GitHub repository Xiaoyangy/novel-studio (107 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 551 once invoked, about $0.0005 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.