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 LiPu-jpg/Openwrite --skill novel-creatorgit clone --depth 1 https://github.com/LiPu-jpg/OpenwriteWrote 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/lipu-jpg/openwrite/novel-creator)<a href="https://agentmods.dev/skills/lipu-jpg/openwrite/novel-creator"><img src="https://agentmods.dev/badge/skills/lipu-jpg/openwrite/novel-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.
<a href="https://agentmods.dev/skills/lipu-jpg/openwrite/novel-creator"><img src="https://agentmods.dev/badge/skills/lipu-jpg/openwrite/novel-creator.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 | $0.00044 | $0.01148 |
| Opus 5 | $0.00022 | $0.00574 |
| Sonnet 5 | $0.00009 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
novel-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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小说创作编排
通过 openwrite-bridge 的 novel_* 工具写章。不要调用 Python 模块、内置 Writer 类或已废弃的大纲命令。
所有正文写入走预览/确认门控；已有正文不得覆盖。
触发条件
- "写第X章" / "写章节"
- "生成章节" / "生成草稿"
- "续写" / "继续创作"
- "创作" + 章节相关
工作流程
novel_status看项目阶段、资产缺口、待确认项。novel_outline_read定位章纲：未指定章节时取大纲顺序中最早尚无正文的章；指定章节时校验章纲存在。已有正文则打开或审查，不得直接覆盖。novel_context_preview预检写章上下文包（大纲窗口、出场角色、伏笔、风格、正典）。novel_chapter_work读取本章到期/超期/待埋入伏笔与字数目标。novel_write_chapter写下一章或指定章（可带outline_revision与guidance）。- 草稿出来后暂停，请作者选择：通过进入评审、按意见重写、或到创作页手工编辑。
- 作者通过后调用
novel_review_chapter；需要改稿时用novel_revision_create_from_review，确认后再novel_revision_apply。
工具
| 工具 | 用途 |
|---|---|
novel_status |
项目快照、阶段、缺口 |
novel_outline_read |
大纲树与建议下一章 |
novel_context_preview |
写前上下文包 |
novel_chapter_work |
本章目标、伏笔义务、最近修改 |
novel_write_chapter |
写章（长耗时） |
novel_review_chapter |
六域累加评审 |
novel_document_change_plan |
已有正文的逐项预览/确认修改 |
novel_structured_change_plan |
大纲/资产/伏笔的逐项预览/确认 |
novel_doc_write 与 novel_outline_edit 仅在作者本轮已明确授权精确变更时作为直接写入兼容入口。
节拍
从大纲读取本章 dramatic_position（起/承/转/合/过渡）和内容焦点。
节拍数量由目标字数决定（3000 以下 2–3 个；3000–5000 为 3–4 个；5000+ 为 4–6 个），写入 novel_write_chapter 的 guidance。
- 起 → 场景切入 + 悬念铺设 + 角色状态 + 衔接钩子
- 承 → 推进 + 碰撞 + (伏笔) + 递进
- 转 → 升级 + 核心决策 + 后果初现
- 合 → 余波 + 变化确认 + 遗留
用户审核（强制）
草稿生成后必须暂停：
章节: {chapter_id}
字数: {word_count}
请选择：1 通过并评审 2 按意见重写 3 保存后手工编辑
前置条件
| 数据 | 必须？ | 如何确认 |
|---|---|---|
| 大纲 | 必须 | novel_outline_read |
| 本章出场角色 | 必须 | novel_context_preview / novel_assets_list |
| 合成风格 | 建议 | 上下文包 |
| 伏笔 | 可选 | novel_chapter_work 的分类义务 |
资产不齐时先规划补齐，不切换会话。novel_status 若显示 outline_scope 待确认，先让作者确认大纲范围再写。
错误处理
| 情况 | 处理 |
|---|---|
| 上下文超限 | 报告 novel_context_preview 的压缩/保护原因，不静默丢掉正典 |
| 章纲缺失 | 回到规划，用 novel_structured_change_plan(change_kind="outline") |
| 已有正文 | 打开或审查；改稿走 novel_document_change_plan |
| 写章失败 | 用 novel_tasks_list / novel_task_get 查看后台任务，可 novel_task_retry |
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.
- yesterday Changed · -185 lines cc46f7ca2a8e
- 4d ago Changed · -7 lines cfacba3e6d6c
- 11d ago First seen · 280 lines · 44 tokens per session scan A df370f354a7e
novel-creator is a skill published in the GitHub repository LiPu-jpg/Openwrite (709 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 1,148 once invoked, about $0.0002 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
awesome-novel
A nine-agent workflow for writing a novel with AI, from creating the initial setting through organizing the finished material. It can also bring an existing novel into the workflow.
audit-playbook
A code-security audit playbook covering source-code review, runtime checks, software dependencies, deployment settings, and AI-agent security risks.
ida-reversing
Perform reverse engineering and binary analysis in IDA Pro using natural language commands powered by IDA MCP. Use this skill whenever the user wants to: analyze executable files, understand function behavior, decompile code, explore cross-references, search for strings or bytes, patch binary code, document reverse…
workflow
A command set for starting and managing step-by-step automated workflows.
local-search
A local search component that finds web results using installed command-line tools and page parsers. It supports general web search and extra sources for areas such as Chinese pages, news, code questions, academic work, and reference material.
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…