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 xiaofeng-928/chinese-longnovel-skill --skill chinese-longnovel-skillgit clone --depth 1 https://github.com/xiaofeng-928/chinese-longnovel-skillWrote 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/xiaofeng-928/chinese-longnovel-skill/chinese-longnovel-skill)<a href="https://agentmods.dev/skills/xiaofeng-928/chinese-longnovel-skill/chinese-longnovel-skill"><img src="https://agentmods.dev/badge/skills/xiaofeng-928/chinese-longnovel-skill/chinese-longnovel-skill/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/xiaofeng-928/chinese-longnovel-skill/chinese-longnovel-skill"><img src="https://agentmods.dev/badge/skills/xiaofeng-928/chinese-longnovel-skill/chinese-longnovel-skill.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 | $0.00125 | $0.03411 |
| Opus 5 | $0.00063 | $0.01706 |
| Sonnet 5 | $0.00025 | $0.00682 |
| Haiku 4.5 | $0.00013 | $0.00341 |
Grade A, and why
my-novel 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 13d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MyNovel 长篇网络小说工作流
先定位项目和用户意图，再按路由读取所需资源。入口只定义路由、全局不变量和执行边界；具体领域规则由对应 references/ 文档负责，执行模板由对应 prompts/ 文件负责。
目录
- Skill 根目录：当前
SKILL.md所在目录；引用prompts/、references/、scripts/时都相对此目录解析，不硬编码安装路径 - 提示词：
prompts/ - 参考文档：
references/ - 通用脚本：
scripts/ - 第三方许可：
THIRD_PARTY_NOTICES.md（不进入正文运行上下文） - 小说工作区：优先使用用户明确指定的路径，其次使用环境变量
MYNOVEL_WORKSPACE，否则使用当前工作区 - 长篇项目根目录：小说工作区内的
小说/；若不存在该层，则直接以小说工作区为项目扫描根 - 长篇范文库：长篇项目根目录内的
范文/
启动与加载
- 非小说对象退出本 Skill。
- 小说任务先完整读取
references/项目定位.md并定位唯一项目；存在多个候选且用户未指定时先询问。 - 根据下表选择唯一主路由，完整读取该行列出的参考文档和提示词。只加载当前任务所需资源，不预读其他工作流。
- 路由文档声明条件性前置流程时，先完成前置流程，再返回当前路由。
- 意图或项目明确且用户要求直接执行时直接开始；明确的写作、续写、审查或修复任务不做启动确认，也不得因存在
review_pending节点询问是否先审查。只有意图确实无法判断时才确认一次。
规则归属
- 本入口只保存所有长篇任务都需要知道的规则；不得把单一题材、金手指、文风、角色、状态仓库或某一生产阶段的细则追加到入口。
references/是流程、状态权威关系和领域硬约束的唯一说明层。prompts/只定义该任务的输入、输出和执行约束；与参考文档冲突时，以参考文档和项目内已发生事实为准。scripts/只提供确定性事实与证据；脚本适用性和失败处理以references/自动化脚本契约.md为准。
全局不变量
- 搜索小说工作区时遵守当前工作区的
AGENTS.md；没有额外约束时使用所在平台可用的原生文件和文本搜索工具。 - 修改正文、总结、配置或大纲前先完成项目定位；同一章存在多个正文文件时停止并让用户确认权威文件。
- 正文生成、续写、草稿审查和自动修复不得跳过
references/长篇上下文与一致性.md；有效节点顺序以references/长篇上下文与一致性.md为准。 - 正文必须服从本章正式细纲和已发生事实；不得擅自新增主线事件、角色、设定、能力或伏笔。
- 写入归档文件时只替换目标章节或目标锚点块，不覆盖无关内容，不重复追加或破坏 HTML 锚点。
执行范围
| 任务 | 单次上限 | 超限处理 |
|---|---|---|
| 正文生成或续写 | 5 章 | 停止并要求拆分 |
| 草稿审查或自动修复 | 每个子批 5 章 | 按连续 5 章拆分执行 |
| 分阶段大纲细化 | 50 章 | 按 50 章归档段拆分 |
章节范围按 references/长篇上下文与一致性.md 的有效节点解析；正文单个请求最多 5 章，审查/修复每个子批最多 5 章，大纲、总结和审查报告仍按 50 章文件归档。
智能路由
| 用户意图 | 工作流 | 必读参考文档 | 必读提示词 |
|---|---|---|---|
| rank-scan / 扫榜与选题 / 确定题材 / 开新书 | 扫榜与开书 | references/开书流程.md |
prompts/扫榜与开书构思提示词.md |
| 装书 / 导入长篇范文 / 范文入库 | 范文入库 | references/范文与创作依据.md、references/项目结构与迁移.md |
有合法正文时读 prompts/范文结构与文风分析提示词.md |
| 拆书 / 深度拆解范文 / 分析爆款结构 | 范文拆书 | references/范文与创作依据.md |
prompts/范文结构与文风分析提示词.md |
| 文风蒸馏 / 生成文风基因 / 更新范文文风档案 | 文风蒸馏 | references/范文与创作依据.md、references/项目结构与迁移.md |
prompts/范文结构与文风分析提示词.md |
| 仿写 / 对标范文开原创长篇 | 原创仿写 | references/范文与创作依据.md、references/项目定位.md、references/项目结构与迁移.md |
prompts/范文结构与文风分析提示词.md、prompts/大纲生成提示词.md |
| 确定或融合项目文风 / 修改后续文风 | 项目文风确定 | references/范文与创作依据.md、references/项目定位.md、references/项目结构与迁移.md |
prompts/项目文风规范提示词.md |
| 文风校准 / 连续章节文风偏移 | 文风校准 | references/范文与创作依据.md、references/长篇上下文与一致性.md |
无 |
| 新小说 / 新建小说 / 粘贴新总大纲 | 新小说初始化 | references/项目定位.md、references/项目结构与迁移.md |
无 |
| 大纲 / 总大纲 / 规划剧情 | 大纲生成 | references/项目定位.md |
prompts/大纲生成提示词.md |
| 设计系统或金手指 / 重构系统 | 系统设计/重构 | references/项目定位.md、references/系统设计与运营.md |
prompts/系统设计提示词.md |
| 规划阶段系统发展 | 系统阶段规划 | references/项目定位.md、references/项目结构与迁移.md、references/系统设计与运营.md |
prompts/系统阶段规划提示词.md |
| 细化大纲 / 第X-X章大纲 | 分阶段大纲细化 | references/项目定位.md、references/项目结构与迁移.md |
prompts/分阶段大纲细化提示词.md |
| 整理手写或笼统细纲 | 细纲整理 | references/项目定位.md、references/项目结构与迁移.md、references/细纲整理流程.md、references/长篇上下文与一致性.md |
prompts/分阶段大纲细化提示词.md（整理既有细纲模式） |
| 黄金三章 / 前三章微操 | 黄金三章微操细纲 | references/项目定位.md、references/项目结构与迁移.md |
prompts/黄金三章微操细纲提示词.md |
| 写第X章 / 正文 / 写下一章 | 正文生成 | references/长篇上下文与一致性.md、references/正文生产与审修.md、references/状态与总结.md |
prompts/正文生成提示词.md |
| 自然化 / 去AI / 去除AI味 / 手动润稿 | 手动正文自然化 | references/长篇上下文与一致性.md、references/正文生产与审修.md、references/状态与总结.md、references/项目结构与迁移.md |
prompts/正文自然化提示词.md |
| 审查草稿 / 检查草稿 | 草稿审查 | references/长篇上下文与一致性.md、references/正文生产与审修.md、references/项目结构与迁移.md、references/自动化脚本契约.md |
prompts/正文审查与修复提示词.md |
| 审查并修复 / review and fix | 草稿审查后自动修复 | references/长篇上下文与一致性.md、references/正文生产与审修.md、references/状态与总结.md |
prompts/正文审查与修复提示词.md |
| 修复第X章 / fix / 修复自然化或审查发现的问题 | 自动修复 | references/长篇上下文与一致性.md、references/正文生产与审修.md |
prompts/正文审查与修复提示词.md |
| 修好了 / 已修复 / 修改完毕 | 修复确认 | references/正文生产与审修.md、references/项目结构与迁移.md |
无 |
| 总结第X章 / 章节总结 | 章节总结 | references/状态与总结.md、references/项目结构与迁移.md |
无 |
| 一致性 / 矛盾 / 对不上 | 一致性检查 | references/长篇上下文与一致性.md |
无 |
| 续写 / 继续写 / 接着写 | 续写并提交创作节点 | references/长篇上下文与一致性.md、references/正文生产与审修.md、references/状态与总结.md |
prompts/正文生成提示词.md |
| 今天小说就到这 / 本轮章节结束 | 会话结束流程 | references/状态与总结.md、references/项目结构与迁移.md |
无 |
| 生成 EPUB / 导出电子书 | EPUB 导出与同步 | references/EPUB导出与同步.md、references/项目结构与迁移.md |
无 |
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.
- 13d ago First seen · 103 lines · 125 tokens per session scan A 09e1303470e1
my-novel is a skill published in the GitHub repository xiaofeng-928/chinese-longnovel-skill (67 stars, last pushed 22d ago), licensed MIT. It adds 125 tokens to every session and 3,411 once invoked, about $0.0006 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
zh-novel-polish
A Chinese fiction editing tool focused on making narrative prose sound like it was written by a person rather than generated by AI.
novel-review
A review coordinator for long novels. It breaks a manuscript review into focused checks by specialist roles, combines their reports, and stores the results in a review directory.
novel-sync
A Chinese-language workflow for updating a novel's continuity notes after a chapter is written or changed. It records events, character changes, unresolved clues, and notable lines in the project's reference files.
novel-plan
A planning workflow for designing a new long-form novel before writing it. It helps settle the premise, setting, character, progression, ending, outline, and writing approach, then tests the setting for logical problems.
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
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.