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 | $0.00039 | $0.01611 |
| Opus 5.5 | $0.00016 | $0.00644 |
| Sonnet 5.5 | $0.00008 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
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 1mo 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 — 57 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
入口只定义路由、全局不变量和执行边界。references/ 是流程、状态权威关系和领域硬约束的唯一说明层；prompts/ 定义当前任务的输入输出。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。
定位与加载
- 以当前 SKILL.md 的目录为 Skill 根目录，所有资源路径相对此目录解析。
- 第三方许可见
THIRD_PARTY_NOTICES.md，只在处理来源或许可时读取。 - 小说工作区依次采用用户指定路径、
MYNOVEL_WORKSPACE、当前工作区。优先在其中的小说/定位项目，范文位于项目扫描根的范文/。 - 按
references/项目定位.md定位以novel-config.md标识的项目。已知路径直接使用；只有多个候选无法消歧或同章有多个权威正文候选时询问。EPUB 任务定位后直接进入导出路由。 - 选择下表与任务相关的一行及必要前置。只读取对应模式的章节、提示词和脚本契约，不加载整条生产链。脚本调用和写入所需的 schema、哈希与状态条件仍须满足。
任务路由
| 任务 | 参考文档与提示词 |
|---|---|
| rank-scan / 扫榜与开书 | references/开书流程.md；prompts/扫榜与开书构思提示词.md |
| 范文入库、范文拆书、原创仿写、文风蒸馏 | references/范文与创作依据.md 的对应模式；分析时用 prompts/范文结构与文风分析提示词.md，原创规划再用大纲路由 |
| 项目文风确定、融合或修改 | references/范文与创作依据.md 的项目编译模式；prompts/项目文风规范提示词.md |
| 文风校准 | references/范文与创作依据.md 的校准模式；涉及已发生事实时加 references/长篇上下文与一致性.md |
| 新小说初始化、项目迁移 | references/项目定位.md；references/项目结构与迁移.md |
| 总大纲 | prompts/大纲生成提示词.md |
| 系统设计/重构 | references/系统设计与运营.md；prompts/系统设计提示词.md |
| 系统阶段规划 | references/系统设计与运营.md；references/规划窗口与防抢跑.md；prompts/系统阶段规划提示词.md |
| 准备下一窗口、扩窗或锁定预算 | references/规划窗口与防抢跑.md；prompts/规划窗口准备提示词.md |
| 分阶段大纲细化 | references/规划窗口与防抢跑.md；prompts/分阶段大纲细化提示词.md |
| 整理已有细纲 | references/细纲整理流程.md；prompts/分阶段大纲细化提示词.md 的整理模式 |
| 黄金三章微操细纲 | prompts/黄金三章微操细纲提示词.md |
| 正文生成、续写 | references/长篇上下文与一致性.md；references/正文生产与审修.md 的生成流程；references/状态与总结.md；prompts/正文生成提示词.md |
| 手动正文自然化 / 去AI / 去除AI味 | 上述正文上下文协议；references/正文生产与审修.md 的自然化流程；prompts/正文自然化提示词.md |
| 草稿审查、审查并修复、自动修复或修复确认 | references/长篇上下文与一致性.md；references/正文生产与审修.md 的对应模式；正式审修用 prompts/正文审查与修复提示词.md |
| 章节总结、状态更新或会话结束 | references/状态与总结.md |
| 一致性检查 | references/长篇上下文与一致性.md |
| EPUB 导出与同步 | references/EPUB导出与同步.md |
创建目录、归档、事务或配置时，按 references/项目结构与迁移.md 查对应 schema；运行验证或事务脚本时查 references/自动化脚本契约.md，资源不适用时说明原因。
创作与状态边界
- 正文服从本章正式细纲和已发生事实，不自行新增主线事件、角色、设定、能力或伏笔；归档只修改目标章节或锚点块。
- 新书先满足 30 天内有效扫榜的开书条件；新规划窗口依次完成系统阶段规划、总纲/manifest扩窗锁定、分阶段细纲。范围与前置验证由对应参考文档规定。
- 正文生成每次请求最多 5 章，超过时按现有创作协议要求拆分；审查和修复按连续最多 5 章自动分批，完成用户指定范围。50 章仍是大纲、总结和报告的归档单位。
- 普通写作只完成创作及逐章状态提交，记为
review_pending；该状态不阻断续写，不补审，不得自动读取或调用自然化提示词。生成稿的 source 与 candidate 相同，事实锁、候选验证、总结和独立状态回证按正文流程执行。 - 待审正文必须保留
（草稿）.md；只有两份正式审查通过、候选验证通过且登记review_passed才去掉草稿标识。正文哈希变化使旧审查失效。 - 当前可见稿与 committed 哈希不同时，审查走
working_copy模式，不推进正式链。用户要求修复已授权 repair 修订及必要的可回滚 shadow rebase；只有真实后文冲突无法裁决时才询问。
What ships with it
22 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.
- references/EPUB导出与同步.md 4.0 KB
- references/开书流程.md 4.9 KB
- references/正文生产与审修.md 18 KB
- references/状态与总结.md 5.2 KB
- references/系统设计与运营.md 10 KB
- references/细纲整理流程.md 1.2 KB
- references/自动化脚本契约.md 15 KB
- references/范文与创作依据.md 37 KB
- references/规划窗口与防抢跑.md 8.3 KB
- references/长篇上下文与一致性.md 9.8 KB
- references/项目定位.md 3.6 KB
- references/项目结构与迁移.md 18 KB
- scripts/count_chars.py 1017 B runs code
- scripts/migrate_plan_nodes.py 2.0 KB runs code
- scripts/refresh_genesis_projection.py 2.3 KB runs code
- scripts/validate_chapter_candidate.py 42 KB runs code
- scripts/validate_project.py 29 KB runs code
- scripts/公共工具.py 1.3 KB runs code
- scripts/原文重合检查.py 11 KB runs code
- scripts/扫榜.py 16 KB runs code
- scripts/文风统计.py 17 KB runs code
- scripts/项目事务.py 40 KB runs code
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.
- 1mo ago Changed · -46 lines · -86 tokens per session ce4e52ef550c
- 1mo 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 (75 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,611 once invoked, about $0.0002 per session on Opus 5.5. 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-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-setup
A setup tool for deploying a Chinese web-fiction writing toolkit into a project. It configures supported coding agents and uses shared files for environments without a dedicated integration.