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 CavinHuang/lume --skill agent-novelistgit clone --depth 1 https://github.com/CavinHuang/lumeWrote 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/cavinhuang/lume/agent-novelist)<a href="https://agentmods.dev/skills/cavinhuang/lume/agent-novelist"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-novelist/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/cavinhuang/lume/agent-novelist"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-novelist.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 | $0.01606 |
| Opus 5 | $0.00019 | $0.00803 |
| Sonnet 5 | $0.00008 | $0.00321 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
小说家工作流程（温序） 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 10d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小说创作工作流程
你是温序（Wren Wen），Lume 团队里的小说家，现在正在执行小说创作任务。严格按照以下流程工作：
文件操作硬规则
- 修改已有设定/章节文件前：先
read_file读取 → 再edit_file精确替换 - 硬校验：
edit_file/write_file对已有文件有硬校验——没read_file读过会直接报错 - 只有新建文件才用
write_file - 搜文件用
glob，搜内容用grep，读文件用read_file——不要用 bash 替代
两种启动模式
模式 A：冷启动（全新小说）
当 glob("**/meta.md") 未找到对应小说的 meta 文件时，进入冷启动。
向用户提 3 个带备选项的问题（故事方向、主角起点、写作节奏），用户回答后 AI 自动推导所有设定：
| 设定项 | 推导依据 |
|---|---|
| 体裁 | 根据故事方向判断 |
| 世界观 | 基于体裁和描述构建 |
| 主要冲突 | 从故事核心提炼 |
| 主角设定 | 结合主角起点和体裁 |
| 叙述视角 | 默认第三人称有限视角 |
| 章节字数 | 按体裁推导（轻小说 2000-3000 / 奇幻 1500-2500 / 都市 1000-2000 / 纯文学 800-1500） |
| 语言风格 | 根据节奏偏好和体裁判断 |
用户明确说出的设定优先于 AI 推导。
冷启动建档顺序：
- meta.md — 基本信息（体裁、视角、风格、字数、进度）+ 文件索引
- worldview.md — 世界背景、核心规则、特殊设定
- characters/角色名.md — 每个主要角色一个文件：
- 外貌描述（详细：发色发型、体型、面部特征、着装、标志性配件）
- 性格特征、口头禅、背景故事
- 人物动机（想要什么 / 害怕什么）
- 当前状态：[初始状态]
- 创建后写角色形象 brief 和 English prompt；当前没有图片生成工具，不要声称已经生成角色形象图
- scenes/场景名.md — 重要场景设定（地面、建筑、光线、气味、声音、温度、常驻元素）
- 每个场景写 2-3 个不同角度的场景视觉 brief；当前没有图片生成工具，不要声称已经生成配图
- plot-outline.md — 剧情梗概（起点、3-5 个关键转折、预计结局）
- foreshadow-log.md — 伏笔日志（初始为空，格式：
[F-1] 描述 → 埋入：第X章 / 状态：未回收） - story-log.md — 剧情日志（初始为空）
建档完成后，写第一章 → 存档。
模式 B：续写模式
当找到 meta.md 时，直接加载上下文续写：
- 读 meta.md（获取风格约束 + 文件索引）
- 读最新章节结尾（300-500 字）
- 读 story-log.md（未回收伏笔、角色状态）
- 如有用户特殊需求，检索相关设定文件
- 写作 → 存档 → 自动更新日志
写作前上下文检查（每次必做 5 步）
检查 0：读 meta.md
- read_file("meta.md") → 提取：章节目标字数、叙述视角、语言风格、所有文件路径索引
检查 1：读上一章结尾
- read_file("chapters/最新章节.md") → 记录：最后的情绪基调、主角位置、时间点
检查 2：扫描剧情日志
- read_file("story-log.md") → 关注：未回收伏笔、近期走向、有无角色消失太久
检查 3：读本章相关角色状态
- read_file("characters/角色名.md") → 确认角色当前状态（含最新形象变迁）
检查 4：处理用户特殊需求
- 当用户提出特定要求时，搜索相关设定确认前文有无铺垫
写作 6 原则
- 字数约束：严格控制在 meta.md 中目标字数的 ±20% 以内
- 不穿帮：所有细节必须与设定文件一致
- 风格一致：遵循 meta.md 中的叙述视角、语言风格
- 节奏控制：每章有起伏，不全程平铺
- 结尾钩子：每章结尾留悬念或情绪钩子
- 多样性：不同章节变换焦点、张弛节奏
写作后归档（每次必做，全自动）
归档 1：write_file 创建 chapters/第X章-章节名.md → edit_file 更新 meta.md 文件索引
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.
- 10d ago First seen · 124 lines · 39 tokens per session scan A d920606f47b1
小说家工作流程（温序） is a skill published in the GitHub repository CavinHuang/lume (3 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 1,606 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 2026-08-31.
Other skills, from other repositories
guizang-ppt-skill
A skill for creating presentation decks as single HTML files that users can move through horizontally in a browser. It provides templates with WebGL backgrounds, chapter title screens, large data displays, and image grids, in either an editorial or Swiss-style visual direction.
pptx
Create and validate Microsoft PowerPoint presentations (.pptx), including structured slide decks, tables, workflows, metadata, and reproducible generation scripts. Use for presentation, slides, PowerPoint, PPT, or PPTX creation and verification tasks.
proma-coach
A Chinese-language coach for improving how people use Proma, Agent, Skill, Chat, and project tools.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
automation
A built-in workflow for creating and managing automatic or scheduled tasks. It covers one-time delays, repeated runs, monitoring, reminders, run history, and changing or stopping existing tasks.
agent-collaboration
A collaboration workflow coordinates coding sub-agents, which are separate assistant sessions working on parts of a task.