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 TulanCN/vibe-noveling --skill novel-writegit clone --depth 1 https://github.com/TulanCN/vibe-novelingWrote 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/tulancn/vibe-noveling/novel-write)<a href="https://agentmods.dev/skills/tulancn/vibe-noveling/novel-write"><img src="https://agentmods.dev/badge/skills/tulancn/vibe-noveling/novel-write/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/tulancn/vibe-noveling/novel-write"><img src="https://agentmods.dev/badge/skills/tulancn/vibe-noveling/novel-write.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 | $0.00051 | $0.01948 |
| Opus 5 | $0.00026 | $0.00974 |
| Sonnet 5 | $0.00010 | $0.00390 |
| Haiku 4.5 | $0.00005 | $0.00195 |
Grade A, and why
novel-write 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
章节创作
本章负责一件事：把剧情链展开为具象的、可阅读的小说正文。 补环境、感官、动作链、台词；保持角色声线和设定一致；避免 AI 腔。
第一步：准备
- 读当前事件卡
memory/future/40-events/对应文件，提取本章剧情链。 草稿防护：先看「定位」区设计阶段字段——若不是done，或本章「章节拆分」下的剧情链仍是占位（含待 L或剧情链待 L4 推导字样），说明事件设计未完成。停下，不要写正文，也不要自己补剧情链，提示用户："事件 E0X 的设计停在 {设计阶段}，剧情链还没推导完，请先回 novel-discuss 把它走到 done 再写正文。" - 读上一章
正文.md— 确认承接状态和章末钩子 memory/past.md— 最近摘要和当前状态 → 停，不展开- 读 CLAUDE.md 获取创作风格基线、叙事纹理、目标读者（频道定位和阅读经验直接影响节奏和复杂度）
设定文件缺失就先补全再写作，不自己编造。
第二步：写作前强制反思
在动笔前，在 thinking 中完成以下反思。不输出到对话。
2.1 本章气质（四维定调）
从 CLAUDE.md 的「叙事纹理」读取用户的 7 维度文风偏好，映射到以下四维，作为本章写作的默认气质：
| 维度 | ← 极端 | 极端 → | 从叙事纹理推导 |
|---|---|---|---|
| 节奏 | 绷紧：句句推进 | 舒展：有留白 | 处理模式 + 信息密度 |
| 距离 | 冷眼旁观 | 贴着 POV 人物呼吸 | 叙事距离 |
| 密度 | 锋利：每句推进 | 绵密：感官铺陈 | 心理意象 + 信息密度 |
| 质感 | 粗粝直接：短句口语 | 精密细腻：长句层次 | 语言可预测性 |
在 thinking 中完成推导：
- 先从叙事纹理翻译出默认四维落点
- 再根据本章剧情链的具体需要做微调（如高潮场景可在默认基础上向绷紧端偏移一档）
- 如偏离默认超过一档，注明原因
选好后整章写作全程维持。如果不同场景确实需要不同气质，预先声明切换点。
2.2 本章最易被 AI 腔污染的位置
基于剧情链，预先定位 2-3 个最容易翻车的点，每个给出本章的具体预防措施。
注意：AI 腔判断必须尊重叙事纹理中的用户偏好。例如：
- 用户的「语言可预测性」偏向「高偏离」→ 破折号、精致修辞不是 AI 腔，是用户要的风格
- 用户的「情感投入」偏向「高投入」→ 情感标签和心理描写不是 AI 腔
- 用户的「对话对抗性」偏向「高对抗」→ 对话中的打断和攻击性不是失真
以下四类高危场景仍需预防（与 taste 无关的通用问题）：
- 情感高危场景 → 预先决定用什么动作或感官细节替代情感标签（但高情感投入偏好下可保留部分心理描写）
- 对话失真高危场景 → 预先决定谁在哪句话撕破脸、打断、反问
- 转场空泛高危位 → 预先确定触发切场的具体动作
- 结尾泄力高危位 → 预先确定留动作还是留意念
2.3 本章最该被记住的一个瞬间
选一个具体的、可见的画面、台词或动作。整章写作围绕它组织。
- 必须可见，不是"主角成长了"而是"他做了 X"
- 写这个瞬间时，允许比其他段落多花篇幅
2.4 本章禁用句式
根据本章气质和内容，声明 3-5 个具体禁用的表达模式，落到能在写作时直接检查的粒度。
以下为默认禁用（除非本章气质明确需要，否则无需在声明中重复）：
- 中文破折号
——叙事文本不超过 1 处（对话内的截断破折号不计入限额） - "形容词+冒号+解释"句式（如"残酷的是：..."、"讽刺之处在于：..."）
第三步：写作
从剧情链直接展开为正文。每条剧情链是一个叙事节拍，包含环境 <...>、动机 [...]、动作 （...）、话语 "..."、结果 → ... 五个元素（按需出现，顺序自由，→ 必选）。从中理解推进方向后展开为具象正文，写作时保持同一剧情链内的 POV 一致。
每个场景至少包含 2 个具体的感官细节——不是抽象形容词（「美丽」「恐怖」），而是读者能触摸到的东西：铜锈味、指甲刮桌面的声音、后背贴着冰凉的墙、鞋底踩到黏腻的东西。感官细节跟着角色的身体走，角色碰到什么写什么。
篇幅靠剧情密度自然展开，不靠注水：本系统不设字数配额，单章篇幅是剧情密度被充分展开后的自然结果。若初稿读起来单薄、撑不起一章：
- 剧情链本身有料、只是展开不够 → 把已有节拍展开得更具象：补感官落点、拆细动作链、增加对抗回合。这是分内的充分展开，可以放手写厚。
- 剧情链本就稀薄（无实质推进、只剩孤立节拍） → 停下，不靠堆环境描写或重复心理独白凑篇幅（那是注水），回 novel-discuss 按"合并相邻章"调整事件卡——结构问题不在正文阶段硬修。
What ships with it
7 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.
- 9d ago First seen · 102 lines · 51 tokens per session scan A 355b67a1a43e
novel-write is a skill published in the GitHub repository TulanCN/vibe-noveling (23 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,948 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…