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 DankerMu/novel-writer-plugin --skill novel-writinggit clone --depth 1 https://github.com/DankerMu/novel-writer-pluginWrote 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/dankermu/novel-writer-plugin/novel-writing)<a href="https://agentmods.dev/skills/dankermu/novel-writer-plugin/novel-writing"><img src="https://agentmods.dev/badge/skills/dankermu/novel-writer-plugin/novel-writing/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/dankermu/novel-writer-plugin/novel-writing"><img src="https://agentmods.dev/badge/skills/dankermu/novel-writer-plugin/novel-writing.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 | $0.00104 | $0.01572 |
| Opus 5 | $0.00052 | $0.00786 |
| Sonnet 5 | $0.00021 | $0.00314 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
novel-writing 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小说创作方法论
本知识库为 novel 插件系统提供共享方法论。入口 Skill（/novel:continue、/novel:start）在 context 组装阶段读取本目录下的 references，按需注入到各 Agent 的 prompt 中。
卷制滚动工作流
网文创作采用"边写边想"模式，以卷（30-50 章）为单位滚动规划：
- 卷规划：PlotArchitect 生成本卷大纲 + 伏笔计划 + L3 章节契约
- 日更续写：ChapterWriter → StyleRefiner → [QualityJudge + ContentCritic 并行] → Gate → Summarizer（单章流水线）
- 定期检查：每 5 章自动执行滑窗一致性校验（窗口 10 章、步长 5，形成 ch1-10/ch6-15/ch11-20… 重叠覆盖）+ 质量简报 + 风格漂移监控；每 10 章深度盘点（伏笔盘点 + 跨线桥梁检查 + 故事线节奏分析）
- 卷末自动核查：到达卷末章时自动执行全卷 NER 一致性 + 伏笔/桥梁/节奏分析；State 清理和下卷规划由
/novel:start完成
核心循环状态机：VOL_PLANNING → WRITING ⟲ (每章含内嵌门控+修订) → VOL_REVIEW → VOL_PLANNING
Spec-Driven Writing 原则
小说创作遵循"规范先行，实现随后，验收对齐规范"范式：
| 层级 | 内容 | 生成者 | 约束强度 |
|---|---|---|---|
| L1 世界规则 | 物理/魔法/社会硬约束 | WorldBuilder → rules.json |
不可违反 |
| L2 角色契约 | 能力边界/行为模式 | WorldBuilder（角色模式） → contracts |
可变更需走协议 |
| L3 章节契约 | 前置/后置条件/验收标准 | PlotArchitect → chapter-contracts/ |
可协商须留痕 |
验收采用四轨制：Track 1 Contract Verification（合规检查 L1/L2/L3/LS，硬门槛）+ Track 2 Quality Scoring（9 维度评分含 tonal_variance，软评估）由 QualityJudge 执行；Track 3 Reader Engagement（读者参与度）+ Track 4 Content Substance（信息密度/剧情推进/对话效率，硬门槛）由 ContentCritic 并行执行。合规是编译通过，质量是 code review，内容实质是 regression test。
多线叙事体系
支持多 POV 群像、势力博弈暗线、跨卷伏笔交汇等复杂叙事结构：
- 小说级定义：
storylines/storylines.json管理全部故事线（类型 + 范围 + 势力 + 桥梁关系） - 卷级调度：PlotArchitect 在卷规划时生成
storyline-schedule.json（volume_role: primary/secondary/seasoning + 交汇事件） - 章级注入：ChapterWriter 接收 storyline_context + concurrent_state + transition_hint
- 防串线：三层策略（结构化 Context + 反串线指令 + QualityJudge 后验校验），每次续写为独立 LLM 调用
- 活跃线限制：同时活跃 ≤ 4 条
去 AI 化四层策略
| 层 | 手段 | 执行者 |
|---|---|---|
| L1 风格锚定 | 用户样本 → style-profile.json | WorldBuilder（风格提取模式） |
| L2 约束注入 | 黑名单 + 语癖 + 反直觉 + 句式多样 | ChapterWriter |
| L3 后处理 | 替换 AI 用语 + 匹配风格指纹 | StyleRefiner |
| L4 检测度量 | 黑名单命中率 + 句式重复率 + 风格匹配度 | QualityJudge |
核心指标：AI 黑名单命中 < 3 次/千字，相邻 5 句重复句式 < 2。
详见 references/style-guide.md。
质量评分标准
9 维度加权评分（详见 references/quality-rubric.md）：
What ships with it
6 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.
- 10d ago First seen · 88 lines · 104 tokens per session scan A f13c61210662
novel-writing is a skill published in the GitHub repository DankerMu/novel-writer-plugin (13 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 1,572 once invoked, about $0.0005 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…