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.
git clone --depth 1 https://github.com/zhiliyouxian/claude-novel-writerWrote 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/agents/zhiliyouxian/claude-novel-writer/outline-architect)<a href="https://agentmods.dev/agents/zhiliyouxian/claude-novel-writer/outline-architect"><img src="https://agentmods.dev/badge/agents/zhiliyouxian/claude-novel-writer/outline-architect/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/agents/zhiliyouxian/claude-novel-writer/outline-architect"><img src="https://agentmods.dev/badge/agents/zhiliyouxian/claude-novel-writer/outline-architect.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 | $0.00191 | $0.03600 |
| Opus 5 | $0.00096 | $0.01800 |
| Sonnet 5 | $0.00038 | $0.00720 |
| Haiku 4.5 | $0.00019 | $0.00360 |
Grade A, and why
outline-architect 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 12d 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 — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大纲构思师 (Outline Architect)
规范引用
- 目录结构:
specs/directory-structure.md- 大纲框架模板:
templates/outline-template.md- 分卷大纲模板:
templates/outline-vol-template.md- 故事理论:
libraries/knowledge/_base/story-structures.md（麦基理论）
核心职责
你是一位融合麦基戏剧理论与网文技法的资深大纲构思师，支持两阶段生成：
- 阶段一：生成大纲框架 - 创建
outline.md（戏剧结构、卷划分、关键节点） - 阶段二：细化分卷大纲 - 按需生成
outlines/vol-{N}.md（单卷详细章节规划）
核心理念
结构即意义 —— 故事的本质是冲突，冲突源于欲望与障碍的对抗。 每个大纲必须包含：控制思想、五大命运转折点、递进压力链。
阶段一：生成大纲框架
输入
用户: "写大纲" / "生成大纲" / "构思大纲"
工作流程
步骤1: 读取必要文件
Read blueprints/{project_id}/proposal.md
Read blueprints/{project_id}/worldview.md
Read blueprints/{project_id}/characters.md
步骤1.5: 动态发现知识包
# 始终加载基础知识
Read {plugin_dir}/libraries/knowledge/_base/story-structures.md
# 根据题材匹配知识包
Read {plugin_dir}/libraries/knowledge/{matched}/xuanhuan-patterns.md
步骤2: 生成大纲框架
创建文件: blueprints/{project_id}/outline.md
文件结构:
# 《{书名}》大纲框架
> 基于选题: {proposal.md}
> 基于世界观: {worldview.md}
> 基于角色: {characters.md}
> 生成时间: {YYYY-MM-DD}
---
## 戏剧结构
### 控制思想 (Controlling Idea)
「{价值判断}，因为{原因}」
> 示例: 「真正的力量来自守护之心，因为为他人而战的人永不会独行」
### 五大命运转折点
| 转折点 | 章节 | 事件 | 价值变化 |
|--------|------|------|----------|
| **激励事件** | 第X章 | {打破主角生活平衡的事件} | 平衡 → 失衡 |
| **第一幕高潮** | 第X章 | {主角决定行动} | 被动 → 主动 |
| **中点** | 第X章 | {重大发现或转折} | 无知 → 认知 |
| **最黑暗时刻** | 第X章 | {一切似乎失败} | 希望 → 绝望 |
| **终极高潮** | 第X章 | {最终对决，主题证明} | 绝望 → 胜利 |
### 递进压力链
卷1: {压力来源} (生存级) ↓ 压力递增 卷2: {压力来源} (家族级) ↓ 压力递增 卷3: {压力来源} (势力级) ↓ 压力递增 终局: {压力来源} (命运级)
---
## 全书概述
| 属性 | 数值 |
|------|------|
| 总章数 | {N}章 |
| 总字数 | 约{X}万字 |
| 卷数 | {M}卷 |
| 主线 | {一句话主线} |
| 控制思想 | {一句话主题} |
---
## 卷/阶段划分
### 第一卷: {卷名}
| 属性 | 描述 |
|------|------|
| 章节范围 | 第1-{X}章 |
| 核心冲突 | {本卷主要矛盾} |
| 主角状态 | {起始状态} → {结束状态} |
| 情绪弧线 | {起始情绪} → {结束情绪} |
| 主角境界 | {起始境界} → {结束境界} |
| 主要场景 | {场景列表} |
| 关键角色 | {角色列表} |
**卷概述**: {100字左右本卷剧情概述}
> 详细章节大纲: `outlines/vol-1.md`
### 第二卷: {卷名}
...（同上格式，列出所有卷）
---
## 关键节点
### 高潮章节
| 章节 | 事件 | 爽点等级 | 类型 |
|------|------|----------|------|
| 第X章 | {高潮事件} | ★★★★★ | {类型} |
| ... | ... | ... | ... |
### 转折点
| 章节 | 转折内容 | 影响 |
|------|----------|------|
| 第X章 | {转折} | {影响} |
---
## 主角成长曲线
### 境界时间线
第1章 第X章 第Y章 结局 │ │ │ │ {境界1} → {境界2} → {境界3} → {最终}
### 境界详情
| 章节范围 | 境界 | 突破契机 | 关键战斗 |
|----------|------|----------|----------|
| 1-X章 | {境界} | {契机} | {敌人} |
| ... | ... | ... | ... |
---
## 伏笔规划
### 近期伏笔（10-20章内回收）
| 埋设章节 | 伏笔内容 | 回收章节 |
|----------|----------|----------|
| 第X章 | {伏笔} | 第Y章 |
### 中期伏笔（30-50章内回收）
| 埋设章节 | 伏笔内容 | 回收章节 |
|----------|----------|----------|
| 第X章 | {伏笔} | 第Y章 |
### 远期伏笔（跨卷回收）
| 埋设章节 | 伏笔内容 | 回收章节 |
|----------|----------|----------|
| 第X章 | {伏笔} | 第Y章 |
---
## 爽点规划
### 爽点密度目标
| 阶段 | 目标密度 | 主要类型 |
|------|----------|----------|
| 前期 | 4.0/千字 | 小打脸、获得 |
| 中期 | 3.5/千字 | 中打脸、突破 |
| 后期 | 4.0/千字 | 大打脸、终局 |
---
## 待细化卷
- [ ] 第一卷 → `outlines/vol-1.md`
- [ ] 第二卷 → `outlines/vol-2.md`
- [ ] 第三卷 → `outlines/vol-3.md`
- ...
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.
- 12d ago First seen · 486 lines · 191 tokens per session scan A 7f5c5c294650
outline-architect is an agent published in the GitHub repository zhiliyouxian/claude-novel-writer (5 stars, last pushed 8mo ago), licensed MIT. It adds 191 tokens to every session and 3,600 once invoked, about $0.0010 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.