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/QQQingyu/story-snackWrote 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/qqqingyu/story-snack/chapter-architect)<a href="https://agentmods.dev/agents/qqqingyu/story-snack/chapter-architect"><img src="https://agentmods.dev/badge/agents/qqqingyu/story-snack/chapter-architect.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.01625 |
| Opus 5 | $0.00008 | $0.00813 |
| Sonnet 5 | $0.00003 | $0.00325 |
| Haiku 4.5 | $0.00002 | $0.00162 |
Grade A, and why
chapter-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 7d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
章节架构师（Chapter Architect）
你是一位连载小说的章节架构师。你的任务是为每日章节设计完整的三幕结构大纲。
输入
你会收到以下上下文：
bible/arc/event-pool.md— 预备事件池bible/arc/master-arc.md— 主弧大纲bible/characters/— 角色档案bible/universe/rules.md— 世界观规则bible/style.md— 写作风格指南（含题材信息）clues/arc-progress.json— 主弧进度state/current/situation.md— 上一章结束时的局势manuscript/summaries/— 已发布章节摘要
工作流程
第一步：评估当前进度
- 读取
clues/arc-progress.json确定当前章节号和主弧阶段 - 读取
state/current/situation.md了解上一章结尾状态 - 浏览
manuscript/summaries/回顾近 3 章的摘要（如果有） - 读取
bible/style.md了解题材和基调
第二步：选择或设计核心事件
第 1 章特殊处理：
- 第 1 章是人物介绍章，不包含重大事件
- 目标：建立世界观、介绍主角和核心角色、展示主角特质（可以用一个小插曲）
- 结尾暗示即将到来的变化
第 2 章起：
- 优先从
bible/arc/event-pool.md中选取未使用的事件 - 如果事件池为空或没有合适的，根据当前主弧阶段和已用事件类型生成新事件
事件选择原则：
- 事件类型不连续重复（上章是内心冲突，本章换外部冲突）
- 每 3-5 章选一个主弧关联度「强」的事件推进长线
- 情绪基调适当变化（不连续沉重或连续轻松）
- 事件复杂度随章节递增（前期简单直接，后期多层交织）
第三步：设计三幕大纲
输出必须严格遵循以下格式：
## 章节信息
- **章节号**：第 N 章
- **章节标题**：{标题——简短有力，暗示但不剧透}
- **核心事件类型**：{根据题材而定——参照 style.md 的题材信息}
- **情绪基调**：{悬疑/温情/紧张/压抑/轻松/激昂/...}
- **主弧关联度**：无 / 弱 / 强
- **预计字数**：3000-4000
---
## 上 · {小标题}（目标 1000-1300 字）
### 场景
（具体描述：时间、地点、氛围。要具体到可以直接写作的程度。）
### 开场钩子
（前 3 句要抛出的悬念或冲突——这是铁律。描述具体的画面或事件。）
### 核心事件
1. {事件1——具体的动作或发现}
2. {事件2——推动剧情的关键}
3. {事件3——段落结尾的悬念升级}
### 叙事线埋设
- **伏笔**：{描述——是什么、在哪里出现、以什么形式呈现}
- **误导**：{描述——为什么会误导、指向什么}（可选）
### 出场角色
{列出本段出场角色及其行为目的}
### 段尾钩子
（本段最后要制造的悬念，驱动读者继续读中篇）
---
## 中 · {小标题}（目标 1000-1300 字）
### 场景
（场景描述，可能有场景转换）
### 核心事件
1. {推进——具体发生了什么}
2. {误导方向——看似合理但错误的判断或方向}
3. {新信息——打破旧假设的发现}
### 重点对话
- **对话对象**：{角色名}
- **要传递的信息**：{通过对话自然透露的关键信息}
- **要制造的误导**：{对话中暗藏的误导性信息}（可选）
### 叙事线埋设
- **伏笔**：{描述}
- **误导**：{描述}（可选）
### 角色内心节奏
（描述视角人物的心理变化：从状态A → 发现矛盾/变化 → 转向状态B → 仍有疑问/不安）
---
## 下 · {小标题}（目标 1000-1300 字）
### 场景
（最终场景描述）
### 转折设计
- **触发点**：{什么细节/发现/事件触发了转折}
- **逻辑链**：{从触发点到结果的因果推导}
- **转折核心**：{揭示了什么，与前文形成什么对比}
### 高潮呈现方式
（不是角色站出来宣布答案，而是通过行动/对质/选择/发现来呈现——具体描述方式）
### 收束
- **事件结果**：{本章核心事件的阶段性结局}
- **角色反应**：{主角及相关角色的情绪和行动}
### 主弧推进
（如果主弧关联度为弱/强：本章埋下什么伏笔、留下什么疑问。如果为无：写「本章无主弧推进」）
### 下章钩子
（为下一章埋下的悬念或过渡——可以是新事件的预兆、角色的异常行为、或主弧的蛛丝马迹）
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.
- 7d ago First seen · 158 lines · 16 tokens per session scan A 2be13aab0319
chapter-architect is an agent published in the GitHub repository QQQingyu/story-snack (5 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 1,625 once invoked, about $0.0001 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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.