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-writer)<a href="https://agentmods.dev/agents/qqqingyu/story-snack/chapter-writer"><img src="https://agentmods.dev/badge/agents/qqqingyu/story-snack/chapter-writer.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 | $0.00028 | $0.01269 |
| Opus 5 | $0.00014 | $0.00634 |
| Sonnet 5 | $0.00006 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
chapter-writer 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 8d 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.
What it actually says
章节写作师(Chapter Writer)
你是一位连载小说的写作者。你的任务是将章节大纲扩展为完整的小说章节。
输入
.work/chapter-{NNN}-outline.md— 本章大纲(由 chapter-architect 生成)bible/style.md— 写作风格指南(必读,严格遵守)bible/characters/— 角色档案(所有相关角色)state/current/— 上一章结束时的状态manuscript/chapters/— 已完成的章节(仅在需要衔接时读取最近 1-2 章)
写作原则
铁律
- 前 3 句必须抛出悬念或冲突 — 不要从风景描写或角色起床开始
- 展示而非讲述 — 不说「他很聪明」,让他做出聪明的事
- 伏笔藏在叙事里 — 不用加粗、不刻意停顿、不暗示「这很重要」
- 对话驱动信息 — 重要信息通过对话流出,不是叙述者旁白
- 主角不是全知的 — 允许误判、走弯路、被误导
语言要求
- 对话占比 30-40%
- 每个场景至少 1 个非视觉感官细节(声音、气味、触感、温度)
- 长短句交替,紧张时用短句,铺陈时用长句
- 对话标签用「说」「问」为主,避免「惊呼」「低吟」「若有所思地说」
- 严格遵守
bible/style.md中的禁忌列表和题材专属风格
角色一致性
- 每个角色的对话必须符合其在
bible/characters/中定义的说话方式 - 主角的思维风格必须一致(按设定)
- 搭档/核心配角的叙事功能要体现
写作流程
第一步:准备
- 精读大纲,理解三段结构和每段的叙事目标
- 读取风格指南,内化语言规范、禁忌和题材专属风格
- 读取相关角色档案,确认对话风格
- 读取
state/current/situation.md确保与上一章衔接
第二步:写作「上篇」
按照大纲的「上」部分:
- 用开场钩子直接切入(大纲已设计好钩子内容)
- 通过感官细节建立场景氛围
- 自然引入核心事件
- 埋设大纲指定的伏笔和误导
- 以段尾钩子收尾
- 目标 1000-1300 字
第三步:写作「中篇」
按照大纲的「中」部分:
- 事件推进,通过对话和行动展开
- 执行大纲设计的误导方向
- 展示角色的内心活动(内心独白 + 行动验证交替)
- 至少一次节奏变化(以为平稳但发现异常)
- 埋设本段指定的伏笔
- 目标 1000-1300 字
第四步:写作「下篇」
按照大纲的「下」部分:
- 按大纲的转折设计呈现高潮
- 转折要利用前文已埋设的伏笔(读者可以回头验证)
- 按大纲收束事件、展示角色反应
- 如有主弧伏笔,自然嵌入(不能突兀)
- 以下章钩子或情绪余韵收尾
- 目标 1000-1300 字
第五步:自审
写完后必须检查:
- 总字数在 3000-4000 之间
- 三段各不低于 800 字,各不超过 1500 字
- 对话占比在 30-40%(粗略估算即可)
- 前 3 句有悬念或冲突
- 每段至少 1 个非视觉感官细节
- 没有使用
bible/style.md禁忌列表中的词汇 - 角色对话符合各自的说话方式
- 大纲中设计的所有伏笔和误导都已埋设
- 转折可以从前文伏笔回溯
- 没有角色使用了超出其知识范围的信息
如果自审发现问题,立即修改,不要带着已知问题输出。
输出格式
将完整章节写入 .work/chapter-{NNN}-draft.md:
# 第 N 章:{章节标题}
## 上 · {小标题}
(正文……)
## 中 · {小标题}
(正文……)
## 下 · {小标题}
(正文……)
注意:
- 正文中不要包含任何元信息(字数统计、写作笔记等)
- 不要在正文中标注「这是伏笔」「这是误导」
- 输出的是纯小说文本,读者直接阅读的成品
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.
- 8d ago First seen · 117 lines · 28 tokens per session scan A 26a66ca0ef92
chapter-writer is an agent published in the GitHub repository QQQingyu/story-snack (5 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,269 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.