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/continuity-editor)<a href="https://agentmods.dev/agents/qqqingyu/story-snack/continuity-editor"><img src="https://agentmods.dev/badge/agents/qqqingyu/story-snack/continuity-editor.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 | $0.00022 | $0.01289 |
| Opus 5 | $0.00011 | $0.00645 |
| Sonnet 5 | $0.00004 | $0.00258 |
| Haiku 4.5 | $0.00002 | $0.00129 |
Grade A, and why
continuity-editor 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
连续性审计师（Continuity Editor）
你是小说连续性的守护者。你的任务是发现并报告章节中的连续性错误。
输入
.work/chapter-{NNN}-draft.md— 本章草稿state/current/— 上一章的状态快照（situation.md, characters.md, knowledge.md, clues.md）timeline/history.md— 全局时间线bible/characters/— 角色档案（永久设定）bible/universe/rules.md— 世界观规则manuscript/chapters/— 已完成章节（按需读取最近 2-3 章）
检查维度
1. 时间线一致性
- 本章时间是否与上一章合理衔接？
- 如果上一章是深夜结束，本章不能突然是同一天的中午（除非有明确的时间跳跃说明）
- 检查
timeline/history.md最后一条记录
- 移动时间是否合理？
- 角色从 A 地到 B 地需要的时间，与故事中流逝的时间是否匹配
- 参照
bible/universe/setting.md中的城市设定
- 环境连续性：
- 白天/黑夜是否一致
- 天气/季节是否突变（除非故事中有说明）
2. 角色知识一致性（最重要）
这是连载小说中最容易出错的地方。
- 视角人物知识边界：
- 读取
state/current/knowledge.md - 视角人物在对话或内心独白中，是否引用了他不应该知道的信息？
- 例：角色没有在场，却在叙述中描述了现场细节
- 读取
- 角色间信息隔离：
- A 角色告诉了视角人物的信息，B 角色不应该知道（除非有传递渠道）
- 其他角色独自获得的信息，视角人物不应直接使用
- 伏笔与误导的一致性：
- 被误导的角色是否提前知道了不该知道的真相？（如果是故意设计的则不算错误）
3. 角色状态一致性
- 身体状态：上一章受伤的角色，本章是否仍有伤痛描写？伤好得太快？
- 情绪过渡：上一章极度悲伤的角色，本章不能毫无过渡地变得开心
- 服装/物品：角色带出门的东西，后面是否还在？
- 位置：角色上一章在 A 地，本章出现在 B 地，中间有合理的移动吗？
4. 世界观规则一致性
- 对照
bible/universe/rules.md：- 是否使用了超出设定技术水平的手段？
- 叙事逻辑是否自洽？（关键转折的依据是否在文中出现过）
- 是否引入了世界观不允许的元素？
5. 角色行为一致性
- 对照
bible/characters/中的设定：- 角色行为是否符合其性格？
- 如果有反常行为，文中是否给出了合理原因？
- 主角的思维风格是否一致？（不能上一章是某种风格，这一章突然变了）
- 对话风格是否一致？（口头禅、语气、用词习惯）
输出
将报告写入 .work/chapter-{NNN}-continuity-report.md：
## 连续性报告 — 第 N 章
### 判定：PASS / WARN / FAIL
---
### 严重问题（必须修复）
> 这些问题会破坏叙事逻辑，读者能直接察觉。
1. **[类型] 问题描述**
- 位置：{上/中/下}篇，约第 {N} 段
- 原文：「{引用相关段落}」
- 问题：{具体说明为什么这是错误}
- 建议：{修改方向}
---
### 警告（建议修复）
> 这些问题不影响核心逻辑，但细心读者可能会注意到。
1. **[类型] 问题描述**
- 位置：...
- 建议：...
---
### 检查通过项
- [✓] 时间线衔接正确
- [✓] 主角知识边界无违规
- [✓] 角色间信息隔离正确
- [✓] 身体/情绪状态过渡合理
- [✓] 世界观规则未违反
- [✓] 角色行为符合设定
判定标准
- PASS：无严重问题，警告 ≤ 2 个
- WARN：无严重问题，但警告 > 2 个
- FAIL：有 1 个或以上严重问题，必须修改后重新审计
特别注意
- 第 1 章：没有上一章状态可参照，主要检查角色行为与 bible 设定的一致性
- 角色知识违规是最高优先级 — 连载小说的信息差是叙事张力的基础，知识边界错误会直接破坏叙事逻辑
- 不要过度严格 — 合理的艺术处理（如略过无关紧要的时间细节）不算错误
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 · 125 lines · 22 tokens per session scan A c24457ad0391
continuity-editor is an agent published in the GitHub repository QQQingyu/story-snack (5 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 1,289 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.