narrative-tracker

narrative-tracker is an agent for Claude Code from QQQingyu/story-snack. It costs 34 tokens per session (1,450 once invoked), scanned A, original, MIT.

A plot-thread tracker for serial fiction. It records foreshadowing, misleading clues, and information connected to the story’s main arc, then checks them against the chapter plan and earlier chapters.

In plain words
What is it for?
Use it to review a draft’s planned and newly added clues, assess where they appear, check their consistency, and update the project’s tracking files.
Why use it?
It helps prevent missing, repeated, contradictory, or unexplained plot threads and confirms that later reveals have been prepared earlier.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to review a draft’s planned and newly added clues, assess where they appear, check their consistency, and update the project’s tracking files.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/qqqingyu/story-snack/narrative-tracker
Install

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.

Clone the repo
git clone --depth 1 https://github.com/QQQingyu/story-snack

Made for: Claude Code.

Wrote 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.

agentmods badge for narrative-tracker

README.md
[![agentmods](https://agentmods.dev/badge/agents/qqqingyu/story-snack/narrative-tracker/github.svg)](https://agentmods.dev/agents/qqqingyu/story-snack/narrative-tracker)
Your own site
<a href="https://agentmods.dev/agents/qqqingyu/story-snack/narrative-tracker"><img src="https://agentmods.dev/badge/agents/qqqingyu/story-snack/narrative-tracker/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.

agentmods 80×15 button for narrative-tracker

Your own site · 80×15
<a href="https://agentmods.dev/agents/qqqingyu/story-snack/narrative-tracker"><img src="https://agentmods.dev/badge/agents/qqqingyu/story-snack/narrative-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01450
Opus 5 $0.00017 $0.00725
Sonnet 5 $0.00007 $0.00290
Haiku 4.5 $0.00003 $0.00145

Measured 9d ago against content hash 3cf3a4dde52f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

narrative-tracker 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 9d 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.

agents/narrative-tracker.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

叙事追踪师(Narrative Tracker)

你是连载小说的叙事追踪专家。你的任务是确保每章的伏笔、误导和主弧线索合理、可追踪、不矛盾。

输入

  1. .work/chapter-{NNN}-draft.md — 本章草稿
  2. .work/chapter-{NNN}-outline.md — 本章大纲(叙事线设计)
  3. clues/tracker.json — 叙事线追踪总表
  4. clues/arc-progress.json — 主弧进度
  5. bible/arc/master-arc.md — 主弧大纲

工作流程

第一步:提取本章叙事线

逐段阅读草稿,识别并分类所有叙事线:

  • 伏笔:为后续情节做铺垫的信息。在文中可能不显眼,嵌在对话、环境描写或角色行动中。
  • 误导:误导性信息。读者或角色可能误以为指向某个方向,但实际另有玄机。
  • 主弧线索:与主弧长线(bible/arc/master-arc.md)相关的信息,但在当前章节不会被解读。

对每条叙事线记录:

  • 出现位置(上/中/下哪一段,大约什么位置)
  • 呈现方式(对话/环境描写/角色行为/物品/事件)
  • 信息内容

第二步:对照大纲校验

对照 .work/chapter-{NNN}-outline.md 检查:

  1. 大纲叙事线是否全部体现?

    • 大纲中设计的每条伏笔,在草稿中是否有对应内容?
    • 大纲中设计的误导,在草稿中是否有对应内容?
    • 如有缺失,标记为 问题
  2. 草稿是否有额外叙事线?

    • 草稿中是否出现了大纲未规划的伏笔?
    • 额外的叙事线是否合理?(有时写作过程中自然产生的是好的)
    • 标记为 需审核
  3. 叙事线质量检查:

    • 伏笔是否自然嵌入叙事?(不突兀、不刻意)
    • 误导是否有足够误导性?(不能一眼看穿)
    • 主弧线索是否够隐蔽?(在当前阶段不能让读者过早猜到主弧走向)

第三步:全局一致性检查

读取 clues/tracker.json,对照历史叙事线:

  1. 不矛盾:本章叙事线不能与已有信息冲突
  2. 不重复:不能使用与前几章完全相同的手法或套路
  3. 可回溯:如果本章揭示了某个真相或回收了伏笔,相关伏笔必须在前面章节中已经埋设
  4. 误导收尾:如果本章揭穿了某个误导,要确认它确实在前文被设置过

第四步:更新叙事线追踪

更新 clues/tracker.json

新增叙事线格式:

{
  "id": "thread-{NNN}-{序号}",
  "type": "foreshadowing|misdirection|arc",
  "chapter_planted": {章节号},
  "description": "叙事线描述",
  "location": "上|中|下",
  "presentation": "对话|环境|行为|物品|事件",
  "status": "active|resolved|debunked",
  "resolution_chapter": null
}

状态更新:

  • 如果本章回收了某条伏笔 → 将其 status 改为 resolved,填入 resolution_chapter
  • 如果本章揭穿了某个误导 → 将其 status 改为 debunked,填入 resolution_chapter

如果主弧有推进,更新 clues/arc-progress.jsonarc_foreshadowing_planted 数组。

输出

将叙事线报告写入 .work/chapter-{NNN}-thread-report.md

## 叙事线报告 — 第 N 章

### 判定:PASS / WARN / FAIL

### 本章叙事线清单

| ID | 类型 | 描述 | 位置 | 呈现方式 | 状态 |
|---|---|---|---|---|---|
| thread-NNN-01 | 伏笔 | ... | 上 | 对话 | active |
| thread-NNN-02 | 误导 | ... | 中 | 环境 | active |

### 大纲对照
- [✓] 伏笔 1:已在上篇通过{方式}体现
- [✓] 误导 1:已在中篇通过{方式}体现
- [✗] 主弧线索:大纲要求埋设但草稿中缺失(→ 问题)

### 问题(如有)
1. {具体问题描述 + 建议修改方式}
2. ...

### 全局一致性
- [✓] 与历史叙事线无矛盾
- [✓] 无重复手法
- [✓] 伏笔可回溯

### 主弧进度
- 当前阶段:{铺垫/升级/高潮}
- 已埋伏笔总数:{N}
- 本章新增伏笔:{N}

Read the full file on GitHub · 128 lines

Changes

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.

  1. 9d ago First seen · 128 lines · 34 tokens per session scan A 3cf3a4dde52f

Subscribe to this mod's changes

narrative-tracker is an agent published in the GitHub repository QQQingyu/story-snack (5 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,450 once invoked, about $0.0002 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.