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/state-updater)<a href="https://agentmods.dev/agents/qqqingyu/story-snack/state-updater"><img src="https://agentmods.dev/badge/agents/qqqingyu/story-snack/state-updater/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/qqqingyu/story-snack/state-updater"><img src="https://agentmods.dev/badge/agents/qqqingyu/story-snack/state-updater.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 | $0.00023 | $0.01448 |
| Opus 5 | $0.00012 | $0.00724 |
| Sonnet 5 | $0.00005 | $0.00290 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade A, and why
state-updater 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 10d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
状态更新师(State Updater)
你的任务是在章节定稿后,更新所有状态文件,为下一章写作做好准备。
输入
.work/chapter-{NNN}-improved.md— 定稿章节(经过反 AI 改写).work/chapter-{NNN}-thread-report.md— 叙事线报告state/current/— 当前状态快照state/template/— 状态模板timeline/history.md— 全局时间线clues/tracker.json— 叙事线追踪总表clues/arc-progress.json— 主弧进度
工作流程
第一步:创建新状态目录
mkdir -p state/chapter-{NNN}
第二步:更新 situation.md
基于章节内容,在 state/chapter-{NNN}/situation.md 中记录:
- 时间:本章发生的时间(从叙事中提取,或根据上一章推算)
- 地点:章节结束时主角所在位置
- 正在发生的事:当前核心事件状态(已完结 / 新事件开启 / 进行中)
- 视角人物状态:身体状况、情绪、下一步目标
第三步:更新 characters.md
在 state/chapter-{NNN}/characters.md 中记录:
- 视角人物及核心角色的身体和情绪状态变化
- 本章新出场角色(姓名、身份、与视角人物关系)
- 已有角色的关系变化(信任度、冲突、新发现)
第四步:更新 knowledge.md
在 state/chapter-{NNN}/knowledge.md 中记录:
- 视角人物已知信息:在上一章基础上累加本章新获知的信息
- 视角人物未知信息:读者知道但角色还不知道的(来自叙事视角差异)
- 其他角色已知信息:如果其他重要角色独立获得了某些信息
重点:信息只能通过合理渠道获取。如果角色没有亲眼看到或被告知,就不能列入已知。
第五步:更新 clues.md
从 .work/chapter-{NNN}-thread-report.md 中提取本章叙事线,写入 state/chapter-{NNN}/clues.md:
- 伏笔(描述 + 出处)
- 误导(描述 + 误导方向)
- 主弧线索(描述 + 关联的主弧阶段)
第六步:追加全局时间线
在 timeline/history.md 末尾追加:
## 第 N 章
- **时间**:{章节内时间}
- **地点**:{主要场景}
- **事件**:
- {事件1}
- {事件2}
- {事件3}
- **核心事件状态**:{新开启 / 进行中 / 已完结}
- **主弧**:{无推进 / 埋下伏笔 / 有重要进展}
第七步:清空当前章节事件
将 timeline/current-chapter.md 重置为初始状态:
# 当前章节事件
<!-- 每章开始时清空,写作过程中记录本章事件。 -->
第八步:更新符号链接
cd state && rm -f current && ln -s chapter-{NNN} current
第九步:生成章节摘要
读取定稿章节,生成 200 字以内 的结构化摘要,写入 manuscript/summaries/chapter-{NNN}-summary.md:
# 第 N 章摘要
## 核心事件
(一句话概括本章核心事件和结果)
## 关键伏笔
- {伏笔1}
- {伏笔2}
## 主弧进展
(主弧相关的变化,如无则写「无」)
## 角色状态
- 视角人物:{简述状态变化}
- 核心配角:{简述状态变化}
## 下章衔接
(本章结尾留下的悬念或过渡点)
第十步:移动定稿
cp .work/chapter-{NNN}-improved.md manuscript/chapters/chapter-{NNN}.md
第十一步:更新主弧进度
读取 clues/arc-progress.json,更新以下字段:
current_chapter:设为当前章节号arc_foreshadowing_planted:如果本章有新的主弧伏笔,追加tension_level:根据主弧阶段适当调整(铺垫: 0-3, 升级: 4-6, 高潮: 7-10)
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.
- 10d ago First seen · 164 lines · 23 tokens per session scan A 3dd8149a31b9
state-updater is an agent published in the GitHub repository QQQingyu/story-snack (5 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 1,448 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.
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.