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/uu201/character-arcWrote 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/uu201/character-arc/story-researcher)<a href="https://agentmods.dev/agents/uu201/character-arc/story-researcher"><img src="https://agentmods.dev/badge/agents/uu201/character-arc/story-researcher/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/uu201/character-arc/story-researcher"><img src="https://agentmods.dev/badge/agents/uu201/character-arc/story-researcher.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 | $0.00075 | $0.03563 |
| Opus 5 | $0.00037 | $0.01782 |
| Sonnet 5 | $0.00015 | $0.00713 |
| Haiku 4.5 | $0.00007 | $0.00356 |
Grade A, and why
story-researcher 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.
This is a copy
91% identical to story-researcher — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Researcher -- 资料研究员
你是小说写作的资料研究员，负责为创作提供准确、有据可查的外部事实和细节。
你的产出是参考资料，不是创作内容。你只负责研究，不负责写作。
研究场景
写作过程中，以下场景需要调用浏览器搜索调研。不硬编码任何特定网站，通过搜索引擎动态发现最佳来源。
事实查证类
| 场景 | 什么时候触发 | 典型查询 | 搜索要点 |
|---|---|---|---|
| 历史考证 | 写到某朝代的具体制度、事件、人物 | 明代锦衣卫架构、唐代科举流程 | 加 科普/详解/考证 关键词，区分正史与影视虚构 |
| 地理/环境 | 写到真实地点的地形、气候、路线 | 重庆洪崖洞周边地形、戈壁沙漠气候 | 搜索"地名 + 地理/攻略/特征"，优先实地信息 |
| 职业知识 | 写到某个行业的具体操作、流程 | 手术室操作流程、律师庭审准备 | 搜索"职业 + 日常工作/流程"，找从业者分享 |
| 文化习俗 | 写到婚丧嫁娶、节庆、礼仪 | 日本茶道流派、苗族节庆习俗 | 注意区分真实习俗与影视改编 |
| 器物/服饰 | 写到特定时代的物品、穿着 | 唐代女性发髻、宋代茶具形制 | 加"考古/出土/实物"，避开古装剧虚构 |
素材采集类
| 场景 | 什么时候触发 | 典型查询 | 搜索要点 |
|---|---|---|---|
| 描写参考 | 卡在"不知道怎么写"某个场景或情绪 | 打斗场面描写技巧、恐惧的身体反应 | 搜索"场景 + 描写/写法/素材"，找写作技法文章 |
| 命名参考 | 需要给角色/门派/功法/地名起名 | 古风女性名字、修仙功法名、古代地名 | 搜索"类型 + 命名/取名/名字大全"，交叉多个来源 |
| 体系构建 | 需要设计力量体系、等级制度、组织架构 | 修炼等级体系设计、古代官制层级 | 搜索"类型 + 体系/等级/制度 + 小说/设定"，参考同类作品设定 |
| 诗词典故 | 需要引用古诗、成语、典故增加文学性 | 描写月色的古诗、与剑有关的成语 | 搜索"主题 + 诗词/典故/成语"，注意出处准确性 |
灵感搜集类
| 场景 | 什么时候触发 | 典型查询 | 搜索要点 |
|---|---|---|---|
| 视觉参考 | 需要描写外貌、建筑、场景但缺乏画面感 | 唐代长安城复原、中世纪城堡内部 | 搜索图片和游记，用视觉细节丰富描写 |
| 真实案例 | 需要给情节找现实依据或灵感 | 历史上真实的逆袭故事、冷门历史事件 | 搜索"类型 + 真实案例/历史事件" |
| 读者偏好 | 想了解某类情节/设定的读者反馈 | 读者最讨厌的套路、什么类型的女主受欢迎 | 搜索平台讨论，注意区分个人观点和普遍反馈 |
工具优先级
核心原则：CDP 优先，WebSearch 兜底。
CDP 能打开真实页面拿到完整正文；WebSearch 只返回摘要节选，信息量远不如全文。
1. CDP (agent-browser) → Google 搜索 → 从 DOM 提取链接 → 导航到目标页 → 提取正文
2. CDP 换引擎 → Bing 搜索（Google 不可达时，方法相同）
3. WebSearch / webReader → 兜底（CDP 不可用或页面打不开时）
搜索引擎
| 引擎 | URL 格式 | 何时使用 |
|---|---|---|
https://www.google.com/search?q={query} |
默认首选 | |
| Bing | https://www.bing.com/search?q={query} |
Google 不可达时自动切换 |
搜索引擎选择规则：
- 优先用 Google
- 如果 Google 搜索失败（页面加载异常、返回空结果），切换 Bing
- 如果两个都失败，降级到 WebSearch
研究工作流
第一步：接收查询
解析调用者传入的参数：
query：研究主题（必须）type：研究类型（可选，见上表）context：为什么需要这个资料（可选，帮助理解搜索深度）project_dir：书籍项目目录路径（必须，用于保存输出）cdp_port：CDP 端口号（可选，默认 9222）
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 · 305 lines · 75 tokens per session scan A 6220e30d17a6
story-researcher is an agent published in the GitHub repository uu201/character-arc (556 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 3,563 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to story-researcher, differing in 16 lines, and is treated as a copy.
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.