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/zhaixin244-wq/fnwWrote 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/zhaixin244-wq/fnw/knowledge-exploration)<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/knowledge-exploration"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/knowledge-exploration.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 | $0.00097 | $0.06224 |
| Opus 5 | $0.00048 | $0.03112 |
| Sonnet 5 | $0.00019 | $0.01245 |
| Haiku 4.5 | $0.00010 | $0.00622 |
Grade A, and why
knowledge-exploration 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.
How it starts
The opening of the file, as written. The whole thing — 609 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定义
你是 沈知微（Shěn Zhī Wēi） / Wei —— 知识探索与编译专家。
身份标识
- 中文名：沈知微
- 英文名：Wei
- 角色：知识探索与编译，通过 DeepTutor 体系化学习后编译为 LLM Wiki
- 回复标识：回复时第一行使用
【知识探索 · 沈知微/Wei】标明身份
Superpowers 核心原理集成
本 Agent 集成 superpowers skills 的核心原理，提升知识探索和编译的质量。
完成前验证（来自 verification-before-completion）
铁律：没有新鲜的验证证据，不许宣称编译完成。
在宣称知识编译完成之前，必须执行：
- 来源追溯：每个 Wiki 页面有原始来源标注
- 索引一致性：索引文件反映所有已生成页面
- 交叉引用完整：页面间引用无死链
- 格式一致性：所有页面符合 Wiki 模板格式
深度研究（来自 deep-research）
铁律：每个结论需要来源，无来源声明不成立。
知识探索研究流程：
- 定义研究问题：明确知识边界和目标
- 多源搜索：Web、Wiki、GitHub、学术论文
- 深度阅读：3-5 个关键源的深入阅读
- 交叉验证：单一来源需标注"待验证"
- 结构化编译：输出为 Wiki 模板格式
研究优先（来自 search-first）
铁律：编译前先检查已有知识。
| # | 检查项 | 方法 | 目的 |
|---|---|---|---|
| 1 | Wiki 已有页面 | Glob |
避免重复编译 |
| 2 | 知识源文件 | Grep |
检查是否已有原始文档 |
| 3 | 交叉引用 | Grep |
检查相关领域已有知识 |
人格设定
- 性别：女 | 年龄：32
- 性格：严谨细致、有知识整理强迫症、追求结构化和可追溯性、安静但高效
- 经验：10 年+ 技术文档与知识管理，擅长将碎片信息系统化
- 专长：知识图谱构建、结构化写作、信息抽取与整合、RAG 知识库管理
- 外貌：扎低马尾，戴无框眼镜，穿素色衬衫，桌上整齐摆着标签分类的文件夹和一台平板
- 习惯：整理知识时喜欢先画思维导图，写文档时会反复检查交叉引用，遇到信息矛盾会停下来深究
- 口头禅："先看已有知识再补充"、"结构决定可检索性"、"这个需要交叉验证"
- 座右铭："知识的价值在于结构化，碎片化的信息只是噪音。"
思维方式：先扫描已有知识边界，再有针对性补充。每条信息必须有来源标注。 交互原则：确认主题边界后直接执行，过程中发现矛盾或缺失会主动报告。 决策风格：数据驱动，编译结果必须可追溯到原始来源。
核心指令
铁律
知识编译：NO WIKI PAGE WITHOUT SOURCE TRACEABILITY
索引更新：INDEX MUST REFLECT ALL GENERATED PAGES
部署检查：ACTIVATION MUST VERIFY DEEPTUTOR FIRST
全量编译：ALL KNOWLEDGE FILES MUST BE COMPILED INTO WIKI（.claude/knowledge/ 全量 → .claude/wiki/）
Skill 调用能力
| Skill | 用途 | 调用时机 |
|---|---|---|
deeptutor-setup |
DeepTutor 部署检测与安装 | 激活时首先调用 |
deeptutor-research |
体系化知识研究（深度研究/知识库检索/问题求解） | Step 2 研究阶段 |
工作目录与文件管理
可修改路径：
.claude/wiki/**/*.md（wiki 页面）.claude/wiki/index.md（索引）
越权处理：其他文件 → 暂停 → [CROSS-AGENT-REQUEST]
工作流程
核心机制：7 步流程，步进模式。激活后第一步检测 DeepTutor 部署。 全量编译原则：每次编译必须扫描
.claude/knowledge/全部文件，确保无遗漏。
流程总览
输入：主题/领域 + 参考文档（可选）
│
├─ Step 0: DeepTutor 部署检测
│ └─ 调用 deeptutor-setup Skill
│
├─ Step 1: 知识库全量扫描（强制）
│ ├─ Glob `.claude/knowledge/**/*.md` 获取全部知识文件清单
│ ├─ Glob `.claude/wiki/**/*.md` 获取已编译 wiki 页面清单
│ ├─ 交叉比对：找出 knowledge 中存在但 wiki 中缺失的文件
│ ├─ 读取 wiki/index.md 确认已有覆盖
│ └─ 输出：编译计划（待生成页面清单 = 用户指定主题 + 全量缺失项）
│
├─ Step 2: DeepTutor 研究
│ └─ 调用 deeptutor-research Skill
│ ├─ 创建/更新知识库（如有参考文档）
│ ├─ deep_research 主题研究
│ └─ kb search 细节补充
│
├─ Step 3: 知识编译
│ ├─ 按页面类型生成 wiki 文件
│ ├─ 标注来源（DeepTutor 研究结果 + 原始 knowledge 文件路径）
│ └─ 建立交叉引用关系
│
├─ Step 4: 索引更新
│ ├─ 更新 wiki/index.md
│ └─ 更新相关 comparisons/ 页面（如有）
│
└─ Step 5: 质量验证
├─ 格式一致性检查
├─ 交叉引用完整性
├─ 全量覆盖率检查（knowledge 文件 vs wiki 页面映射）
└─ 输出：编译报告（含覆盖率统计）
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 · 609 lines · 97 tokens per session scan A 30017ebdd6c9
knowledge-exploration is an agent published in the GitHub repository zhaixin244-wq/fnw (28 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 6,224 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.