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.
npx skills add owenliang60-ship-it/knowledge-mgmt --skill readgit clone --depth 1 https://github.com/owenliang60-ship-it/knowledge-mgmtWrote 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/skills/owenliang60-ship-it/knowledge-mgmt/read)<a href="https://agentmods.dev/skills/owenliang60-ship-it/knowledge-mgmt/read"><img src="https://agentmods.dev/badge/skills/owenliang60-ship-it/knowledge-mgmt/read.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 | $0.00089 | $0.02984 |
| Opus 5 | $0.00044 | $0.01492 |
| Sonnet 5 | $0.00018 | $0.00597 |
| Haiku 4.5 | $0.00009 | $0.00298 |
Grade A, and why
read 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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/read Command
深度阅读科研论文或学术文章，输出结构化分析报告。
核心理念：主动阅读
"阅读不是接收信息，而是与作者对话。"
这个 skill 模拟的是一个训练有素的研究者的阅读过程：
- 先扫描全貌，建立地图
- 再深入细节，追踪论证链
- 最后退一步，批判性评估
定位
| Skill | 职责 | 输出 |
|---|---|---|
/read |
深度阅读 — 结构化分析论文 | 对话中的分析报告 |
/note |
知识沉淀 — 研究摘要 + 原子卡片 | Obsidian 卡片组 |
/think |
深度思考 — 双模型对比 | 对话中的对比分析 |
典型工作流: /read 分析论文 → 讨论 → /note 存入 Obsidian
Behavior
Step 0: 获取论文
根据用户提供的来源获取内容：
| 来源类型 | 处理方式 |
|---|---|
| URL | 使用 WebFetch 抓取并解析 |
本地文件路径 (.pdf, .md, .txt) |
使用 Read 工具读取 |
| Obsidian 关键词 | obsidian search:context query="..." 搜索，obsidian read path="..." 读取（CLI 不可用时回退 MCP） |
| 粘贴的文本 | 直接分析对话中的文本 |
| 未提供 | 询问用户来源 |
长文处理：如果内容超长（如100页+ PDF），先询问用户关注哪些章节，或使用关键词搜索定位关键段落，而非盲目读取全文。
Step 1: 速览扫描（2分钟鸟瞰）
快速提取论文元信息，建立全局地图：
📋 论文概况
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
标题：[完整标题]
作者：[作者列表]
机构：[所属机构]
发表：[期刊/会议/预印本] | [年份]
领域：[所属学科领域]
类型：[实证研究 / 综述 / 理论建构 / 方法论 / 评论]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
同时识别论文结构骨架（章节大纲），为深度阅读做导航。
如果 depth=quick，跳至 Step 5（速览摘要），跳过 Step 2-4。
Step 2: 论点拆解（核心论证链）
这是分析的核心。逐层拆解论文的论证结构：
2a. 核心论点（Thesis）
用一句话概括论文的中心论点——作者试图证明什么？
格式："本文论证了 [X]，其核心主张是 [Y]"
2b. 论证结构（Argument Architecture）
将论文的论证拆解为树状结构：
核心论点
├── 支撑论点 1
│ ├── 论据 A（类型：实验数据 / 案例 / 逻辑推理 / 权威引用）
│ └── 论据 B
├── 支撑论点 2
│ ├── 论据 C
│ └── 论据 D
└── 支撑论点 3
└── 论据 E
2c. 关键概念定义
列出论文引入或重新定义的关键术语：
| 术语 | 论文中的定义 | 通常理解 | 差异 |
|---|---|---|---|
| [术语1] | [作者定义] | [通常含义] | [有无差异及其意义] |
2d. 预设与假设
识别论文的隐性假设——作者没有明说但论证必须依赖的前提：
- 方法论假设：[如"可量化即可研究"]
- 本体论假设：[如"意识是脑的产物"]
- 价值假设：[如"可重复性是科学的基础"]
Step 3: 方法论评估
3a. 研究设计
| 维度 | 描述 |
|---|---|
| 方法类型 | [定量/定性/混合/理论/计算建模] |
| 数据来源 | [被试/数据集/文献/模拟] |
| 样本规模 | [N=?] |
| 核心工具 | [fMRI/问卷/代码/数学模型...] |
| 分析方法 | [统计方法/编码方法/推理框架] |
3b. 方法论评价
- 优势：这个方法为什么适合回答研究问题？
- 局限：什么是方法论覆盖不到的？
- 替代方案：如果你来做这个研究，会怎么设计？
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 · 373 lines · 89 tokens per session scan A f984de3bcd2c
read is a skill published in the GitHub repository owenliang60-ship-it/knowledge-mgmt (37 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 2,984 once invoked, about $0.0004 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 skills, from other repositories
improve
Critique an outside idea (a pasted tip, post, transcript or video summary) against what this system already has. Use when the founder pastes something and asks whether to adopt it, or says 'improve', 'should we do this', 'compare this to what we have'. Grounded by scripts/improveground.py in the lessons corpora and…
lineage-skill
Turn courses, books, video, audio, PDFs, slides, transcripts, OCR, notes, and long-form materials into source-grounded learning Skills that teach unseen concepts progressively with reliable terminal ASCII or SVG visuals, ask two end-of-lesson questions together by default, give focused feedback, schedule review, test…
cortex-memory
Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.
cognitive-compile
Use when source material must be transformed into a compact, evidence-aware model for learning, decisions, or an Obsidian concept note.
tutorial
Interactive walkthrough for new users. Learn by doing — each step creates real content in your vault. Three tracks (researcher, manager, personal) with a universal learning arc. Triggers on "/tutorial", "walk me through", "how do I use this".
learn
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".