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 Agentchengfeng/paper-reading-skills --skill paper-readinggit clone --depth 1 https://github.com/Agentchengfeng/paper-reading-skillsWrote 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/agentchengfeng/paper-reading-skills/paper-reading)<a href="https://agentmods.dev/skills/agentchengfeng/paper-reading-skills/paper-reading"><img src="https://agentmods.dev/badge/skills/agentchengfeng/paper-reading-skills/paper-reading/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/skills/agentchengfeng/paper-reading-skills/paper-reading"><img src="https://agentmods.dev/badge/skills/agentchengfeng/paper-reading-skills/paper-reading.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 | $0.00073 | $0.00700 |
| Opus 5 | $0.00036 | $0.00350 |
| Sonnet 5 | $0.00015 | $0.00140 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
paper-reading 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 11d 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.
What it actually says
论文协作阅读
原则
- 只定义方法、结构、组件契约和执行边界，不定义某篇论文、模型、系统、指标或实验内容。
- 具体内容必须来自当次论文材料、repo、用户补充或当前 HTML。
~/.codex/skills/paper-reading是~/.claude/skills/paper-reading的软链；改这里即同步两边。
组件
paper-reading/
├── docs/01-paper-prompt.md 论文解读方法
├── docs/02-html-contract.md HTML 协作契约
├── docs/03-layout-standard.md 页面版式标准
└── scripts/bridge.py 本地标记写回脚本
来源与协议
- 官方来源：
https://github.com/Agentchengfeng/paper-reading-skills - 作者：
成峰 / AI产品自由 - 协议：Apache-2.0；复制、改造或二次发布时保留
LICENSE和NOTICE.md。
资源路由
- 从论文或 repo 生成/重写正文：读
docs/01-paper-prompt.md。 - 创建、修复或优化论文 HTML：读
docs/03-layout-standard.md，再读docs/02-html-contract.md。 - 处理划线标记、补充解释、作图或正文重组：读
docs/02-html-contract.md。 - 启动本地标记写回：运行
scripts/bridge.py，不要重写 bridge 逻辑。
硬规则
- 解读开头先写研究目的，再写核心结论。
- 页面左侧使用内容阅读地图，不做机械章节目录。
- 稍微复杂的内容默认用 SVG 图解：机制链、流程、对照、公式关系、调度逻辑、瓶颈链和概念间依赖，不能只靠长段文字解释。
- 划线协作只保留三类动作：
名词讲解、逻辑梳理、作图理解。 - 用户说
重组、整合、合并到正文、改成新段落时，把批注内容融入正文，删除对应疑问卡片和解释块；有用 SVG 保留为普通正文图。 - 本地 HTML 的刷新、DOM 检查和交互验证默认使用 Codex 内置浏览器；验证 URL 使用 localhost，不用
file://代替。
边界
- HTML 不放 API key，不直接调用模型。
- Bridge 只接收标记、写 JSONL、改 HTML；不生成解释。
- 不新增 README、examples、templates、runtime 解释层或未验证示例。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 51 lines · 73 tokens per session scan A a9f814e2d87d
paper-reading is a skill published in the GitHub repository Agentchengfeng/paper-reading-skills (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 700 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.