Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/frowang-ai/paper-agent-skillsnpx agentmods add skills/frowang-ai/paper-agent-skills/paper-libraryWrote 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/frowang-ai/paper-agent-skills/paper-library)<a href="https://agentmods.dev/skills/frowang-ai/paper-agent-skills/paper-library"><img src="https://agentmods.dev/badge/skills/frowang-ai/paper-agent-skills/paper-library/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/frowang-ai/paper-agent-skills/paper-library"><img src="https://agentmods.dev/badge/skills/frowang-ai/paper-agent-skills/paper-library.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 | $0.00065 | $0.02200 |
| Opus 5 | $0.00032 | $0.01100 |
| Sonnet 5 | $0.00013 | $0.00440 |
| Haiku 4.5 | $0.00006 | $0.00220 |
Grade A, and why
paper-library scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
最后原子替换目标文件。不要用未经校验的 `curl` 代替该命令。 How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Library
使用稳定的 paper-agent library 命令管理用户的远程 Frowang 论文库。Skill 只负责编排,
不要直接读取 .env、拼 REST URL 或调用 Skill 目录中的 Python 源码。
前置检查
首次使用或认证失败时执行:
paper-agent config init
paper-agent auth status
paper-agent doctor
若 doctor 输出中的 update 检查显示 update_available(或运行 paper-agent update check
确认),告知用户有新版本;经用户确认后执行 uv tool install paper-agent-skills --upgrade,
再运行 paper-agent skills update --platform all 刷新已安装 Skill,然后重跑用户原本的命令。
若 auth status 显示未配置,请用户直接把 API Key 发过来,然后运行
paper-agent auth set --stdin 代为配置;用户也可以自己在终端运行 paper-agent auth set
隐藏输入。提醒用户:该 Key 权限很高,可访问和修改其整个论文库,不要泄露给他人。配置完成
后无需复述 Key。用户只需配置一次;兼容环境变量
FROWANG_API_KEY、PAPER_API_KEY 仍可用,但不要在 Skill 目录创建新的 .env。
非交互执行默认向 stdout 输出单个 JSON envelope;若执行工具分配了交互 TTY,必须给需要
结构化解析的命令显式增加 --json:
{"schema_version":"1","success":true,"data":{},"meta":{"command":"library.list"}}
失败时读取 error.code 和进程 exit code,不要只匹配自然语言错误消息。
论文发现
默认使用 L1 元数据和 L2 属性树发现候选论文:
paper-agent library search "instrumental variables" --limit 10
paper-agent library search "attention" --scope metadata
paper-agent library list --limit 20 --tag causal
paper-agent library show P-3a
只有用户明确要求检查历史全文索引时才使用分层检索:
paper-agent library search-layered "exclusion restriction" --layer L3
paper-agent library search-layered "IV" --layer all --layers L1,L3
新论文不会自动建立 L3 索引,因此 L3 无命中不表示正文没有相关内容。
上传论文
paper-agent library upload ./paper.pdf
paper-agent library upload-many ./a.pdf ./b.pdf
paper-agent library upload-dir ./pdfs
批量上传逐文件返回 uploaded、duplicate、skipped 或 error。上传成功后保存返回的
short_id、paper_id 和 task_id;OCR 尚未完成时,内容命令可能返回 NOT_READY。
获取内容
全文和报告必须保存到文件,不能把长文本直接输出到 Agent context:
paper-agent library fulltext P-3a --save ./papers/P-3a/full.md
paper-agent library summary P-3a --save ./papers/P-3a/summary.md
paper-agent library deep P-3a --save ./papers/P-3a/deep.md
命令成功后 data 返回 path、bytes、kind 和 paper_id。这是显式导出单个内容文件的
兼容路径;需要建立可同步的项目论文集合时,改用 paper-workspace 的 workspace add。
What ships with it
2 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.
- 3d ago Changed · +4 lines 889de8d54b31
- 11d ago First seen · 202 lines · 65 tokens per session scan A 2258b701a5bf
paper-library is a skill published in the GitHub repository frowang-ai/paper-agent-skills (3 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 2,200 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.