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 alaliqing/claude-paper --skill claude-paper-summarygit clone --depth 1 https://github.com/alaliqing/claude-paperWrote 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/alaliqing/claude-paper/claude-paper-summary)<a href="https://agentmods.dev/skills/alaliqing/claude-paper/claude-paper-summary"><img src="https://agentmods.dev/badge/skills/alaliqing/claude-paper/claude-paper-summary/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/alaliqing/claude-paper/claude-paper-summary"><img src="https://agentmods.dev/badge/skills/alaliqing/claude-paper/claude-paper-summary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.02169 |
| Opus 5 | $0.00026 | $0.01085 |
| Sonnet 5 | $0.00010 | $0.00434 |
| Haiku 4.5 | $0.00005 | $0.00217 |
Grade A, and why
claude-paper-summary 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- summary — 89% identical, 36 lines differ
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Agent Compatibility
This file is generated from the existing Claude Paper Skill. Its workflow and output requirements are unchanged; only equivalent host metadata, the plugin-root variable, and cross-skill invocation are adapted.
Resolve CLAUDE_PAPER_PLUGIN_ROOT to the absolute plugin/ directory in this package before each shell invocation. From this SKILL.md, that directory is ../../../plugin.
Treat every ${CLAUDE_PAPER_PLUGIN_ROOT} reference below as that resolved absolute directory. Do not substitute the current workspace root.
When this workflow asks to launch the viewer, load and follow the claude-paper-webui skill.
Quick Paper Summary Workflow
This skill generates a concise summary of a research paper's core ideas and key points.
When to use:
- You want to quickly understand what a paper is about
- You need the main contributions without deep technical details
- You're screening papers to decide which to study in depth
When NOT to use:
- You want comprehensive study materials (use
claude-paper-studyskill instead) - You need code demonstrations
- You want interactive visualizations
Language Detection: Detect the user's language from their input and generate ALL materials in that language.
- Example: User says "我们学习一下这篇论文" → Generate materials in Chinese
- Example: User says "Let's study this paper" → Generate materials in English
Step 0: Check Dependencies (First Run Only)
if [ ! -f "${CLAUDE_PAPER_PLUGIN_ROOT}/.installed" ]; then
echo "First run - installing dependencies..."
cd "${CLAUDE_PAPER_PLUGIN_ROOT}"
npm install || exit 1
# Install Python dependencies for image extraction
python3 -m pip install pymupdf --user 2>/dev/null || pip3 install pymupdf --user 2>/dev/null || echo "Warning: Failed to install pymupdf"
touch "${CLAUDE_PAPER_PLUGIN_ROOT}/.installed"
echo "Dependencies installed!"
fi
Step 1: Download and Parse PDF
Supports multiple input formats:
- Local path:
~/Downloads/paper.pdf - Direct PDF URL:
https://arxiv.org/pdf/1706.03762.pdf - arXiv URL:
https://arxiv.org/abs/1706.03762
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 · 269 lines · 51 tokens per session scan A 98bb1131e572
claude-paper-summary is a skill published in the GitHub repository alaliqing/claude-paper (335 stars, last pushed 27d ago), licensed MIT. It adds 51 tokens to every session and 2,169 once invoked, about $0.0003 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
analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…
datasheet-interpreter
Extracts key specifications from component datasheet PDFs for maker projects. Use when user shares a datasheet PDF URL, asks about component specs, needs pin assignments, I2C addresses, timing requirements, or register maps. Downloads and parses PDF to extract essentials. Complements datasheet-parser for quick lookups.
analyzing-malicious-pdf-with-peepdf
A Chinese-language skill for examining suspicious PDF files with peepdf, pdfid, and pdf-parser. It is intended for static malware analysis, which studies a file without running it.
doa-apidoc
A workflow that creates API documentation from requirements, backend code, or interface definitions. An API is the agreed way that software systems exchange requests and data.
doa-metting
A meeting-minutes tool that turns a meeting summary, notes, or transcript into a structured PDF document. It organizes topics, decisions, unresolved items, action owners, deadlines, and conclusions.
analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.