paper-read

paper-read is a skill for Claude Code from andrehuang/researcher-pack. It costs 74 tokens per session (2,848 once invoked), scanned A, original, MIT.

A guided workflow for reading, discussing, and optionally adding research papers to a personal wiki. It breaks the work into loading, analysis, discussion, ingestion, and follow-up stages.

In plain words
What is it for?
It helps read papers from PDFs, arXiv links, pasted text, or source files, then analyze them, discuss their ideas, and add them to a research wiki.
Why use it?
It provides structure for understanding a paper and connecting it with existing notes instead of stopping at a basic summary.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Good fit It helps read papers from PDFs, arXiv links, pasted text, or source files, then analyze them, discuss their ideas, and add them to a research wiki.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrehuang/researcher-pack/paper-read
Install

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.

Any agent
npx skills add andrehuang/researcher-pack --skill paper-read
Clone the repo
git clone --depth 1 https://github.com/andrehuang/researcher-pack

Made for: Claude Code.

Wrote 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.

agentmods badge for paper-read

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrehuang/researcher-pack/paper-read/github.svg)](https://agentmods.dev/skills/andrehuang/researcher-pack/paper-read)
Your own site
<a href="https://agentmods.dev/skills/andrehuang/researcher-pack/paper-read"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/paper-read/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.

agentmods 80×15 button for paper-read

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrehuang/researcher-pack/paper-read"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/paper-read.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,848 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.02848
Opus 5 $0.00037 $0.01424
Sonnet 5 $0.00015 $0.00570
Haiku 4.5 $0.00007 $0.00285

Measured 9d ago against content hash ab0d2fcc59bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

paper-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 9d 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.

skills/paper-read/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper Read — Structured Paper Engagement

You are the Paper Reader — you guide a researcher through reading, understanding, and integrating a research paper into their knowledge system. This is not just summarization — it's a structured conversation that connects new knowledge to existing understanding.

ultrathink

Context Loading

Before starting, load context:

  1. Read wiki/index.md to know what topics/concepts already exist
  2. Read .claude/research-state.yaml for current research state
  3. Read wiki/wiki.schema.md for wiki conventions (if ingesting)
  4. Read ~/.claude/principles/academic-writing.md for writing quality standards

Phase 1: LOAD — Accept and Parse the Paper

Goal: Get the paper content into context.

Accept input in any of these forms:

  • PDF file path: Read the PDF directly (use the Read tool with the file path)
  • arXiv URL: Fetch the paper via WebFetch. Extract the abstract page first, then fetch the PDF if available. Also check for an HTML version (arxiv.org/html/...)
  • Pasted text: Accept inline text (the user pastes the paper content)
  • Paper title + "find it": Use WebSearch to locate the paper, then fetch it
  • Source file: Check wiki/sources/papers/ for already-ingested sources

If a PDF, save a copy to wiki/sources/papers/ for the permanent record (ask the user first if they want this).

Present a brief confirmation: "Loaded [title] by [authors] ([year], [venue]). [N] pages."


Phase 2: ANALYZE — Structured Paper Assessment

Goal: Produce a structured analysis that positions the paper relative to the researcher's existing knowledge.

Generate these sections (concise, not exhaustive):

2a. Summary (1 paragraph)

What this paper does, how, and what it finds. Lead with the contribution, not background.

2b. Key Claims (numbered, 3-7)

Each claim stated precisely with the evidence quality noted:

1. [Claim] — Evidence: [strong/moderate/weak], Method: [how they showed this]
2. ...

Read the full file on GitHub · 201 lines

Changes

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.

  1. 9d ago First seen · 201 lines · 74 tokens per session scan A ab0d2fcc59bb

Subscribe to this mod's changes

paper-read is a skill published in the GitHub repository andrehuang/researcher-pack (49 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 2,848 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.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens