paper-agent: Skill for Claude Code

.claude/skills/pdf-annotation-extractor/SKILL.md

pdf-annotation-extractor is a skill for Claude Code from Guo-Chenxu/paper-agent. It costs 47 tokens per session (1,070 once invoked), scanned A, original, Apache-2.0.

A tool for extracting highlights, comments, notes, and other annotations from academic-paper PDF files, along with nearby source text.

In plain words
What is it for?
Use it to export paper annotations as Markdown or JSON, including context, authors, dates, and comment content.
Why use it?
It saves the work of manually matching PDF comments to the passages they refer to.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

This is Guo-Chenxu/paper-agent's own configuration. It tells Claude Code how to work on paper-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paper-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Guo-Chenxu/paper-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Guo-Chenxu/paper-agent/main/.claude/skills/pdf-annotation-extractor/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Guo-Chenxu/paper-agent

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 pdf-annotation-extractor

README.md
[![agentmods](https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/pdf-annotation-extractor/github.svg)](https://agentmods.dev/skills/guo-chenxu/paper-agent/pdf-annotation-extractor)
Your own site
<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/pdf-annotation-extractor"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/pdf-annotation-extractor/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 pdf-annotation-extractor

Your own site · 80×15
<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/pdf-annotation-extractor"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/pdf-annotation-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,070 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 $0.00047 $0.01070
Opus 5 $0.00023 $0.00535
Sonnet 5 $0.00009 $0.00214
Haiku 4.5 $0.00005 $0.00107

Measured 9d ago against content hash 27c282c2acaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pdf-annotation-extractor 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/extract_pdf_annotations.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/pdf-annotation-extractor/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Annotation Extractor

Goal

Read a PDF and extract:

  1. The PDF annotation list, including highlight, underline, strikeout, sticky note, text comment, and similar annotations.
  2. The source text snippet corresponding to each annotation.
  3. A surrounding context excerpt for every annotation.
  4. The annotation author, creation/modification time, and comment content.

Every annotation entry must include context: the sentence-level page text located by the annotation coordinates, starting after the previous period (. or ) and ending at the next period. Markdown must show a Context section for every annotation even when no extractable context is found. Markdown is the default output because it is easy to read manually. Use JSON when downstream programmatic processing is needed.

When To Use

  • The user asks to "extract PDF annotations", "export highlights", "organize paper comments", or read comments/notes/annotations.
  • The user provides an academic-paper PDF and wants a new file containing annotations plus their corresponding source text snippets.
  • The user needs to convert highlights/comments from a PDF reader into Markdown or JSON.

Requirements

The script depends on PyMuPDF (fitz). If the dependency is missing, install it first:

python -m pip install pymupdf

Quick Reference

Need Use
Human review Markdown output
Programmatic processing JSON output
Per-annotation sentence context context field / **Context:** section, located by annotation coordinates
Highlighted or underlined text selected_text field / **Selected Text:** section

Basic Workflow

Step 1: Choose output format

Prefer Markdown when the output is for reading, review, and copying.

python .claude/skills/pdf-annotation-extractor/scripts/extract_pdf_annotations.py \
  ./paper-annotation.pdf \
  --output ./paper-annotation_annotations.md

Use JSON when structured data is needed:

python .claude/skills/pdf-annotation-extractor/scripts/extract_pdf_annotations.py \
  ./paper-annotation.pdf \
  --format json \
  --output ./paper-annotation_annotations.json

Read the full file on GitHub · 130 lines

Files

What ships with it

1 file 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.

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 · 130 lines · 47 tokens per session scan A 27c282c2acaa

Subscribe to this mod's changes

pdf-annotation-extractor is a skill published in the GitHub repository Guo-Chenxu/paper-agent (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,070 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories