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 agentmods add skills/dunialabs/mcp-servers/pdf-processingnpx skills add dunialabs/mcp-servers --skill pdf-processinggit clone --depth 1 https://github.com/dunialabs/mcp-serversWrote 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/dunialabs/mcp-servers/pdf-processing)<a href="https://agentmods.dev/skills/dunialabs/mcp-servers/pdf-processing"><img src="https://agentmods.dev/badge/skills/dunialabs/mcp-servers/pdf-processing.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.02261 |
| Opus 5 | $0.00024 | $0.01130 |
| Sonnet 5 | $0.00010 | $0.00452 |
| Haiku 4.5 | $0.00005 | $0.00226 |
Grade A, and why
pdf-processing 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Processing
Comprehensive PDF manipulation guide with Python code examples and best practices.
About This Skill
This skill provides code references and implementation patterns for PDF processing tasks. It includes ready-to-use Python code snippets that Claude can adapt and write to your project when needed.
This is a reference skill, not an executable package. The example scripts in scripts/ directory serve as templates. Claude will read these examples and create appropriate code for your specific use case on the host machine.
Quick Reference
| Task | Script | Example |
|---|---|---|
| Extract text | extract_text.py |
python scripts/extract_text.py input.pdf output.txt |
| Extract tables | extract_tables.py |
python scripts/extract_tables.py input.pdf output.csv |
| Merge PDFs | merge_pdfs.py |
python scripts/merge_pdfs.py output.pdf file1.pdf file2.pdf |
| Split PDF | split_pdf.py |
python scripts/split_pdf.py input.pdf output_dir/ |
| Add watermark | add_watermark.py |
python scripts/add_watermark.py input.pdf output.pdf "CONFIDENTIAL" |
| Encrypt/decrypt | protect_pdf.py |
python scripts/protect_pdf.py encrypt input.pdf output.pdf password |
| Fill forms | fill_form.py |
python scripts/fill_form.py fill input.pdf output.pdf data.json |
Pre-built Scripts
All scripts are located in the scripts/ directory and include comprehensive error handling and help text.
1. Extract Text - extract_text.py
Extract text from PDF files with layout preservation and OCR support.
# Basic text extraction
python scripts/extract_text.py document.pdf output.txt
# Preserve layout
python scripts/extract_text.py document.pdf output.txt --layout
# Use OCR for scanned PDFs
python scripts/extract_text.py scanned.pdf output.txt --ocr
# View help
python scripts/extract_text.py --help
Features:
- Layout preservation mode
- OCR support for scanned documents
- Progress reporting
- UTF-8 encoding
What ships with it
11 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.
- README.md 4.0 KB
- references/advanced-examples.md 15 KB
- references/library-guide.md 9.6 KB
- references/troubleshooting.md 14 KB
- scripts/add_watermark.py 3.1 KB runs code
- scripts/extract_tables.py 3.6 KB runs code
- scripts/extract_text.py 2.6 KB runs code
- scripts/fill_form.py 4.0 KB runs code
- scripts/merge_pdfs.py 1.5 KB runs code
- scripts/protect_pdf.py 2.4 KB runs code
- scripts/split_pdf.py 2.7 KB runs code
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.
- 4d ago First seen · 370 lines · 49 tokens per session scan A 93065041f6ab
pdf-processing is a skill published in the GitHub repository dunialabs/mcp-servers (7 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 2,261 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.
Other skills, from other repositories
agent-output-formats
Convert the canonical markdown+JSON deliverable of any SfSkills runtime agent into Excel, PDF, CSV, Notion card, ServiceNow ticket, or similar downstream format without adding dependencies to the consumer's project. NOT for an Agentforce action's output — use agentforce/agent-actions. NOT for exporting Salesforce data…
agent-output-formats
Convert the canonical markdown+JSON deliverable of any SfSkills runtime agent into Excel, PDF, CSV, Notion card, ServiceNow ticket, or similar downstream format WITHOUT polluting the consumer's project with new dependencies or regenerating from the agent's source logic. NOT for authoring new agent output formats (use…
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.
paddleocr-doc-parsing
Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表…
paper-reader
Use when user asks to "read paper", "analyze paper", "summarize paper", "读论文", "分析文献", "帮我看一下这篇paper", "论文笔记", or provides a PDF file that appears to be an academic paper. Specialized for CV/DL papers. Also supports Zotero integration: "读一下这篇论文 ...", "快速看一下这篇论文 ...", "批判性分析这篇论文 ...", "读一下 Zotero 里的 XXX", "批量读一下 Zotero…
citra
Skill "citra" from SylphxAI/pdf-reader-mcp, covering citra — pdf evidence for agents, install, or, tools and sdk.