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/rangerrick337/operator-os/pdf-conversionnpx skills add rangerrick337/operator-os --skill pdf-conversiongit clone --depth 1 https://github.com/rangerrick337/operator-osWrote 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/rangerrick337/operator-os/pdf-conversion)<a href="https://agentmods.dev/skills/rangerrick337/operator-os/pdf-conversion"><img src="https://agentmods.dev/badge/skills/rangerrick337/operator-os/pdf-conversion.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 | $0.00035 | $0.00262 |
| Opus 5 | $0.00017 | $0.00131 |
| Sonnet 5 | $0.00007 | $0.00052 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
pdf-conversion 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 5d 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.
What it actually says
PDF Conversion Skill
Overview
Converts PDF files to clean, readable Markdown format with proper formatting, image extraction, and table preservation.
When to Use
- "Convert this PDF to markdown"
- "Extract text from PDF"
- "Transform PDF to MD format"
- "Process PDFs in folder X"
Related Resources
- SOP:
Operator Team OS/1. SOPs/convert_pdfs_to_markdown.md
Scripts
| Script | Purpose |
|---|---|
pdf_to_md.py |
Main PDF to Markdown converter |
Usage
python3 scripts/pdf_to_md.py /path/to/input.pdf /path/to/output.md
Features
- Text extraction with OCR fallback
- Image extraction and embedding
- Table detection and formatting
- Heading structure preservation
- Automatic cleanup of formatting artifacts
Edge Cases
- Scanned PDFs: Falls back to OCR
- Complex tables: Best-effort conversion
- Encrypted PDFs: Will fail (requires password)
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.
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.
- 5d ago First seen · 43 lines · 35 tokens per session scan A 0b357a8ce2b5
pdf-conversion is a skill published in the GitHub repository rangerrick337/operator-os (10 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 262 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
pdf-processing
Process and extract information from PDF documents. Use this skill when the user asks to read, analyze, or extract data from PDF files.
markitdown
Convert files, URLs, and documents to Markdown using the markitdown MCP server. Activate when the user asks to convert, extract, or read content from PDFs, Word docs, PowerPoints, spreadsheets, images, audio files, or any URL.
ocr-run
使用场景：用户在 Mac 上运行 /collate:ocr-run、对清理过的历史论文 PDF 做文字识别、说出"跑 OCR""识别文字""PDF 转文字""MinerU""百度 OCR""把扫描件识别出来""出 Markdown""准备校对"等。这个 skill 支持百度 OCR 和 MinerU 双引擎，根据 /.env 里的 OCRENGINE 自动选（mineru 优先精度、baidu 成本低用户已有 key）。它专门优化了历史文献的识别参数：繁体竖排、古籍异体字、民国新式标点、现代简体；并产出「原图 + OCR 文本逐页并排」的 preview.html…
prep-scan
使用场景：用户在 Mac 上运行 /collate:prep-scan、提供一个扫描版 PDF、说出"去水印""去馆藏章""去知网水印""去页眉页脚""预处理论文 PDF""清理扫描件""图书馆章""历史文献 OCR 前处理""国家图书馆藏""中华再造善本"等。典型输入是用户从知网、读秀、国图扫描服务、档案馆数字资源、古籍数据库下载的 PDF，上面常见问题是：红蓝馆藏章、数据库 logo 水印（知网/维普/读秀/CNKI）、扫描日期戳、页眉刊名、页脚馆藏号、古籍版心鱼尾。这个 skill 把这些都处理干净并合回一份 cleaned.pdf，给下一步 OCR 用。这个 skill 应当主动触发，只要用户提到历史论文 PDF…
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.
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.