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/phodal/routa/pdfnpx skills add phodal/routa --skill pdfgit clone --depth 1 https://github.com/phodal/routaWrote 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/phodal/routa/pdf)<a href="https://agentmods.dev/skills/phodal/routa/pdf"><img src="https://agentmods.dev/badge/skills/phodal/routa/pdf.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 | $0.00077 | $0.01198 |
| Opus 5 | $0.00039 | $0.00599 |
| Sonnet 5 | $0.00015 | $0.00240 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade A, and why
pdf 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Skill
Use the repo-local toolkit under tools/pdfs/. The default operating loop is:
- Render to images.
- Inspect layout visually.
- Perform the edit, extraction, or generation.
- Re-render and verify.
Choose the right authoring path first
Even if the user wants a PDF deliverable, PDF is not always the right authoring format.
- Text-heavy business docs: author in DOCX first, then convert with
python3 tools/pdfs/scripts/lo_convert_to_pdf.py ... - Slide-like visual layouts: author in PPTX first, then export to PDF
- Direct PDF generation or low-level edits: use this toolkit
If you are hand-tuning line breaks in a programmatically generated PDF, stop and reconsider whether DOCX or PPTX is the better source format.
Core loop
Render before and after any meaningful change:
python3 tools/pdfs/scripts/render_pdf.py input.pdf --out_dir /tmp/pdf-renders-in --dpi 200
python3 tools/pdfs/scripts/compare_renders.py before.pdf after.pdf --out_dir /tmp/pdf-diff --dpi 200
Rendered PNGs are the source of truth for layout QA. Do not trust extracted text alone for tables, forms, spacing, or clipping.
Common workflows
Inspect / extract
python3 tools/pdfs/scripts/pdf_inspect.py input.pdf
python3 tools/pdfs/scripts/pdf_extract.py text input.pdf --method pdfplumber
python3 tools/pdfs/scripts/pdf_extract.py tables input.pdf
python3 tools/pdfs/scripts/pdf_extract.py forms input.pdf --include_widgets
Edit / normalize
python3 tools/pdfs/scripts/pdf_edit.py paginate input.pdf -o output.pdf
python3 tools/pdfs/scripts/pdf_edit.py merge a.pdf b.pdf -o merged.pdf
python3 tools/pdfs/scripts/pdf_edit.py rotate input.pdf -o rotated.pdf --pages 1 --degrees 90
python3 tools/pdfs/scripts/pdf_preflight.py input.pdf
Redact / OCR
python3 tools/pdfs/scripts/pdf_redact.py text input.pdf redacted.pdf --text "secret" --ignore_case
python3 tools/pdfs/scripts/ocr_pdf.py scan.pdf -o searchable.pdf --force
Create / convert
What ships with it
32 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.
- examples/smoke_test.md 2.2 KB
- js/extract_form_fields.mjs 1.1 KB runs code
- js/extract_text_pdfjs.mjs 1.3 KB runs code
- js/fill_form.mjs 2.6 KB runs code
- js/install_deps.sh 326 B runs code
- js/package-lock.json 11 KB
- js/package.json 145 B
- LICENSE.txt 1.4 KB
- scripts/batch_pdf.py 4.7 KB runs code
- scripts/box_picker_html.py 7.8 KB runs code
- scripts/compare_renders.py 5.2 KB runs code
- scripts/create_montage.py 3.4 KB runs code
- scripts/edit_smoketest.py 2.0 KB runs code
- scripts/forms_smoketest.py 2.9 KB runs code
- scripts/html_to_pdf.py 2.1 KB runs code
- scripts/latex_to_pdf.py 3.7 KB runs code
- scripts/lo_convert_to_pdf.py 2.8 KB runs code
- scripts/make_watermark_pdf.py 2.2 KB runs code
- scripts/md_to_pdf.py 2.9 KB runs code
- scripts/ocr_pdf.py 6.4 KB runs code
- scripts/pdf_edit.py 19 KB runs code
- scripts/pdf_extract.py 22 KB runs code
- scripts/pdf_inspect.py 5.8 KB runs code
- scripts/pdf_preflight.py 6.3 KB runs code
- scripts/pdf_redact.py 11 KB runs code
- scripts/place_text_by_boxes.py 11 KB runs code
- scripts/redact_smoketest.py 3.0 KB runs code
- scripts/render_pdf.py 5.6 KB runs code
- scripts/renderer_parity.py 4.4 KB runs code
- tasks/forms_debugging.md 1.6 KB
- tasks/js_tools.md 1.3 KB
- troubleshooting/common.md 2.0 KB
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 · 126 lines · 77 tokens per session scan A 568eadd169f1
pdf is a skill published in the GitHub repository phodal/routa (1,807 stars, last pushed 21d ago), licensed MIT. It adds 77 tokens to every session and 1,198 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.
Other skills, from other repositories
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.
graphic-ebook
Creates professionally designed B2B SaaS e-books in HTML + CSS, exported as print-ready PDF. 3–10 pages, 9 style presets, 11 page layout types. Trigger when user says "create an ebook", "design a lead magnet", "make a PDF guide", "build a gated content piece", "write a B2B ebook", "design a white paper", "create a…
larksnap-fetch
把飞书/Lark 文档或普通网页抓取并保存到本地，也能编辑用户有权限的飞书文档，并用已登录浏览器执行一次网页搜索。用户要求下载、导出、抓取、写入飞书文档，或联网搜索资料/参考链接时使用本技能，即使没有提到 larksnap。底层通过技能自带 daemon 桥接已登录的 larksnap 浏览器扩展；arXiv 使用独立脚本。.