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 skills add holon-run/holon --skill pdfgit clone --depth 1 https://github.com/holon-run/holonWrote 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/holon-run/holon/pdf)<a href="https://agentmods.dev/skills/holon-run/holon/pdf"><img src="https://agentmods.dev/badge/skills/holon-run/holon/pdf/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.
<a href="https://agentmods.dev/skills/holon-run/holon/pdf"><img src="https://agentmods.dev/badge/skills/holon-run/holon/pdf.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00033 | $0.00863 |
| Opus 5 | $0.00016 | $0.00432 |
| Sonnet 5 | $0.00007 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00086 |
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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summary
Use this skill for PDF reading, extraction, generation, page operations, forms, rendering, and optional OCR. Match the tool to the operation instead of treating PDF as a simple editable text format.
Common neutral backends include pypdf for page and metadata operations,
pdfplumber for text and table inspection, ReportLab or pdf-lib for
generation, Poppler for rendering, and qpdf for structural checks. OCR is a
separate, explicitly selected path such as local Tesseract.
When To Use
- Extracting text, tables, metadata, links, bookmarks, or form information
- Splitting, merging, rotating, cropping, stamping, or encrypting documents
- Generating a PDF from structured content
- Rendering pages for visual review
- Running OCR on operator-approved scanned pages
- Comparing page-level content before and after a transformation
Safety Boundaries
- Preserve the original and write transformed output to a new path.
- Treat JavaScript, actions, attachments, forms, links, signatures, and embedded files as untrusted.
- Never execute document JavaScript, launch actions, embedded programs, or external links.
- Do not remove passwords, permissions, signatures, or protection as a way to bypass access controls.
- External OCR or conversion requires explicit approval before upload.
- Warn that any content change can invalidate a digital signature.
If a parser reports corruption, suspicious object expansion, extreme page dimensions, excessive object counts, or unsupported encryption, stop the operation and report the limitation.
Backend Selection
- Use pypdf for page assembly, rotation, cropping, metadata, common forms, and supported encryption operations.
- Use pdfplumber for positioned text and rule-based table extraction.
- Use ReportLab or pdf-lib for deliberate PDF generation and drawing.
- Use Poppler tools for local text extraction or rendering when installed.
- Use qpdf for structural validation and supported transformations.
- Use Tesseract only for explicitly requested local OCR and retain the original page images.
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.
- 2d ago First seen · 93 lines · 33 tokens per session scan A 79a7f3d65847
pdf is a skill published in the GitHub repository holon-run/holon (135 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 863 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 2026-09-07.
Other skills, from other repositories
Use this skill whenever the user wants to do anything with PDF files — reading, extracting text or tables, merging, splitting, rotating, creating new PDFs, adding watermarks, OCR on scanned documents, encrypting/decrypting, or filling forms. Trigger whenever a .pdf file is mentioned or needs to be produced.
invoice
A printable invoice page — sender + recipient block, line items table, tax breakdown, totals, and payment instructions. Use when the brief mentions "invoice", "bill", "billing statement", or "发票".
Create and edit PDFs to a professional standard — generate from content, draw vector/precise layouts, embed custom (incl. CJK/Unicode) fonts, CREATE and fill AcroForm fields (text/checkbox/radio/dropdown), flatten, merge/split/rotate, stamp/watermark, encrypt, and extract text. Use when the user asks Brigade to make a…
filex
Parse workspace files, HTTP(S) file URLs, or supported source URLs such as YouTube into Markdown, inspect source routing, and inspect resumable PDF batch status with the FileX CLI inside an AWorld sandbox. Use for reading, extracting, transcribing, inspecting, summarizing, or answering questions about PDF, Word…
pdf-reader
Extract text from PDF files. Use when reading, parsing, or analyzing PDFs.
paper-summarizer
Agents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PDFs, methodology review, limitations, practical implications, or extracting findings for engineering decisions.