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 slogsdon/skills-design --skill pdf-paginatedgit clone --depth 1 https://github.com/slogsdon/skills-designWrote 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/slogsdon/skills-design/pdf-paginated)<a href="https://agentmods.dev/skills/slogsdon/skills-design/pdf-paginated"><img src="https://agentmods.dev/badge/skills/slogsdon/skills-design/pdf-paginated/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/slogsdon/skills-design/pdf-paginated"><img src="https://agentmods.dev/badge/skills/slogsdon/skills-design/pdf-paginated.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 | $0.00162 | $0.01226 |
| Opus 5 | $0.00081 | $0.00613 |
| Sonnet 5 | $0.00032 | $0.00245 |
| Haiku 4.5 | $0.00016 | $0.00123 |
Grade A, and why
pdf-paginated 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 10d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: pdf-paginated
Paginated document PDF via headless Chromium page.pdf({format, margin}). No
.canvas targeting — the whole document flows across paper pages. A folio footer
(title left, page X / Y right, JetBrains Mono) is rendered in the bottom margin.
When to use
- Long-form documents where the reader expects pages: an essay, a field guide, a spec, a report body, a letter.
- When the output should be Letter or A4 with real margins and page numbers, not a single tall canvas.
Skip if:
- The artifact is a fixed-size design canvas (social post, business card, blog
hero, audit-report canvas). Use
pdf-html— it sizes the PDF to the canvas. - You want a PNG. Use
screenshot-html.
The HTML it expects
Plain document-flow HTML, NOT the .canvas convention:
- Content flows normally (
body→article). No fixed-width.canvaswrapper. - Give the reading column a measure with
max-width(e.g.64ch) centered, and put the page surface color onbody(it prints becauseprintBackgroundis on). - Do not set
@pagesize/margins in CSS — the script owns paper size and margins via--format/--margin. A CSS@pagemargin would double up. - Optional
@media printrules to keep things tidy across page breaks:h2, li { break-inside: avoid; }andh2 { break-after: avoid; }. - Set a clean
<title>— it becomes the footer's running head. - Self-contained styles (inline
<style>or a resolvable@import); web fonts load fine (the script waits fordocument.fonts.ready).
How to run
node skills/pdf-paginated/scripts/pdf-paginated.mjs <dir> [--output <dir>] [--format Letter|A4] [--margin <css>] [--bleed <color>] [--no-footer]
Flags:
<dir>(positional, default.): directory scanned recursively for*.html.screenshots/,pdfs/, and hidden dirs are skipped.--output <dir>(default<dir>/pdfs): where PDFs are written, one per HTML file.--format(defaultLetter):LetterorA4.--margin(default0.9in): CSS length applied to all four sides. Ignored in bleed mode.--bleed <color>: full-bleed page surface. See below.--no-footer: drop the folio footer (in bleed mode the footer strip still paints).
What ships with it
2 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.
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.
- 10d ago First seen · 103 lines · 162 tokens per session scan A f5f5cef8abd6
pdf-paginated is a skill published in the GitHub repository slogsdon/skills-design (3 stars, last pushed 27d ago), licensed MIT. It adds 162 tokens to every session and 1,226 once invoked, about $0.0008 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-image-text-extractor
An OCR tool that reads text from images and PDF documents. OCR means converting text in a picture or scanned document into editable text, while keeping the source structure in the result.
html-to-pdf
Export HTML pages to print-quality vector PDFs using Playwright's page.pdf() API. Trigger with /html-to-pdf or when the user wants to export an HTML page to PDF, create a print-ready PDF from HTML, or generate a PDF of a handout, card, flyer, or any HTML design.
paddleocr-doc-parsing
A document-reading tool for turning PDFs and document images into structured Markdown or JSON. It can preserve tables, formulas, figures, seals, charts, headers, columns, and reading order.
paddleocr-text-recognition
An OCR tool for extracting exact text from images, photos, screenshots, scans, and scanned PDFs. OCR means turning text visible in an image into machine-readable text.
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
markitdown
Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.