A skill for working with PDF files using Qubicl's local document tools. PDF is a fixed-layout document format commonly used for forms, reports, and printable files.

Use it to create, inspect, edit, merge, split, fill, watermark, secure, render, or validate PDF files.

It provides procedures and commands for handling common PDF tasks while keeping inspection and output steps consistent. It also supports checking layout by rendering pages as images.

pdf — Skill for Claude Code and Codex by EldanRing/qubicl

Install

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.

Any agent

npx skills add EldanRing/qubicl --skill pdf

Clone the repo

git clone --depth 1 https://github.com/EldanRing/qubicl

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eldanring/qubicl/pdf/github.svg)](https://agentmods.dev/skills/eldanring/qubicl/pdf)

Your own site

<a href="https://agentmods.dev/skills/eldanring/qubicl/pdf"><img src="https://agentmods.dev/badge/skills/eldanring/qubicl/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/eldanring/qubicl/pdf"><img src="https://agentmods.dev/badge/skills/eldanring/qubicl/pdf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 387 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00045	$0.00387
Opus 5.5	$0.00018	$0.00155
Sonnet 5.5	$0.00009	$0.00077
Haiku 4.5	$0.00005	$0.00039

Measured 1mo ago against content hash 320e0cb13f88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo ago.

The scan reads SKILL.md. This mod also ships 13 executable files (scripts/_raster.py, scripts/pdf_create.py, scripts/pdf_fill_form.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/core/pdf/SKILL.md · 26 lines

What it actually says

PDF workflows

Use Qubicl file tools to inspect inputs and save outputs under /home/qubicl. Use exec_command for the deterministic helpers bundled with this skill. Obtain this package's resourceRoot from skill_view; do not assume a client-specific skill directory.

The curated browser, computer, and workstation images provide the declared Python libraries plus Poppler. Run helpers through /opt/qubicl/skills-venv/bin/python. If a dependency is absent, report that the current preset does not support the operation; do not install packages automatically.

Common helpers beneath <resourceRoot>/scripts/:

pdf_read.py FILE --text|--tables|--meta|--fields
pdf_create.py SPEC.json -o OUTPUT.pdf
pdf_merge.py INPUT... -o OUTPUT.pdf
pdf_split.py FILE --pages 1-3,5 -o OUTPUT.pdf
pdf_page_image.py FILE --out-dir DIR
pdf_make_form.py SPEC.json -o OUTPUT.pdf
pdf_fill_form.py FILE --fields-json VALUES.json -o OUTPUT.pdf
pdf_stamp.py, pdf_watermark.py, pdf_meta.py, and pdf_secure.py

Read references/forms.md only for AcroForm work.

For inspection, extract text first and render representative pages when layout matters. Use take_screenshot only for the live desktop; use generated page images for document QA. Verify important outputs by reopening them with a read helper and, when visual fidelity matters, by rendering pages. Never overwrite the only input copy unless the user explicitly requests in-place editing.

Files

What ships with it

15 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.

Changes

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.

1mo ago First seen · 26 lines · 45 tokens per session scan A 320e0cb13f88

Subscribe to this mod's changes

pdf is a skill published in the GitHub repository EldanRing/qubicl (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 387 once invoked, about $0.0002 per session on Opus 5.5. 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.

Documents PDF ai-agents browser-automation docker local-first mcp openapi

pdf

Manipulate PDF files — merge, split, extract pages/text, PDF↔images, OCR, info — via the qpdf / poppler / ocrmypdf CLIs. Use to combine, slice, convert, or OCR PDFs.

AtomicBot-ai/atomic-agent · 56 tokens

pandoc

Convert documents between formats (Markdown, DOCX, HTML, PDF, RST, EPUB, LaTeX) via the pandoc CLI. Use to transform a document from one format to another.

AtomicBot-ai/atomic-agent · 45 tokens

pkf-writing

Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.

Prismer-AI/PrismerCloud · 78 tokens

liteparse

Parse local document files into LLM-ready content on the daemon itself — PDFs → Markdown / structured JSON (with bounding boxes) / page screenshots via the bundled lit CLI. PDF works out of the box, offline, zero external deps (Tesseract + PDFium are bundled): digital PDFs use a near-instant native text path…

Prismer-AI/PrismerCloud · 173 tokens

ingest

Turn external web URLs into LLM-ready content — load + cache web pages (HQCC compression) and search the web. Use whenever the user gives a URL, asks you to read a webpage, or wants top-K pages on a topic. Executes via the cloud load and cloud search CLIs. For local document parsing (PDF text + OCR), use the liteparse…

Prismer-AI/PrismerCloud · 86 tokens

pdf-storybook

Turn a dense PDF or document into an illustrated, partly animated scrollable web story in Live Canvas, using generateimage, generatevideo and canvas assets.

CoWork-OS/CoWork-OS · 34 tokens