pdf-parsing

pdf-parsing is a skill for Claude Code, Codex from jokull/icelandic-data. It costs 30 tokens per session (2,670 once invoked), scanned A, original, MIT.

A guide for extracting information from PDF and office documents with Docling, LiteParse, and pdfplumber. It compares their handling of tables, document structure, text details, screenshots, and graphics.

In plain words
What is it for?
Use it to extract financial tables, headings, text coordinates and fonts, page images, vector graphics, and content from PDF, DOCX, PPTX, XLSX, or HTML files.
Why use it?
Different documents need different extraction methods, especially when tables have no visible borders or layout carries important meaning.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to extract financial tables, headings, text coordinates and fonts, page images, vector graphics, and content from PDF, DOCX, PPTX, XLSX, or HTML files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jokull/icelandic-data/pdf-parsing
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 jokull/icelandic-data --skill pdf-parsing
Clone the repo
git clone --depth 1 https://github.com/jokull/icelandic-data

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.

agentmods badge for pdf-parsing

README.md
[![agentmods](https://agentmods.dev/badge/skills/jokull/icelandic-data/pdf-parsing/github.svg)](https://agentmods.dev/skills/jokull/icelandic-data/pdf-parsing)
Your own site
<a href="https://agentmods.dev/skills/jokull/icelandic-data/pdf-parsing"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/pdf-parsing/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.

agentmods 80×15 button for pdf-parsing

Your own site · 80×15
<a href="https://agentmods.dev/skills/jokull/icelandic-data/pdf-parsing"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/pdf-parsing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,670 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 299
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.02670
Opus 5 $0.00015 $0.01335
Sonnet 5 $0.00006 $0.00534
Haiku 4.5 $0.00003 $0.00267

Measured 9d ago against content hash b45a2d9c60c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pdf-parsing 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 9d 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.

.agents/skills/pdf-parsing/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Parsing — docling + liteparse + pdfplumber

Three tools for PDF extraction. Each has a sweet spot — use the right one (or combine them).

When to use what

Task Tool
Tables (especially borderless financial) docling — AI layout model (TableFormer) handles ársreikningar with no visible borders
Structured document (headings, sections, reading order) docling — classifies every element with semantic labels
Figure/image extraction as PIL images docling with generate_picture_images=True
Markdown/HTML export doclingexport_to_markdown(), export_to_html()
Text with font info (name, size per fragment) liteparse.fontName, .fontSize on each TextItem
Page screenshots at configurable DPI liteparseparser.screenshot()
Quick text extraction with coordinates liteparse — fast, simple API
Vector graphics detection (rects, curves, lines) pdfplumber — detects infographic vs text pages
Character-level access pdfplumber
DOCX, PPTX, XLSX, HTML docling — same API for all formats

docling (primary tool)

IBM's AI-powered document parser. 97.9% table accuracy on benchmarks. The heavy hitter.

uv pip install docling   # v2.74.0

Basic usage

from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.datamodel.base_models import InputFormat

# Configure — ALWAYS disable OCR for native/digital PDFs
po = PdfPipelineOptions()
po.do_ocr = False                      # most Icelandic public PDFs are native text
po.do_table_structure = True           # TableFormer — the killer feature
po.generate_picture_images = True      # extract figures as PIL images

converter = DocumentConverter(
    format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=po)}
)

result = converter.convert("report.pdf")
doc = result.document

Read the full file on GitHub · 300 lines

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.

  1. 9d ago First seen · 300 lines · 30 tokens per session scan A b45a2d9c60c2

Subscribe to this mod's changes

pdf-parsing is a skill published in the GitHub repository jokull/icelandic-data (52 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 2,670 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 2026-08-30.