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 jokull/icelandic-data --skill pdf-parsinggit clone --depth 1 https://github.com/jokull/icelandic-dataWrote 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/jokull/icelandic-data/pdf-parsing)<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.
<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>- NVIDIA SkillSpector warn
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]
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 | $0.00030 | $0.02670 |
| Opus 5 | $0.00015 | $0.01335 |
| Sonnet 5 | $0.00006 | $0.00534 |
| Haiku 4.5 | $0.00003 | $0.00267 |
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.
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 | docling — export_to_markdown(), export_to_html() |
| Text with font info (name, size per fragment) | liteparse — .fontName, .fontSize on each TextItem |
| Page screenshots at configurable DPI | liteparse — parser.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
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.
- 9d ago First seen · 300 lines · 30 tokens per session scan A b45a2d9c60c2
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.
Other skills, from other repositories
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.
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.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
pdf-text-extraction-fallback-85d5ca
Fallback workflow for extracting text from PDFs when readfile returns binary data.