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 rojim666/SztuCode --skill pdf-monstergit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/pdf-monster)<a href="https://agentmods.dev/skills/rojim666/sztucode/pdf-monster"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/pdf-monster/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/rojim666/sztucode/pdf-monster"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/pdf-monster.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 | $0.00077 | $0.01435 |
| Opus 5 | $0.00039 | $0.00718 |
| Sonnet 5 | $0.00015 | $0.00287 |
| Haiku 4.5 | $0.00008 | $0.00144 |
Grade C, and why
pdf-monster scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf -- /tmp/pdf-monster-... How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Monster
Core Rule
Treat PDF files as source artifacts that must be converted into model-readable evidence before analysis. Do not create output/, analysis/, pages/, or similar folders in the user's working directory unless the user explicitly asks to save extracted artifacts.
Use the bundled scripts/analyze_pdf.py first. Resolve this path from the skill root, not from the user's current working directory. It prints JSON to stdout, extracts text in-place, and writes only image artifacts to an OS temporary directory unless --save-to is provided.
Quick Start
Run the bundled script by resolving its path from this skill's root directory, not from the user's current working directory. Set SKILL_DIR to the absolute path of the directory containing this SKILL.md first:
SKILL_DIR=<absolute path to this skill>
python3 "$SKILL_DIR/scripts/analyze_pdf.py" path/to/file.pdf --json
Setup
Python 3 is required. Before first use, check whether PyMuPDF is already available:
python3 -c "import fitz"
If that fails and the agent is allowed to run pip/network installs, install the recommended dependency from this skill's requirements.txt:
python3 -m pip install -r "$SKILL_DIR/requirements.txt"
If dependency installation is not allowed, continue with the script anyway; it can use Poppler fallbacks when available. Optional system tools improve coverage when PyMuPDF is unavailable or OCR is needed, but do not install system packages automatically:
- Poppler:
pdfinfo,pdftotext,pdftoppm,pdfimages - Tesseract:
tesseractplus any needed language data, such asengorkor
For visual-heavy or scanned documents:
python3 scripts/analyze_pdf.py path/to/file.pdf --render-pages all --ocr auto --json
For Korean/English OCR, use Tesseract language data and pass:
python3 scripts/analyze_pdf.py path/to/file.pdf --render-pages all --ocr auto --ocr-lang kor+eng --json
For text-only inspection with no temporary image artifacts:
What ships with it
4 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.
- 4d ago First seen · 128 lines · 77 tokens per session scan C 38a276be68ba
pdf-monster is a skill published in the GitHub repository rojim666/SztuCode (64 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,435 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
pdf-official
Use this skill to read, compose, transform, or fill a PDF: extracting text, tables, metadata, or images; merging, splitting, rotating, cropping, watermarking, or compressing pages; building a report, invoice, or certificate; filling form fields or overlaying values on a scan; running optical character recognition…
pdf-processor
A workflow for working with PDF files, a document format that preserves page layout across devices.
report-to-pdf
Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing Data Analytics report, dashboard, or inline chart export into a PDF artifact.
papyrus-diagnose-compilation
Diagnose and fix LaTeX compilation failures. Use when the document does not compile, pdflatex/bibtex/biber/tectonic errors out, the PDF is stale, or the author reports a build/compile error in the Papyrus editor.
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
moai-docs-generation
Documentation generation patterns for technical specs, API docs, user guides, and knowledge bases using real tools like Sphinx, MkDocs, TypeDoc, and Nextra. Use when creating docs from code, building doc sites, or automating documentation workflows.