PDF Monster

What it does

When your agent uses it

• An agent needs to read
• Reason about PDFs
• Especially when the foundation model cannot ingest PDFs directly

Example prompts

• “/pdf-monster”

Requirements

• Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Run analyze_pdf.py and capture stdout JSON.
2. 2Check warnings, page_count, artifact_root, pages_needing_visual_review, and each page's text_chars, ocr_text_chars, render_path…
3. 3Use text as the primary evidence when it is complete enough.
4. 4Inspect ocr_text when a page has little extracted text or appears scanned.
5. 5Open render_path for pages marked needs_visual_review, and for pages where layout, charts, handwriting, equations, tables, screenshots, or…
6. 6Open embedded_images[].path when the PDF contains standalone figures that may be clearer than the page render.
7. 7Cite page numbers from the manifest when answering.
8. 8Delete temporary artifacts after finishing if artifact_policy is temporary.

What it can do on your machine

Read from SKILL.md and the folder at commit 9e7b281. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

PDF Monster loads about 1.7k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 699 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~99

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 9e7b281, republished under its Apache-2.0 licence (© hashgraph-online). 699 words, ~1,742 tokens.

name

pdf-monster

description

Analyze PDF files by converting them into agent-readable text, OCR text, page render images, and extracted embedded images without polluting the working directory. Use when an agent needs to read, summarize, inspect, compare, quote, or reason about PDFs, especially when the foundation model cannot ingest PDFs directly or when tables, figures, scans, screenshots, or layout matter.

python3 scripts/analyze_pdf.py path/to/file.pdf --json

python3 ${CLAUDE_SKILL_DIR}/scripts/analyze_pdf.py path/to/file.pdf --json

python3 -c "import fitz"

python3 -m pip install -r "${CLAUDE_SKILL_DIR}/requirements.txt"

python3 scripts/analyze_pdf.py path/to/file.pdf --render-pages all --ocr auto --json

python3 scripts/analyze_pdf.py path/to/file.pdf --render-pages all --ocr auto --ocr-lang kor+eng --json

python3 scripts/analyze_pdf.py path/to/file.pdf --render-pages none --no-extract-images --ocr never --json

python3 scripts/analyze_pdf.py path/to/file.pdf --render-pages all --min-image-area 10000 --dedupe-images --json

python3 scripts/analyze_pdf.py path/to/file.pdf --pages 1,3-5 --render-pages all --json

python3 scripts/analyze_pdf.py path/to/file.pdf --save-to ./pdf-monster-artifacts --json

rm -rf -- /tmp/pdf-monster-...

Use pdf-monster/SKILL.md. For PDF tasks, run:
python3 /absolute/path/to/pdf-monster/scripts/analyze_pdf.py <pdf> --json
Read the JSON from stdout. Use temporary image paths only while analyzing, then clean them up.
Do not create output folders in the user's working directory unless explicitly asked.

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in plugins/jbaehova/pdf-monster/skills/pdf-monster of hashgraph-online/awesome-codex-plugins.

• SKILL.md
• agents/openai.yaml
• requirements.txt
• scripts/analyze_pdf.py

Open the folder on GitHubat commit 9e7b281