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 espennilsen/pi --skill pdf-readergit clone --depth 1 https://github.com/espennilsen/piWrote 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/espennilsen/pi/pdf-reader)<a href="https://agentmods.dev/skills/espennilsen/pi/pdf-reader"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/pdf-reader/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/espennilsen/pi/pdf-reader"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/pdf-reader.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 Memory Poisoning · line 222 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00090 | $0.01691 |
| Opus 5.5 | $0.00036 | $0.00676 |
| Sonnet 5.5 | $0.00018 | $0.00338 |
| Haiku 4.5 | $0.00009 | $0.00169 |
Grade A, and why
pdf-reader scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL "URL" -o /tmp/document.pdf How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Reader
Extract content from PDF files using pdftotext (Poppler) for text and
pdfplumber (Python) for tables and structured extraction.
Quick Reference
| Task | Tool | Command |
|---|---|---|
| Full text | pdftotext | pdftotext file.pdf - |
| Text with layout | pdftotext | pdftotext -layout file.pdf - |
| Specific pages | pdftotext | pdftotext -f 3 -l 5 file.pdf - |
| Tables | pdfplumber | python3 scripts/extract.py tables file.pdf |
| Metadata | pdfinfo | pdfinfo file.pdf |
| Page count | pdfinfo | pdfinfo file.pdf | grep Pages |
| Images | pdfimages | pdfimages -list file.pdf |
| Fonts | pdffonts | pdffonts file.pdf |
| OCR (scanned PDF) | tesseract | python3 scripts/extract.py ocr file.pdf |
| Smart text + OCR | extract.py | python3 scripts/extract.py text file.pdf |
| Quick survey | extract.py | python3 scripts/extract.py scan file.pdf |
Workflow
Step 1: Get the PDF
If the user provides a URL, download it first:
curl -sL "URL" -o /tmp/document.pdf
Verify it's a valid PDF:
file /tmp/document.pdf # should say "PDF document"
pdfinfo /tmp/document.pdf # metadata + page count
Step 2: Choose Extraction Method
Plain text (most cases):
pdftotext file.pdf -
This pipes output to stdout. For large PDFs, use page ranges:
pdftotext -f 1 -l 10 file.pdf - # pages 1-10
Layout-preserving text (columns, formatted docs):
pdftotext -layout file.pdf -
Use -layout when the PDF has multi-column layouts, tables rendered as text,
or precise spacing that matters.
Tables (structured data):
python3 scripts/extract.py tables file.pdf
Or inline with pdfplumber:
import pdfplumber
pdf = pdfplumber.open("file.pdf")
for i, page in enumerate(pdf.pages):
tables = page.extract_tables()
for table in tables:
print(f"\n--- Table on page {i+1} ---")
for row in table:
print(" | ".join(str(cell or "") for cell in row))
pdf.close()
What ships with it
1 file 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.
- 1mo ago First seen · 223 lines · 90 tokens per session scan A cb0669ca2bc7
pdf-reader is a skill published in the GitHub repository espennilsen/pi (122 stars, last pushed 9d ago), licensed MIT. It adds 90 tokens to every session and 1,691 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
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.
paper-reader
A reading assistant for computer-vision and deep-learning research papers. It can work with PDF files, arXiv papers, and papers stored in Zotero, a reference-management app.