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 agentmods add skills/espennilsen/pi/pdf-readernpx skills add espennilsen/pi --skill pdf-readergit clone --depth 1 https://github.com/espennilsen/piWhat 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 | $0.00090 | $0.01691 |
| Opus 5 | $0.00045 | $0.00846 |
| Sonnet 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 2d 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.
- 2d ago First seen · 223 lines · 90 tokens per session scan A cb0669ca2bc7
pdf-reader is a skill published in the GitHub repository espennilsen/pi (117 stars, last pushed 9d ago), licensed MIT. It adds 90 tokens to every session and 1,691 once invoked, about $0.0005 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.