pdf-verification

pdf-verification is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 19 tokens per session (948 once invoked), scanned A, original, MIT.

A check for PDF files after they have been generated, using PyPDF2, a Python library that reads PDF structure. It verifies the page count and whether the file can be opened.

In plain words
What is it for?
Use it to check generated PDFs for readable structure, nonzero pages, and an expected page count.
Why use it?
It catches empty, corrupted, or incorrectly sized PDFs before they are delivered.

Skill for Claude CodeCodex

About the project

OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.

HKUDS/OpenSpace · 7,501 stars · on GitHub

Install

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.

agentmods
npx agentmods add skills/hkuds/openspace/pdf-verification
Any agent
npx skills add HKUDS/OpenSpace --skill pdf-verification
Clone the repo
git clone --depth 1 https://github.com/HKUDS/OpenSpace

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pdf-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/pdf-verification.svg)](https://agentmods.dev/skills/hkuds/openspace/pdf-verification)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/pdf-verification"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 948 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00948
Opus 5 $0.00010 $0.00474
Sonnet 5 $0.00004 $0.00190
Haiku 4.5 $0.00002 $0.00095

Measured yesterday against content hash f225538ad289, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pdf-verification 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 yesterday.

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.

benchmarks/gdpval/skills/pdf-verification/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Verification Skill

Purpose

After generating PDF files, always verify page counts and file integrity programmatically before declaring task completion. This catches formatting issues, empty pages, and corrupted files early.

When to Use

  • After any PDF generation task
  • When specific page counts are required
  • Before marking a PDF-related task as complete

Verification Steps

1. Install PyPDF2 (if needed)

pip install PyPDF2

2. Verify Page Count and Integrity

Use run_shell to execute a Python verification script:

python -c "
from PyPDF2 import PdfReader
import sys

def verify_pdf(filepath, expected_pages=None):
    try:
        reader = PdfReader(filepath)
        actual_pages = len(reader.pages)
        print(f'✓ {filepath}: {actual_pages} pages')
        
        if expected_pages and actual_pages != expected_pages:
            print(f'✗ Page count mismatch: expected {expected_pages}, got {actual_pages}')
            return False
        
        # Check file is not empty/corrupted
        if actual_pages == 0:
            print(f'✗ Empty PDF: {filepath}')
            return False
        
        return True
    except Exception as e:
        print(f'✗ Error reading {filepath}: {e}')
        return False

# Verify each PDF
results = []
results.append(verify_pdf('output.pdf', expected_pages=2))
print(f'All checks passed: {all(results)}')
sys.exit(0 if all(results) else 1)
"

3. Verify Multiple PDFs

For tasks with multiple PDFs, verify each one:

python -c "
from PyPDF2 import PdfReader

pdfs = {
    'listings.pdf': 2,
    'map.pdf': 1,
    'summary.pdf': 1
}

all_passed = True
for filepath, expected in pdfs.items():
    try:
        reader = PdfReader(filepath)
        actual = len(reader.pages)
        status = '✓' if actual == expected else '✗'
        print(f'{status} {filepath}: {actual}/{expected} pages')
        if actual != expected:
            all_passed = False
    except Exception as e:
        print(f'✗ {filepath}: {e}')
        all_passed = False

print(f'Verification: {\"PASSED\" if all_passed else \"FAILED\"}')
"

Read the full file on GitHub · 157 lines

Files

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.

Changes

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.

  1. yesterday First seen · 157 lines · 19 tokens per session scan A f225538ad289

Subscribe to this mod's changes

pdf-verification is a skill published in the GitHub repository HKUDS/OpenSpace (7,501 stars, last pushed 23d ago), licensed MIT. It adds 19 tokens to every session and 948 once invoked, about $0.0001 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 2026-09-03.

Related

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.

microsoft/agent-framework · 82 tokens

skill-doc-delivery

Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.

nyldn/claude-octopus · 29 tokens

parse-document

Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.

superlinked/sie · 64 tokens

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…

vellum-ai/vellum-assistant · 90 tokens

paper-reader

Use when user asks to "read paper", "analyze paper", "summarize paper", "读论文", "分析文献", "帮我看一下这篇paper", "论文笔记", or provides a PDF file that appears to be an academic paper. Specialized for CV/DL papers. Also supports Zotero integration: "读一下这篇论文 ...", "快速看一下这篇论文 ...", "批判性分析这篇论文 ...", "读一下 Zotero 里的 XXX", "批量读一下 Zotero…

huangkiki/dailypaper-skills · 157 tokens

pdf-processor

Process PDF files including text extraction, rotation, and merging. USE FOR: "extract PDF text", "rotate PDF", "merge PDFs", "split PDF pages", "convert PDF to text". DO NOT USE FOR: creating PDFs from scratch (use document-creator), editing PDF forms (use form-filler).

microsoft/waza · 67 tokens