A tool for reading PDF files and turning their contents into text, tables, or other structured data. It covers both normal digital PDFs and scanned pages.

Use it to summarize papers, contracts, reports, or statements; extract tables; search document text; and read scanned PDFs using OCR, which turns page images into text.

It removes the need to read long documents manually or handle each PDF format differently. It also helps preserve page-level context when extracting information.

pdf-handler — Skill for Claude Code and Codex by bjorn-ingmanson: A tool for reading PDF files and turning their…

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/bjorn-ingmanson/thefroject-plugins/pdf-handler

Any agent

npx skills add bjorn-ingmanson/thefroject-plugins --skill pdf-handler

Clone the repo

git clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-plugins

Made for: Claude Code, Codex.

Or install thefroject-customer-success, the plugin that ships this one along with the rest of its 47 skills, 11 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/pdf-handler.svg)](https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/pdf-handler)

Your own site

<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/pdf-handler"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/pdf-handler.svg" alt="Measured on agentmods" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 674 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.

Model	Per session	Once invoked
Fable 5	$0.00047	$0.00674
Opus 5	$0.00023	$0.00337
Sonnet 5	$0.00009	$0.00135
Haiku 4.5	$0.00005	$0.00067

Measured 4d ago against content hash 7da028928ac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pdf-handler 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 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.

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.

customer-success/skills/pdf-handler/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Handler

Read PDF files and surface their content as usable text, tables, or structured data. PDFs are common in finance (statements, audits), operations (contracts, vendor docs), people (offer letters, policies), and research (papers, reports).

Pick the right approach

PDFs vary widely in quality. Pick by source type:

Text-native PDFs (exports from Word, LaTeX, web): pdfplumber or PyPDF2 for text, pdfplumber for tables.
Scanned PDFs (images of paper): OCR via pytesseract after page-to-image with pdf2image.
Forms / structured PDFs: pdfplumber extracts cell positions; for AcroForm fields use pypdf.

If no library is available, install pdfplumber (pip install pdfplumber) before proceeding. Tell the user.

Reading

Print a structure overview first:

Pages: 24 | Estimated text: 12,400 words | Tables detected: 3 | Has images: yes

Extract text page by page rather than all at once for long documents — it makes citing page numbers possible later.

Tables

Tables in PDFs are tricky. Use pdfplumber.extract_tables() and verify by printing the first 3 rows of each detected table. If the table looks broken (mis-aligned columns, fragmented cells), tell the user before trying to act on it. Don't pretend a broken table is clean.

Summarizing

For a long PDF the user wants summarized:

Extract the full text.
Skim section headings and produce a short outline.
Ask the user what level of detail they want (executive summary, section-by-section, or topic-focused).
Cite page numbers in your summary so they can verify.

Output format

For data extraction: save structured output to outputs/<stem>.json or outputs/<stem>.csv.

For summaries: save to outputs/<stem>-summary.md with a "Source" heading at the top citing the PDF path and page count.

For text dumps: save to outputs/<stem>.md so the user can grep it later.

Common mistakes

Treating a scanned PDF as text-native (you'll get garbage). Detect and route to OCR.
Losing page numbers when concatenating text — keep them.
Confidently summarizing a PDF when the OCR is unreliable. Flag uncertain extractions.
Hallucinating content when the PDF is image-only and OCR failed. Say "I couldn't read this reliably" instead.

Read the full file on GitHub · 65 lines

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.

4d ago First seen · 65 lines · 47 tokens per session scan A 7da028928ac3

Subscribe to this mod's changes

pdf-handler is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 674 once invoked, about $0.0002 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 2026-08-31.

Documents PDF

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

pdf-handler

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

PDF Handler

Pick the right approach

Reading

Tables

Summarizing

Output format

Common mistakes

What this file has done since we first saw it

Other skills, from other repositories

foundry-hosted-agent-validation

skill-doc-delivery

pdf-extract-create-workflow

document-direct-python

pdf-text-extraction-fallback-85d5ca

pdf-verification-cli