pdf-extract-embedded-images

pdf-extract-embedded-images is a skill for Claude Code from danielrosehill/Claude-Image-Production-Plugin. It costs 52 tokens per session (857 once invoked), scanned B, original, MIT.

A utility for recovering JPEG and PNG files embedded inside a PDF at their original embedded resolution. It extracts the image objects rather than rendering each PDF page into a new image.

In plain words
What is it for?
Use it to recover photos or other image assets from PDFs, especially when the PDF mainly contains embedded pictures.
Why use it?
It preserves the source images more directly and avoids the quality loss and extra work caused by page rasterization.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the image-production plugin — 29 skills, 19 commands shipped together

Good fit Use it to recover photos or other image assets from PDFs, especially when the PDF mainly contains embedded pictures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielrosehill/claude-image-production-plugin/pdf-extract-embedded-images
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.

Any agent
npx skills add danielrosehill/Claude-Image-Production-Plugin --skill pdf-extract-embedded-images
Clone the repo
git clone --depth 1 https://github.com/danielrosehill/Claude-Image-Production-Plugin

Made for: Claude Code.

Or install image-production, the plugin that ships this one along with the rest of its 29 skills, 19 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.

agentmods badge for pdf-extract-embedded-images

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/pdf-extract-embedded-images/github.svg)](https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/pdf-extract-embedded-images)
Your own site
<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/pdf-extract-embedded-images"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/pdf-extract-embedded-images/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.

agentmods 80×15 button for pdf-extract-embedded-images

Your own site · 80×15
<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/pdf-extract-embedded-images"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/pdf-extract-embedded-images.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 857 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00052 $0.00857
Opus 5 $0.00026 $0.00428
Sonnet 5 $0.00010 $0.00171
Haiku 4.5 $0.00005 $0.00086

Measured 11d ago against content hash 8ed7c14fd6c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

pdf-extract-embedded-images scanned grade B 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 11d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

command -v pdfimages || echo "pdfimages not installed — install with: sudo apt install poppler-utils"
skills/pdf-extract-embedded-images/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract Embedded Images from PDF

Pull out JPEG and PNG objects embedded in a PDF using pdfimages. Extracts at native resolution without rasterizing the page. Different from pdf-to-images — this recovers the original embedded image files, not a rasterized page render.

When to use

  • A PDF is a container for photos (e.g., a photo book or brochure) — you want the original images, not a rasterized version.
  • Bulk-extracting image assets from a multi-page document without re-encoding.
  • Recovering embedded images at their full embedded resolution and quality.

Inputs to gather

  • Input PDF file — path to the PDF. Required.
  • Output directory — optional. Default: current directory.

Procedure

1. Check tooling

command -v pdfimages || echo "pdfimages not installed — install with: sudo apt install poppler-utils"

Abort if missing.

2. Validate PDF and inspect contents

file "<input.pdf>"
pdfimages -list "<input.pdf>"

The -list flag shows a summary of embedded images: page number, index, width, height, bits per component, color space, encoding. This helps set expectations (e.g., "3 JPEG images at 2400×3000px").

3. Extract

pdfimages -all "<input.pdf>" "<output-prefix>"

The -all flag extracts both the raw image stream (if JPEG, as .jpg; if PNG, as .png, etc.) plus any alternate-format versions.

Alternatives:

  • -j — extract JPEG objects only (faster if there are many PNG/PNG variants).
  • -png — convert all images to PNG (may re-encode non-JPEG content; slower but lossy compression converted to lossless).

Recommend -all unless the user specifies otherwise.

4. Report

After extraction:

  • Count of images extracted, by type (JPEG, PNG, etc.).
  • Output filenames and their dimensions.
  • File sizes and whether any extraction failed.
  • Remind the user that embedded images may have compression applied by the PDF creator — they are not necessarily at absolute maximum quality, but they are at their native resolution.

Read the full file on GitHub · 78 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.

  1. 11d ago First seen · 78 lines · 52 tokens per session scan B 8ed7c14fd6c7

Subscribe to this mod's changes

pdf-extract-embedded-images is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (17 stars, last pushed 24d ago), licensed MIT. It adds 52 tokens to every session and 857 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories