What is deepseek-ocr?

A tool for extracting text from images and PDF files using the DeepSeek-OCR model, a system designed to read text from visual documents. It supports several common image formats and saves extracted text files in the Downloads folder.

Use it to read text from PNG, JPG, WEBP, BMP, GIF, TIFF, or PDF files with DeepSeek on Apple Silicon.

It turns text inside scans, screenshots, and PDFs into text you can search or reuse. It is intended specifically for requests that mention DeepSeek.

deepseek-ocr — Skill for Claude Code and Codex by joonlab

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 joonlab/joonlab-claudecode-setting-for-share --skill deepseek-ocr

Clone the repo

git clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-share

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/deepseek-ocr/github.svg)](https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/deepseek-ocr)

Your own site

<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/deepseek-ocr"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/deepseek-ocr/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/deepseek-ocr"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/deepseek-ocr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,071 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 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.

Model	Per session	Once invoked
Fable 5.1	$0.00120	$0.02071
Opus 5	$0.00060	$0.01035
Sonnet 5	$0.00024	$0.00414
Haiku 4.5	$0.00012	$0.00207

Measured 9d ago against content hash 0bd908f6ba96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deepseek-ocr 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/ocr_images.py, scripts/run_ocr.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

process = subprocess.Popen(

claude/skills/deepseek-ocr/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepSeek OCR

Overview

Extract text from images and PDFs using the DeepSeek-OCR-8bit model optimized for Apple Silicon. Process single or multiple files at once, with results automatically saved to the Downloads folder as {filename}_OCR.txt.

Supported formats: PNG, JPG, WEBP, BMP, GIF, TIFF, PDF

When to Use This Skill

Use this skill ONLY when the user explicitly mentions DeepSeek in their request:

"딥식 OCR 해줘"
"Deepseek으로 이미지 읽어줘"
"DeepSeek OCR 돌려줘"
"딥시크로 텍스트 추출해줘"
"이 이미지 딥식으로 OCR"

DO NOT use this skill for general OCR requests like:

❌ "Extract text from this image"
❌ "Run OCR on these images"
❌ "Read the text from this PNG"
❌ "이미지 텍스트 추출해줘"

The user must specifically request DeepSeek/딥식 for this skill to activate.

Quick Start

Command Line Usage

Run the OCR processor directly from the terminal:

~/.claude/skills/deepseek-ocr/scripts/run_ocr.sh

The script will prompt for image paths. Paste one or more paths (separated by newlines or spaces), then press Enter twice to start processing.

Python Usage

Run the Python script directly:

python3 ~/.claude/skills/deepseek-ocr/scripts/ocr_images.py

How It Works

Input: User provides one or more image/PDF file paths
Validation: Checks that files exist and are valid formats
Processing:
- Images: Direct OCR on the image
- PDFs: Converts each page to image, then runs OCR on all pages
Output:
- Images: One TXT file per image
- PDFs: One TXT file with all pages (marked as [Page 1], [Page 2], etc.)

Supported Formats

Images:

PNG, JPG/JPEG, WEBP, BMP, GIF, TIFF

Documents:

PDF (all pages processed automatically)

Usage Examples

Example 1: Single Image

User provides:

~/Desktop/document.png

Result:

File saved: ~/Downloads/document_OCR.txt

Example 2: Multiple Images (Newline Separated)

User provides:

~/Desktop/page1.png
~/Desktop/page2.png
~/Desktop/page3.png

Read the full file on GitHub · 302 lines

Files

What ships with it

2 files 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.

9d ago First seen · 302 lines · 120 tokens per session scan A 0bd908f6ba96

Subscribe to this mod's changes

deepseek-ocr is a skill published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 2,071 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Documents PDF

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

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

deepseek-ocr