pdf-ocr-to-markdown

pdf-ocr-to-markdown is a skill for Codex from jseook11/codex-pdf-ocr-to-markdown-skill. It costs 50 tokens per session (4,430 once invoked), scanned A, original, MIT.

A workflow that reads text from PDFs or images with optical character recognition (OCR) and produces separate Markdown files plus internal quality data. The original PDFs are preserved.

In plain words
What is it for?
Use it to extract document text, structure pages into Markdown, analyze visual layouts when inspected, and create JSON or quality-report artifacts.
Why use it?
It turns scanned or image-based documents into editable text while keeping the source files unchanged and marking pages that still need visual review.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to extract document text, structure pages into Markdown, analyze visual layouts when inspected, and create JSON or quality-report artifacts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jseook11/codex-pdf-ocr-to-markdown-skill/pdf-ocr-to-markdown
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 jseook11/codex-pdf-ocr-to-markdown-skill --skill pdf-ocr-to-markdown
Clone the repo
git clone --depth 1 https://github.com/jseook11/codex-pdf-ocr-to-markdown-skill

Made for: 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-ocr-to-markdown

README.md
[![agentmods](https://agentmods.dev/badge/skills/jseook11/codex-pdf-ocr-to-markdown-skill/pdf-ocr-to-markdown/github.svg)](https://agentmods.dev/skills/jseook11/codex-pdf-ocr-to-markdown-skill/pdf-ocr-to-markdown)
Your own site
<a href="https://agentmods.dev/skills/jseook11/codex-pdf-ocr-to-markdown-skill/pdf-ocr-to-markdown"><img src="https://agentmods.dev/badge/skills/jseook11/codex-pdf-ocr-to-markdown-skill/pdf-ocr-to-markdown/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-ocr-to-markdown

Your own site · 80×15
<a href="https://agentmods.dev/skills/jseook11/codex-pdf-ocr-to-markdown-skill/pdf-ocr-to-markdown"><img src="https://agentmods.dev/badge/skills/jseook11/codex-pdf-ocr-to-markdown-skill/pdf-ocr-to-markdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00050 $0.04430
Opus 5 $0.00025 $0.02215
Sonnet 5 $0.00010 $0.00886
Haiku 4.5 $0.00005 $0.00443

Measured 10d ago against content hash 426a2dd93eb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pdf-ocr-to-markdown 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 10d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/batch_ocr.py, scripts/classify_pages.py, scripts/cleanup_workdir.py, …), 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.

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.

pdf-ocr-to-markdown/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF OCR to Markdown

Use this skill when the user provides PDFs or images and wants Codex to handle OCR, routing, visual-structure analysis, and final Markdown deliverables with internal JSON/quality diagnostics.

This skill does not modify the source PDF, add an OCR layer to the PDF, or create a searchable replacement PDF. "OCR" here means reading visible or embedded page content and writing separate structured outputs such as final.md, final.json, page-level Markdown, page-level JSON, and quality reports.

The default user experience should be: user gives files, Codex runs the bundled pipeline from the user's working directory, Codex decides the route per page, Codex performs the visual pass when it can actually inspect rendered images, and Codex reports the Markdown sidecar path next to each source file. Internal JSON, quality reports, and run artifacts stay under .ocr_work/ so Finder-visible output is limited to the final Markdown sidecar unless the user asks otherwise.

Quick Start

If the user asks Codex to OCR/analyze files, do not make them choose pipeline steps. From the user's current working directory, run the bundled script by absolute path:

python3 /path/to/pdf-ocr-to-markdown/scripts/batch_ocr.py file1.pdf file2.pdf image1.png

Dependencies should be installed once during skill installation with scripts/setup_dependencies.py --install. For Korean/English documents, the default language hint is already kor+eng. Only add options when the user asks for custom output locations, DPI, dependency repair, or work retention. The default internal output root is .ocr_work/ocr_output; the user-facing Markdown sidecar is copied next to the source file.

Dry-run for skill verification:

python scripts/batch_ocr.py \
  --file-list examples/example_input.md \
  --out-dir /tmp/ocr_output_test \
  --work-dir /tmp/ocr_work_test \
  --dry-run

Use --keep-work or --no-cleanup internally when pages need a surrounding Codex visual pass, because rendered page images and generated prompt files live under the work directory.

Read the full file on GitHub · 373 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. 10d ago First seen · 373 lines · 50 tokens per session scan A 426a2dd93eb9

Subscribe to this mod's changes

pdf-ocr-to-markdown is a skill published in the GitHub repository jseook11/codex-pdf-ocr-to-markdown-skill (2 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 4,430 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

paddleocr-doc-parsing

A document-parsing tool configuration for extracting structured Markdown or JSON from complex PDFs and document images, including tables, formulas, charts, and multi-column pages.

PaddlePaddle/PaddleOCR · 140 tokens

paddleocr-text-recognition

An optical character recognition tool configuration for extracting text from images, photos, scans, screenshots, and scanned PDFs. OCR means converting text visible in an image into machine-readable text.

PaddlePaddle/PaddleOCR · 125 tokens

nsfc-budget

A tool that creates an editable LaTeX budget justification and renders it as a PDF for an NSFC research-funding application. NSFC is China’s National Natural Science Foundation, and a budget justification explains why proposed costs are needed.

huangwb8/ChineseResearchLaTeX · 138 tokens

nsfc-ref-alignment

A read-only checker for references in NSFC LaTeX proposals. It compares citations with the bibliography and flags missing entries, field errors, and possible mismatches between claims and papers.

huangwb8/ChineseResearchLaTeX · 90 tokens

larksnap-fetch

A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.

AmbroseX/larksnap · 111 tokens

xiaobei-skill-academic-paper-to-ppt

A workflow that turns academic papers, reports, and technical documents into presentation slides, optionally following a supplied PowerPoint template. It creates a written outline, full-slide images, and a PowerPoint file.

xiao24bei/xiaobei-skill · 101 tokens