vlm-ocr

vlm-ocr is a command for Claude Code from scdenney/open-science-skills. It costs 0 tokens per session (171 once invoked), scanned A, original, no licence file.

A command for evaluating and running a visual-language-model OCR workflow. OCR is the process of extracting text from images or scanned documents.

In plain words
What is it for?
Use it to evaluate OCR models against human-transcribed samples, select a system, and run large-scale image text extraction.
Why use it?
It provides a defined process for comparing OCR systems and then building a production pipeline based on measured accuracy.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the oss plugin — 1 skill, 51 commands, 2 agents shipped together

Good fit Use it to evaluate OCR models against human-transcribed samples, select a system, and run large-scale image text extraction.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/scdenney/open-science-skills/vlm-ocr
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.

Clone the repo
git clone --depth 1 https://github.com/scdenney/open-science-skills

Made for: Claude Code.

Or install oss, the plugin that ships this one along with the rest of its 1 skill, 51 commands, 2 agents.

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 vlm-ocr

README.md
[![agentmods](https://agentmods.dev/badge/commands/scdenney/open-science-skills/vlm-ocr.svg)](https://agentmods.dev/commands/scdenney/open-science-skills/vlm-ocr)
Your own site
<a href="https://agentmods.dev/commands/scdenney/open-science-skills/vlm-ocr"><img src="https://agentmods.dev/badge/commands/scdenney/open-science-skills/vlm-ocr.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 171 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 unknown 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 $0.00000 $0.00171
Opus 5 $0.00000 $0.00086
Sonnet 5 $0.00000 $0.00034
Haiku 4.5 $0.00000 $0.00017

Measured 4d ago against content hash 0b86cbf8b3f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vlm-ocr 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.

plugin/commands/vlm-ocr.md · 8 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 4d ago First seen · 8 lines · 0 tokens per session scan A 0b86cbf8b3f5

Subscribe to this mod's changes

vlm-ocr is a command published in the GitHub repository scdenney/open-science-skills (54 stars, last pushed 2d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 171 tokens. 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 commands, from other repositories

council-extract

Extract a completed Perplexity Model Council response from the current browser tab, converting it to structured markdown with model attribution, and save to disk.

intellegix/intellegix-code-agent-toolkit · 0 tokens

notebooklm

Google NotebookLM programmatic access — create notebooks, manage sources (URLs, PDFs, YouTube, Drive), generate audio/video/slides/quizzes, and chat with documents. Use when building a research notebook, generating a podcast from docs, or querying a source collection. Triggers on notebooklm, podcast from docs…

ArieGoldkin/claude-forge · 72 tokens

pdf-to-markdown-docling

Convert a local PDF to markdown via Docling's standard pipeline (layout + table-structure recognition — higher fidelity than MarkItDown on complex tables/layouts, 10x slower). Requires the opt-in Docling install.

tboome33/obsidian-mcp-router · 45 tokens

pdf-to-markdown

Convert a local PDF to markdown via the bundled MarkItDown Python CLI (fast, lightweight — plain text extraction, no table-structure recognition). For complex tables/layouts prefer /obsidian-router:pdf-to-markdown-docling.

tboome33/obsidian-mcp-router · 47 tokens

pdf

Captures the current page in tandem's Chrome as a PDF (if headless Chrome) or full-page PNG screenshot (in normal tandem mode). Saves to /.claude/tandem/output/.

bgmacris/quimera-ai · 39 tokens

telegram-to-notebook

A command that imports a Telegram chat export into NotebookLM, Google's tool for asking questions about uploaded sources. It can organize forum chats by discussion topic and keep text, code, PDFs, and documents while filtering media such as stickers and GIFs.

CreatmanCEO/notebooklm-claude-workflows · 0 tokens