A decision guide for choosing between OCR, which reads text from an image, and visual description, which explains what a scene or object shows. It also covers cases where both kinds of understanding are needed.

Use it for screenshots, scanned documents, receipts, tables, schedules, photos of scenes, and images that contain both important text and visual context. For PDFs, it directs processing to the document-reading tool.

It prevents using a visual description when exact transcription is needed, or OCR when the important information is the scene itself. This makes image-processing requests more accurate.

ocr — Skill for Claude Code and Codex by radif-ru: A decision guide for choosing between OCR, which reads…

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/radif-ru/ai-multi-agent-system/ocr

Any agent

npx skills add radif-ru/ai-multi-agent-system --skill ocr

Clone the repo

git clone --depth 1 https://github.com/radif-ru/ai-multi-agent-system

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/radif-ru/ai-multi-agent-system/ocr.svg)](https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/ocr)

Your own site

<a href="https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/ocr"><img src="https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/ocr.svg" alt="Measured on agentmods" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 547 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 5.1	$0.00044	$0.00547
Opus 5	$0.00022	$0.00273
Sonnet 5	$0.00009	$0.00109
Haiku 4.5	$0.00004	$0.00055

Measured 5d ago against content hash d5f3ee7b3f32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 5d 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.

app/skills/ocr/SKILL.md · 47 lines

What it actually says

Skill: ocr

Определяет, когда использовать OCR для точной транскрипции текста, а когда Vision для описания сцены.

Когда использовать только `ocr_image`

Скриншот переписки/диалога — нужно точно прочитать текст.
Скан документа/чека/квитанции — задача прочитать цифры и текст.
Таблица или расписания — точная транскрипция содержимого.
Любое изображение, где основная задача — получить точный текст.

Когда использовать только `describe_image`

Фото сцены/объекта без текста (пейзаж, здание, человек, животное).
Фото с малозначительной подписью (небольшой текст на фоне).
Запрос на описание визуального содержания («что на фото?», «опиши объект»).
Ситуации, где важен визуальный контекст, а не точный текст.

Когда использовать `describe_image` + `ocr_image`

Фото со смешанным содержимым (сцена с важными надписями/табличками).
Когда нужно и описание сцены, и точная транскрипция текста.
Фото с неизвестным содержанием — сначала описать через Vision, затем при необходимости применить OCR к областям с текстом.

Для PDF документов

Для PDF документов используй tool read_document — он сам решит, нужен ли OCR на основе количества текста в PDF. Не вызывай ocr_image напрямую для страниц PDF.

Порядок действий

Если пользователь явно просит «прочитать текст» или «распознать» — используй ocr_image.
Если пользователь просит «описать» или «что на фото» — используй describe_image.
Если фото содержит и сцену, и текст — используй оба инструмента последовательно.
Для PDF всегда используй read_document.

Заметки

ocr_image работает только с изображениями в директории tmp/.
OCR требует установленного tesseract-ocr (опциональная зависимость).
Если OCR не установлен или не сработал — ocr_image вернёт сообщение об ошибке.
Кеш OCR сохраняется в <file>.ocr.txt для ускорения повторных вызовов.

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.

5d ago First seen · 47 lines · 44 tokens per session scan A d5f3ee7b3f32

Subscribe to this mod's changes

ocr is a skill published in the GitHub repository radif-ru/ai-multi-agent-system (6 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 547 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.

Creative and media Documents LLM Multi-Agent aiogram local-llm ollama

docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…

MRWillisT/PullNexus · 168 tokens

xlsx

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…

MRWillisT/PullNexus · 201 tokens

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…

MRWillisT/PullNexus · 92 tokens

pptx

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…

MRWillisT/PullNexus · 152 tokens

officecli-commonly-templates

Use this skill when producing a polished, Commonly-branded deliverable (.docx brief / memo, .xlsx data matrix, .pptx deck) and you do not have specific brand guidance from the user. Trigger on: 'write me a brief', 'one-pager', 'memo', 'data sheet', 'status matrix', 'short deck', 'summary deck', 'closing slide', 'final…

Team-Commonly/commonly · 182 tokens

markdown-converter

Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's markitdown Python tool. Use when a user attaches a binary file and you need to read its contents.

Team-Commonly/commonly · 57 tokens