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.
npx skills add timaliev/mcp_ocr --skill ocr-recipesgit clone --depth 1 https://github.com/timaliev/mcp_ocrWrote 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.
[](https://agentmods.dev/skills/timaliev/mcp_ocr/ocr-recipes)<a href="https://agentmods.dev/skills/timaliev/mcp_ocr/ocr-recipes"><img src="https://agentmods.dev/badge/skills/timaliev/mcp_ocr/ocr-recipes.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00095 | $0.00731 |
| Opus 5 | $0.00048 | $0.00365 |
| Sonnet 5 | $0.00019 | $0.00146 |
| Haiku 4.5 | $0.00010 | $0.00073 |
Grade A, and why
ocr-recipes 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OCR Recipes
Pluggable OCR workflows. Each recipe is a standalone subskill file in this directory. The agent reads the relevant file at runtime — no monolithic config.
Bundled with mcp_ocr. Install
mcp_ocr[all]and this skill auto-loads in Pi.
Phase 1: Backend Discovery
Check which OCR backends are available before running any recipe:
mcp_ocr_ocr_text_vision(path=<any_valid_image>)
mcp_ocr_ocr_text_paddle(path=<any_valid_image>)
| Backend | Best for |
|---|---|
| Vision | European/CJK, fast, zero-config |
| Paddle | Cross-platform, wide languages, needs lang param |
| PaddleOCR-VL | 109 languages, tables/formulas, slow |
Prefer Vision when available. Fall back to Paddle with explicit lang.
Phase 2: Dispatch
Match user request to subskill file:
| User says | Read subskill |
|---|---|
| "scan receipt", "receipt", "check photo" | receipt-scanner.md |
| "business card", "contact from image" | business-card.md |
| "text from screenshot", "read screen" | text-from-screenshot.md |
| "scan document", "digitize", "OCR document" | document-ocr.md |
| "read this", "what does it say", "OCR" | simple-ocr.md |
| "extract table", "table from image" | extract-table.md |
| "text layout", "where is text" | extract-layout.md |
| "scan barcode", "scan QR", "product code" | scan-code.md |
| "find online", "where to buy", "price" | scan-and-search.md |
| "compare OCR", "which backend" | compare-backends.md |
| "batch OCR", "OCR multiple files" | batch-ocr.md |
If no match: present the list and ask user to pick.
Image Preprocessing
Quick reference — read full guide in preprocessing.md:
| Problem | Fix |
|---|---|
| Low resolution | raster_resize to 2400-3200px |
| JPEG noise | raster_colorspace to "L" |
| Low contrast | raster_adjust contrast=2.0 |
| Skewed photo | raster_perspective |
| >4000px (Paddle limit) | raster_resize to 3000px |
What ships with it
12 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.
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.
- 6d ago First seen · 72 lines · 95 tokens per session scan A 57a119206bcc
ocr-recipes is a skill published in the GitHub repository timaliev/mcp_ocr (0 stars, last pushed 29d ago), licensed MIT. It adds 95 tokens to every session and 731 once invoked, about $0.0005 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.