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 agentmods add skills/junmo-kim/mac-local-vision/macvisnpx skills add junmo-kim/mac-local-vision --skill macvisgit clone --depth 1 https://github.com/junmo-kim/mac-local-visionWrote 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/junmo-kim/mac-local-vision/macvis)<a href="https://agentmods.dev/skills/junmo-kim/mac-local-vision/macvis"><img src="https://agentmods.dev/badge/skills/junmo-kim/mac-local-vision/macvis.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 | $0.00294 | $0.01529 |
| Opus 5 | $0.00147 | $0.00764 |
| Sonnet 5 | $0.00059 | $0.00306 |
| Haiku 4.5 | $0.00029 | $0.00153 |
Grade A, and why
macvis 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macvis
macvis reads and locates things in images, on-device. Put the binary on your PATH
(repo README → Install) and call it. Output is YAML by default; add --format json to parse.
Which command
| You need | Command |
|---|---|
| Read all text from an image / screenshot / PDF | macvis ocr <path> |
The click-point (x,y) of a specific word — E2E / UI targeting |
macvis find <path> --target "<text>" |
| Scan a QR code or barcode (any symbology) | macvis barcode <path> |
| Scan for a QR code only (skip other symbologies) | macvis qr <path> |
| Tag/classify what an image contains (labels, not free text) | macvis classify <path> |
| Generate a scannable QR code PNG | macvis make-qr "<text>" --out <path> |
| Find a document's four corners in a photo | macvis document-bounds <path> |
| Flatten/straighten a photographed document into a scan | macvis rectify-document <path> --out <path> |
| Extract a document's title/paragraphs/tables/lists with layout preserved | macvis document-ocr <path> |
| To interpret an image (describe, reason, summarize) — macOS 27 | macvis ask <path> --prompt "<question>" |
| To extract structured JSON fields from an image (schema-constrained) — macOS 27 | macvis ask <path> --prompt "<question>" --schema <path|inline-json> |
| Group photos by person | macvis sort-faces <dir> |
| Find photos matching a given face | macvis find-person --target <face.jpg> --dir <dir> |
| Check what runs on this machine | macvis doctor |
Rule of thumb: ocr to read everything, find to get one word's pixel to click/assert,
document-ocr when the layout (table cells, list items) matters rather than flat lines,
ask only when you need interpretation rather than raw text.
Examples
macvis ocr ./receipt.png # full text + per-line entries
macvis ocr ./receipt.png --words --format json # per-word pixel boxes, JSON
macvis find ./screen.png --target "Submit" # → x,y click center + bounding box
macvis find ./screen.png --target "결제하기" # non-Latin works (locale-aware)
macvis ocr ./doc.pdf --page 2 # PDF page (rasterized)
macvis barcode ./ticket.png # scan every QR/barcode symbology
macvis qr ./ticket.png # scan for a QR code only
macvis classify ./photo.jpg # tag against a 1,303-label taxonomy
macvis make-qr "https://example.com" --out ./qr.png # write a scannable QR PNG
macvis document-bounds ./receipt.jpg # find a document's 4 corners
macvis rectify-document ./receipt.jpg --out ./flat.png # flatten a photographed document
macvis document-ocr ./invoice.png # title/paragraphs/tables/lists, structured
macvis ask ./receipt.png --prompt "extract the fields" --schema ./receipt-schema.json # structured JSON answer
macvis sort-faces ./photos --output-dir ./by-person # cluster a folder of photos by person
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.
- 4d ago First seen · 89 lines · 294 tokens per session scan A 8784ebfce8e5
macvis is a skill published in the GitHub repository junmo-kim/mac-local-vision (58 stars, last pushed 13d ago), licensed MIT. It adds 294 tokens to every session and 1,529 once invoked, about $0.0015 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 2026-08-30.
Other skills, from other repositories
md2pdf
Convert a Markdown file to PDF with GitHub-style formatting using the md2pdf tool.
Use this skill when the user asks to inspect or summarize PDF documents.
scan-to-practice
A complete methodology for turning scanned or image-based learning materials into high-quality desktop, web, or mobile practice products. Covers visual transcription, data assembly, answer-key-driven controls and grading, product design, animation, validation, and long-term maintenance. Use when a user wants to…
PDF → spreadsheet — extract data into Excel (Local MCP)
Use when the user wants to pull data out of one or more PDFs (invoices, bank/credit-card statements, receipts, reports, tables) and put it into a spreadsheet. pdfread is one of the most-used tools; this codifies the read-PDF → structure → write-Excel workflow. Powered by Local MCP, on-device.
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.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…