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 X-School-Academy/skill-pilot --skill local-openai-visiongit clone --depth 1 https://github.com/X-School-Academy/skill-pilotWrote 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/x-school-academy/skill-pilot/local-openai-vision)<a href="https://agentmods.dev/skills/x-school-academy/skill-pilot/local-openai-vision"><img src="https://agentmods.dev/badge/skills/x-school-academy/skill-pilot/local-openai-vision/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.
<a href="https://agentmods.dev/skills/x-school-academy/skill-pilot/local-openai-vision"><img src="https://agentmods.dev/badge/skills/x-school-academy/skill-pilot/local-openai-vision.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.00634 |
| Opus 5.5 | $0.00017 | $0.00254 |
| Sonnet 5.5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
local-openai-vision 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 16d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Builder - Local OpenAI Vision
Use this skill when an image should be analyzed through the local OpenAI-compatible vision endpoint instead of a remote hosted model.
When to Use This Skill
- Describe a local image in natural language
- Read visible text from screenshots, photos, or scanned documents
- Answer targeted questions about image contents
- Perform OCR-style extraction from UI screenshots, posters, receipts, slides, or forms
Your Roles in This Skill
- Project Manager: Confirm the image task and choose the most direct prompt style for the requested output
- AI Engineer: Route the request through the local vision CLI and shape prompts for description or OCR accuracy
- Technical Writer: Return the extracted text or description in a clear format that matches the user's request
Role Communication
As an expert in your assigned roles, you must announce your actions before performing them using the following format:
As a {Role, and Role-XYZ if have more roles}, I will {action description}
This communication pattern ensures transparency and allows for human-in-the-loop oversight at key decision points.
Instructions
Follow these steps in order:
Step 1: Confirm the local image input
- Prefer a local file path provided by the user
- If the user gave a relative path, resolve it from the repo root before running the command
- If the file does not exist, stop and report the missing path clearly
Step 2: Choose the right prompt mode
- For a general description request, ask for a concise or detailed scene description
- For OCR or image-to-text, ask to transcribe all visible text and preserve line breaks when useful
- For targeted questions, include the specific question directly in the prompt
- If the user wants strict extraction, instruct the model to avoid adding commentary beyond the visible text
Step 3: Run the local vision command
- Use
core/bin/local-openai-infer --type image - Pass the prompt with
--prompt - Pass the image path with
--file_path - If model or endpoint specifics matter, refer to
references/local-openai-infer.md
What ships with it
1 file 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.
- 16d ago First seen · 71 lines · 42 tokens per session scan A ac2b21f16746
local-openai-vision is a skill published in the GitHub repository X-School-Academy/skill-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 634 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
markitdown
Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
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.
azure-ai-document-intelligence-ts
Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building custom document models.
azure-ai
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
ingest
Turn external web URLs into LLM-ready content — load + cache web pages (HQCC compression) and search the web. Use whenever the user gives a URL, asks you to read a webpage, or wants top-K pages on a topic. Executes via the cloud load and cloud search CLIs. For local document parsing (PDF text + OCR), use the liteparse…
markitdown
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.