gpt-multimodal

gpt-multimodal is a skill for Claude Code, Codex from benchflow-ai/skillsbench. It costs 18 tokens per session (4,425 once invoked), scanned A, original, Apache-2.0.

Guidance for using vision-capable GPT models to understand images and sequences of video frames. It covers visual description, reading text from images, and comparing images over time.

In plain words
What is it for?
Analyzing scenes, extracting text from screenshots, comparing images, and reviewing video frames with Python and an OpenAI client.
Why use it?
It gives developers a defined way to handle visual input instead of treating images like ordinary text. It also states supported file types, size guidance, and the expected setup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Analyzing scenes, extracting text from screenshots, comparing images, and reviewing video frames with Python and an OpenAI client.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/benchflow-ai/skillsbench/gpt-multimodal
About the project

SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.

benchflow-ai/skillsbench · 1,757 stars · on GitHub · skillsbench.ai

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.

Any agent
npx skills add benchflow-ai/skillsbench --skill gpt-multimodal
Clone the repo
git clone --depth 1 https://github.com/benchflow-ai/skillsbench

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.

agentmods badge for gpt-multimodal

README.md
[![agentmods](https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gpt-multimodal/github.svg)](https://agentmods.dev/skills/benchflow-ai/skillsbench/gpt-multimodal)
Your own site
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/gpt-multimodal"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gpt-multimodal/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.

agentmods 80×15 button for gpt-multimodal

Your own site · 80×15
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/gpt-multimodal"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gpt-multimodal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,425 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.04425
Opus 5 $0.00009 $0.02212
Sonnet 5 $0.00004 $0.00885
Haiku 4.5 $0.00002 $0.00443

Measured 10d ago against content hash faf77d38e4ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gpt-multimodal 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

tasks-extra/pedestrian-traffic-counting/environment/skills/gpt-multimodal/SKILL.md · 649 lines

How it starts

The opening of the file, as written. The whole thing — 649 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenAI Vision Analysis Skill

Purpose

This skill enables image analysis, scene understanding, text extraction, and multi-frame comparison using OpenAI's vision-capable GPT models (e.g., gpt-4o, gpt-5). It supports single and multiple images analysis and sequential frames for temporal analysis.

When to Use

  • Analyzing image content (objects, scenes, colors, spatial relationships)
  • Extracting and reading text from images (OCR via vision models)
  • Comparing multiple images to detect differences or changes
  • Processing video frames to understand temporal progression
  • Generating detailed image descriptions or captions
  • Answering questions about visual content

Required Libraries

The following Python libraries are required:

from openai import OpenAI
import base64
import json
import os
from pathlib import Path

Input Requirements

  • File formats: JPG, JPEG, PNG, WEBP, non-animated GIF
  • Image quality: Clear and legible; minimum 512×512px recommended
  • File size: Under 20MB per image recommended
  • Maximum per request: Up to 500 images, 50MB total payload
  • URL or Base64: Images can be provided as URLs or base64-encoded data

Output Schema

All analysis results should be returned as valid JSON conforming to this schema:

{
  "success": true,
  "model": "gpt-5",
  "analysis": "Detailed description or analysis of the image content...",
  "metadata": {
    "image_count": 1,
    "detail_level": "high",
    "tokens_used": 850,
    "processing_time_ms": 1234
  },
  "extracted_data": {
    "objects": ["car", "person", "building"],
    "text_found": "Sample text from image",
    "colors": ["blue", "white", "gray"],
    "scene_type": "urban street"
  },
  "warnings": []
}

Field Descriptions

  • success: Boolean indicating whether the API call succeeded
  • model: The GPT model used for analysis (e.g., "gpt-4o", "gpt-5")
  • analysis: Complete textual analysis or description from the model
  • metadata.image_count: Number of images analyzed in this request
  • metadata.detail_level: Detail parameter used ("low", "high", or "auto")
  • metadata.tokens_used: Approximate token count for the request
  • metadata.processing_time_ms: Time taken to process the request
  • extracted_data: Structured information extracted from the image(s)
  • warnings: Array of issues or limitations encountered

Read the full file on GitHub · 649 lines

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. 10d ago First seen · 649 lines · 18 tokens per session scan A faf77d38e4ed

Subscribe to this mod's changes

gpt-multimodal is a skill published in the GitHub repository benchflow-ai/skillsbench (1,757 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 4,425 once invoked, about $0.0001 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.