smolvlm

smolvlm is a skill for Claude Code, Codex from tdimino/claude-code-minoan. It costs 20 tokens per session (594 once invoked), scanned A, original, MIT.

A local vision-language model that examines images and answers questions about them. It can describe pictures, read visible text, and identify interface elements without sending the image to a remote service.

In plain words
What is it for?
Use it for image descriptions, OCR (extracting text from images), screenshot and UI analysis, and detailed visual questions.
Why use it?
It helps inspect images privately and avoids manually reading screenshots or documents. Running locally can also make image analysis available without a network connection.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it for image descriptions, OCR (extracting text from images), screenshot and UI analysis, and detailed visual questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tdimino/claude-code-minoan/smolvlm
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 tdimino/claude-code-minoan --skill smolvlm
Clone the repo
git clone --depth 1 https://github.com/tdimino/claude-code-minoan

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 smolvlm

README.md
[![agentmods](https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/smolvlm/github.svg)](https://agentmods.dev/skills/tdimino/claude-code-minoan/smolvlm)
Your own site
<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/smolvlm"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/smolvlm/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 smolvlm

Your own site · 80×15
<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/smolvlm"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/smolvlm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 594 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 $0.00020 $0.00594
Opus 5 $0.00010 $0.00297
Sonnet 5 $0.00004 $0.00119
Haiku 4.5 $0.00002 $0.00059

Measured 8d ago against content hash 09dd49125018, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

smolvlm 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/view_image.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/design-media/smolvlm/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SmolVLM - Local Image Analysis

Analyze images locally using SmolVLM-2B, a state-of-the-art compact vision-language model optimized for Apple Silicon via mlx-vlm.

Quick Usage

Describe an Image

python ~/.claude/skills/smolvlm/scripts/view_image.py /path/to/image.png

Ask a Question About an Image

python ~/.claude/skills/smolvlm/scripts/view_image.py /path/to/image.png "What text is visible?"

Specific Tasks

# Extract text (OCR)
python ~/.claude/skills/smolvlm/scripts/view_image.py screenshot.png "Extract all text"

# UI analysis
python ~/.claude/skills/smolvlm/scripts/view_image.py ui.png "Describe the UI elements"

# Detailed description
python ~/.claude/skills/smolvlm/scripts/view_image.py photo.jpg --detailed

Effective Prompts

General Description

  • "Describe this image" - Basic description
  • "Describe this image in detail, including colors, composition, and any text" - Comprehensive

Text Extraction (OCR)

  • "Extract all visible text from this image"
  • "What text appears in this screenshot?"
  • "Read the text in this document"

UI/Screenshot Analysis

  • "Describe the user interface elements"
  • "What buttons and controls are visible?"
  • "Identify the application and its current state"

Visual Question Answering

  • "How many [objects] are in this image?"
  • "What color is the [object]?"
  • "Is there a [object] in this image?"

Code/Technical

  • "What programming language is shown?"
  • "Describe what this code does"
  • "Identify any errors in this code screenshot"

Model Details

Spec Value
Model SmolVLM-2B-Instruct
Size ~4GB
Peak Memory 5.8GB
Speed ~94 tok/s (M-series)
Supported Formats PNG, JPG, JPEG, GIF, WebP

Requirements

  • macOS with Apple Silicon (M1/M2/M3)
  • Python 3.10+
  • mlx-vlm package: uv pip install mlx-vlm --system

Troubleshooting

"Model not found": First run downloads the model (~4GB). Wait for completion.

Read the full file on GitHub · 84 lines

Files

What ships with it

2 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.

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. 8d ago First seen · 84 lines · 20 tokens per session scan A 09dd49125018

Subscribe to this mod's changes

smolvlm is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 594 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 2026-09-03.

Related

Other skills, from other repositories

add-ai-webapi

Integrates Power Pages generative-AI summarization APIs (PREVIEW) into a Single Page Application (SPA) site — the Search Summary API and the Data Summarization API — on any record-detail or list page. Generates per-target service code (CSRF-handled) and AI site settings; delegates Web API settings, table permissions…

microsoft/power-platform-skills · 226 tokens

ml-engineer

Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps.

RightNow-AI/openfang · 24 tokens

admet_genetic

ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.

PKU-YuanGroup/OpenAI4S · 63 tokens

prompt-lab

LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites. Triggers on: "prompt engineering", "generate prompt variants", "A/B test prompts", "optimize prompt", "improve this prompt". NOT for SKILL.md files, use skill-evaluator.

Mathews-Tom/armory · 74 tokens

801-regulations-eu-ai-act

Use when reviewing, designing, or modifying Java enterprise systems that use AI, LLMs, AI agents, RAG, tool calling, workflow automation, or model-based decision support and need EU AI Act regulatory awareness. This should trigger for requests such as Review a Java AI system for EU AI Act controls; Design governance…

jabrena/plinth · 108 tokens

032-architecture-adr-non-functional-requirements

Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable…

jabrena/plinth · 120 tokens