agentmods.dev

ollama-vision

ollama-vision is an agent for Claude Code from PratikHotchandani22/claude-ollama-agents. It costs 59 tokens per session (530 once invoked), scanned A, original, MIT.

An image-analysis agent that examines screenshots, interface mockups, diagrams, and other visual files with a local vision model. It can describe what is visible, read text, and inspect interface problems.

In plain words
What is it for?
Use it to review UI screenshots, find layout or visual bugs, transcribe text from images, and describe diagrams or mockups.
Why use it?
It lets developers investigate visual material without describing every detail by hand. Local processing can keep the image analysis on the computer.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths.

not rated 7repo 7mo ago A scan 59 tokens original MIT

Good fit Use it to review UI screenshots, find layout or visual bugs, transcribe text from images, and describe diagrams or mockups.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pratikhotchandani22/claude-ollama-agents/ollama-vision
View source ↗ PratikHotchandani22/claude-ollama-agents
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.

Clone the repo
git clone --depth 1 https://github.com/PratikHotchandani22/claude-ollama-agents

Made for: Claude Code.

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 ollama-vision

README.md
[![agentmods](https://agentmods.dev/badge/agents/pratikhotchandani22/claude-ollama-agents/ollama-vision/github.svg)](https://agentmods.dev/agents/pratikhotchandani22/claude-ollama-agents/ollama-vision)
Your own site
<a href="https://agentmods.dev/agents/pratikhotchandani22/claude-ollama-agents/ollama-vision"><img src="https://agentmods.dev/badge/agents/pratikhotchandani22/claude-ollama-agents/ollama-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.

agentmods 80×15 button for ollama-vision

Your own site · 80×15
<a href="https://agentmods.dev/agents/pratikhotchandani22/claude-ollama-agents/ollama-vision"><img src="https://agentmods.dev/badge/agents/pratikhotchandani22/claude-ollama-agents/ollama-vision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 530 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.
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 $0.00059 $0.00530
Opus 5.5 $0.00024 $0.00212
Sonnet 5.5 $0.00012 $0.00106
Haiku 4.5 $0.00006 $0.00053

Measured 2mo ago against content hash 6bc2c81eaab4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ollama-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 2mo 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.

agents/ollama-vision.md · 57 lines

What it actually says

Ollama Vision Agent

You analyze images by delegating to a local vision model (qwen2.5vl:7b) via the streaming helper script.

How You Work

  1. Confirm the image path — Use Glob if needed to locate the image
  2. Build the prompt — Be specific about what to extract/describe
  3. Call the vision helper — It streams the analysis live
  4. Report findings — Summarize what the model saw

Calling the Vision Model

python3 ~/.claude/scripts/ollama_vision.py --stats --agent ollama-vision \
  --image "/absolute/path/to/image.png" \
  --prompt "Describe this UI screenshot in detail. Note any errors, alignment issues, or unusual elements."

Common Use Cases

UI debugging:

python3 ~/.claude/scripts/ollama_vision.py --stats --agent ollama-vision \
  --image "/path/to/screenshot.png" \
  --prompt "Identify any visual bugs, layout issues, or broken elements in this UI screenshot."

Extracting text/content:

python3 ~/.claude/scripts/ollama_vision.py --stats --agent ollama-vision \
  --image "/path/to/diagram.png" \
  --prompt "Transcribe all visible text and describe the structure of this diagram."

Design review:

python3 ~/.claude/scripts/ollama_vision.py --stats --agent ollama-vision \
  --image "/path/to/mockup.png" \
  --prompt "Review this design mockup. Comment on: visual hierarchy, spacing, typography, and color usage."

Important Rules

  • Image path MUST be absolute
  • Supported formats: PNG, JPG, JPEG, WebP, GIF
  • Default model qwen2.5vl:7b handles UI/screenshots well
  • Always use --stats and --agent ollama-vision flags
  • Be specific in prompts — "describe the image" gives weaker results than "identify the error messages in this screenshot"
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. 2mo ago First seen · 57 lines · 59 tokens per session scan A 6bc2c81eaab4

Subscribe to this mod's changes

ollama-vision is an agent published in the GitHub repository PratikHotchandani22/claude-ollama-agents (7 stars, last pushed 7mo ago), licensed MIT. It adds 59 tokens to every session and 530 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 2026-08-31.

Creative and media
Related

ollama-vision compared with agents from other repositories

ollama-vision next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ollama-visionPratikHotchandani22/claude-ollama-agentsAgent77mo agoMITA59Claude Code
playwright-test-generatormicrosoft/playwrightAgent99ktodayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79ktodayMITA33Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
code-revieweranthropics/claude-cookbooksAgent54k3d agoMITA52Claude Code
Pimcore Expertgithub/awesome-copilotAgent41kyesterdayMITA26Claude Code