A tool for examining a local image or screenshot with a vision model. It can describe what is visible or read text from the image.

Use it to inspect user-interface screenshots, terminal output, error dialogs, web pages, layouts, visual bugs, or visible text.

It helps when the important evidence is in a screenshot rather than in source files or terminal output. It keeps image observations separate from guesses about what cannot be seen.

vision — Skill for Claude Code by tmchao7/local-vision-mcp

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 tmchao7/local-vision-mcp --skill vision

Clone the repo

git clone --depth 1 https://github.com/tmchao7/local-vision-mcp

Made for: Claude Code.

Or install local-vision, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tmchao7/local-vision-mcp/vision/github.svg)](https://agentmods.dev/skills/tmchao7/local-vision-mcp/vision)

Your own site

<a href="https://agentmods.dev/skills/tmchao7/local-vision-mcp/vision"><img src="https://agentmods.dev/badge/skills/tmchao7/local-vision-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tmchao7/local-vision-mcp/vision"><img src="https://agentmods.dev/badge/skills/tmchao7/local-vision-mcp/vision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 252 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00252
Opus 5.5	$0.00014	$0.00101
Sonnet 5.5	$0.00007	$0.00050
Haiku 4.5	$0.00003	$0.00025

Measured 2mo ago against content hash 0ea780bdfcca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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.

skills/vision/SKILL.md · 20 lines

What it actually says

Local Vision

Use the mcp__local-vision__vision_analyze tool when the user provides a local image path or asks about a screenshot available as a local file.

Invocation

Pass the exact local path in path.
Use mode: "ui" for screenshots, terminal output, web pages, layouts, and visual bugs.
Use mode: "ocr" when exact visible text is the main goal.
Use mode: "general" for other image content.
Put the user's focused question in question when one exists.
Start with detail: "standard"; use fast only for a quick first pass.

The tool reads only the explicitly named image and returns a text report. Treat observations as visual evidence, visible_text as an OCR-style transcription, and uncertainties as unresolved. Do not claim that DeepSeek directly saw the image. Do not invent a screenshot path, and ask the user for one when no local path is available.

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.

2mo ago First seen · 20 lines · 34 tokens per session scan A 0ea780bdfcca

Subscribe to this mod's changes

vision is a skill published in the GitHub repository tmchao7/local-vision-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 252 once invoked, about $0.0001 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.

Design and UX

vision next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
visiontmchao7/local-vision-mcp	Skill	2	3mo ago	MIT	A	34	Claude Code
webgl-holographic-foilnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	41	Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	53	Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	78	Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codex	Skill	34k	4d ago	MIT	A	52	Codex
glance-canonical-layoutsandroid/skills	Skill	10k	yesterday	Apache-2.0	A	56	Claude Code
accessibilitymicrosoft/hve-core	Skill	1.6k	yesterday	MIT	A	47	Claude Code