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 tmchao7/local-vision-mcp --skill visiongit clone --depth 1 https://github.com/tmchao7/local-vision-mcpWrote 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/tmchao7/local-vision-mcp/vision)<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.
<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>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 | $0.00017 | $0.00126 |
| Sonnet 5 | $0.00007 | $0.00050 |
| Haiku 4.5 | $0.00003 | $0.00025 |
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 9d 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.
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
questionwhen one exists. - Start with
detail: "standard"; usefastonly 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.
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.
- 9d ago First seen · 20 lines · 34 tokens per session scan A 0ea780bdfcca
vision is a skill published in the GitHub repository tmchao7/local-vision-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 252 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.