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 LeviReisJs/mcp-openi-server --skill medical-imagegit clone --depth 1 https://github.com/LeviReisJs/mcp-openi-serverWrote 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/levireisjs/mcp-openi-server/medical-image)<a href="https://agentmods.dev/skills/levireisjs/mcp-openi-server/medical-image"><img src="https://agentmods.dev/badge/skills/levireisjs/mcp-openi-server/medical-image/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/levireisjs/mcp-openi-server/medical-image"><img src="https://agentmods.dev/badge/skills/levireisjs/mcp-openi-server/medical-image.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 | $0.00127 | $0.00819 |
| Opus 5 | $0.00063 | $0.00409 |
| Sonnet 5 | $0.00025 | $0.00164 |
| Haiku 4.5 | $0.00013 | $0.00082 |
Grade A, and why
medical-image 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find & embed a medical image (Open-i)
You have the search_openi_images MCP tool available (from the openi plugin). Use it to fetch a real, citable biomedical image and hand it back in a form the user can paste or embed immediately.
Steps
-
Translate the topic to English. Open-i is English-only. Translate any Portuguese term before searching:
- "cárie" →
dental caries· "incisão oral" →oral incision· "radiografia panorâmica" →panoramic radiograph· "gengivite" →gingivitis· "anatomia do periodonto" →periodontal anatomy· "odontolegista" →forensic dentistry.
- "cárie" →
-
Pick the right image-type filter (
it) based on what the user wants:- Diagram / chart / illustration →
it="g" - Clinical or gross photo →
it="ph" - X-ray →
it="x"· CT →it="c"· MRI →it="m"· ultrasound →it="u"· histology/microscopy →it="mc" - If unsure, omit
itand let Open-i return everything, then choose the most relevant result yourself. - For dentistry topics you may add
sp="d".
- Diagram / chart / illustration →
-
Call
search_openi_imageswith a small window first (m=1, n=6). Read thetitleandsummaryof each result and choose the one that genuinely matches the topic — don't just grab the first hit. Prefer results whose caption clearly depicts the concept. -
Return it as Markdown, always with attribution:
 *<caption / summary>* — [Fonte](<article_url>)If the user asked for several, return 2–3 options and say which you'd pick and why.
-
If no good match: broaden the query (drop adjectives, use the core anatomical/clinical term), remove the
it/spfilters, and try once more before telling the user nothing fit.
When working inside a notes vault (e.g. Obsidian)
If the user is building study notes and asks you to place the image in the note (not just show it):
- Insert the Markdown image at the most relevant point in the note — typically right under the heading of the section it illustrates, or inside the relevant callout — not dumped at the top or bottom.
- Keep the caption +
[Fonte](...)link so the note stays citable. - If the vault is used offline (synced to a phone/tablet) and the user wants images to work without internet, offer to download the image into the vault's assets folder and embed it locally instead of hot-linking. Ask before downloading many files.
- One well-chosen figure per concept beats several — don't clutter the note.
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 · 45 lines · 127 tokens per session scan A 37f85336be7c
medical-image is a skill published in the GitHub repository LeviReisJs/mcp-openi-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 819 once invoked, about $0.0006 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
prior-art-search
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.
sanity-best-practices
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this…
portable-text-serialization
Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown…
development-assistant
Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.
mpep-search
Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.