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 mordor-forge/gemini-media-mcp --skill gemini-imagegit clone --depth 1 https://github.com/mordor-forge/gemini-media-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/mordor-forge/gemini-media-mcp/gemini-image)<a href="https://agentmods.dev/skills/mordor-forge/gemini-media-mcp/gemini-image"><img src="https://agentmods.dev/badge/skills/mordor-forge/gemini-media-mcp/gemini-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/mordor-forge/gemini-media-mcp/gemini-image"><img src="https://agentmods.dev/badge/skills/mordor-forge/gemini-media-mcp/gemini-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 | $0.00134 | $0.03247 |
| Opus 5.5 | $0.00054 | $0.01299 |
| Sonnet 5.5 | $0.00027 | $0.00649 |
| Haiku 4.5 | $0.00013 | $0.00325 |
Grade A, and why
gemini-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 3d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Image (Nano Banana)
Quick start
- Write the prompt as full sentences: subject, setting, composition, lighting, style and purpose. Put exact text to render in quotes.
- Call
gemini-media:generate_imagewithpromptand, if the destination implies one,aspectRatio. Keep the default model (nb2) and size (1K) for a first pass. - Review the result: inspect the preview returned with it (if your client renders images), or open the saved file if your environment can view images. If you cannot see images, say so instead of guessing what it looks like.
- Refine with
gemini-media:edit_image, passing the result'suriasimageand one specific change. - Report the file path(s), model and cost from the result.
Tools
The tools live on the gemini-media MCP server. Harnesses name MCP tools differently (mcp__gemini-media__generate_image, gemini-media.generate_image, or plain generate_image); match on the part after the server name. This skill writes them as gemini-media:<tool>.
| Tool | Use it to |
|---|---|
gemini-media:generate_image |
Create 1-4 images from text, optionally guided by up to 14 reference images |
gemini-media:edit_image |
Change an existing image (add/remove/replace, restyle, relight, fix text, change aspect ratio); saves a new file |
gemini-media:estimate_cost |
Price a request before running it (compare: true prices every image model) |
gemini-media:list_models |
Current models, aliases, prices; detail: true adds sizes and aspect ratios |
gemini-media:get_usage / gemini-media:get_config |
Spend so far and budget; backend, output directory and input-file policy |
Results carry files[] (each with path on the server's disk, a gemini-media:// uri, width and height), model, cost, optional text (the model's own commentary) and warnings (read them: they report dropped parameters and retired-model redirects). Inputs accept a file path, a gemini-media:// URI or bare file name of an earlier output, or a data: URI. Web URLs are not fetched: download the file first.
What ships with it
4 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.
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.
- 3d ago First seen · 153 lines · 134 tokens per session scan A f7f237706bb6
gemini-image is a skill published in the GitHub repository mordor-forge/gemini-media-mcp (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 134 tokens to every session and 3,247 once invoked, about $0.0005 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 2026-10-08.
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 $ultragoal 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.