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 Cleveland-RD/claude-image-gen --skill image-gengit clone --depth 1 https://github.com/Cleveland-RD/claude-image-genWrote 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/cleveland-rd/claude-image-gen/image-gen)<a href="https://agentmods.dev/skills/cleveland-rd/claude-image-gen/image-gen"><img src="https://agentmods.dev/badge/skills/cleveland-rd/claude-image-gen/image-gen/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/cleveland-rd/claude-image-gen/image-gen"><img src="https://agentmods.dev/badge/skills/cleveland-rd/claude-image-gen/image-gen.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 | $0.00101 | $0.04069 |
| Opus 5 | $0.00051 | $0.02034 |
| Sonnet 5 | $0.00020 | $0.00814 |
| Haiku 4.5 | $0.00010 | $0.00407 |
Grade A, and why
image-gen 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 11d 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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Generation
This skill drives the image-gen MCP server, which calls either OpenAI's
gpt-image-2 or Google's gemini-3-pro-image-preview and writes the
result to disk. The server returns the file path and a small inline
preview — Claude does NOT need to decode or save anything itself.
Picking a model
If you got here via a slash command (/image-gpt or /image-gemini),
the model is already chosen — skip this section and use it.
If the user invoked the skill plainly (e.g. "generate an image of …"), ask them which model to use before generating. Offer three options:
- GPT — OpenAI
gpt-image-2. Editorial / brand photography, literal text rendering, natural-prose adherence. - Gemini — Google Nano Banana family (defaults to
gemini-flash). Multi-image composition, character / object consistency, fast iteration. If the user wants top quality and is OK with occasional 503 retries, usegemini-proinstead. - Both — generate with both
gptandgemini-flashin parallel and present the two results side-by-side. Useful for comparing styles or picking the better output. Make the twogenerate_imagecalls in a single message so they run in parallel; polling rounds for each can also be issued back-to-back.
If the user already named a model in their request ("…with Gemini Pro", "using gpt-image"), respect that. If they say "both" / "compare" / "side-by-side," go straight to both without asking.
When to use
- "Generate / create / make / draw / render an image of …"
- "Design a hero image / banner / business card / mockup / poster …"
- "Use this logo in a marketing banner"
- "Edit this image — change the background / remove the watermark / add a hat"
- "Iterate on the last image — same but darker / wider / in portrait"
When NOT to use
- Diagrams, flowcharts, system architecture → produce SVG via the
frontend-designskill, or a Mermaid block. Sharper, smaller, editable. - Data charts / graphs from a spreadsheet → use the
xlsxskill or write a chart widget. - Region-specific in-place edits requiring a mask → not exposed here. Tell the user this isn't supported and suggest Photopea / Adobe Express.
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.
- 11d ago First seen · 368 lines · 101 tokens per session scan A 65c2d3ff9e2d
image-gen is a skill published in the GitHub repository Cleveland-RD/claude-image-gen (1 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 4,069 once invoked, about $0.0005 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
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
video-content
Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a…
visual-content
Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals…
avfoundation-media-pipeline-workflow
Guide AVFoundation media-pipeline implementation and repair, including AVCaptureSession, capture queues, AVPlayer, AVAsset async loading, AVAssetReader, AVAssetWriter, export, transcode, sample-buffer append back-pressure, and capture or playback ownership boundaries. Use when fixing or modernizing Apple media…
coremedia-timing-samplebuffer-workflow
Guide Core Media timing and sample-buffer implementation and repair, including CMTime, CMTimeRange, CMClock, CMTimebase, CMFormatDescription, CMSampleBuffer, attachments, readiness, presentation and decode timestamps, dropped buffers, AVSampleBufferDisplayLayer, AVSampleBufferRenderSynchronizer, and synchronization…
photos-library-editing-workflow
Guide privacy-preserving PhotosUI media selection and PhotoKit authorization, limited-library access, assets, collections, fetches, change observation, image/video requests, caching, iCloud delivery, asset resources, creation transactions, albums, content editing, adjustment data, nondestructive edits, cancellation…