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 Vallykrie/gemini-swarm-skill --skill gemini-imagegengit clone --depth 1 https://github.com/Vallykrie/gemini-swarm-skillWrote 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/vallykrie/gemini-swarm-skill/gemini-imagegen)<a href="https://agentmods.dev/skills/vallykrie/gemini-swarm-skill/gemini-imagegen"><img src="https://agentmods.dev/badge/skills/vallykrie/gemini-swarm-skill/gemini-imagegen/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/vallykrie/gemini-swarm-skill/gemini-imagegen"><img src="https://agentmods.dev/badge/skills/vallykrie/gemini-swarm-skill/gemini-imagegen.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 | $0.00107 | $0.01030 |
| Opus 5 | $0.00053 | $0.00515 |
| Sonnet 5 | $0.00021 | $0.00206 |
| Haiku 4.5 | $0.00011 | $0.00103 |
Grade A, and why
gemini-imagegen 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gemini-imagegen
Claude cannot generate raster images. Gemini sessions launched through the
agy (Antigravity CLI) have a generate_image tool that can — this skill
dispatches an agy job that generates the image and saves it to a file you
specify.
Verified against agy 1.0.15 (model Gemini 3.1 Pro (High), tool name
generate_image). Re-check agy --help if flags seem wrong.
Step 0 — Preflight
command -v agy— if missing, stop and tell the user to install the Antigravity CLI (https://antigravity.google).- Decide the absolute output path(s) for the image(s). agy
--printsessions do not run in your invocation cwd, so relative paths land in the wrong place — always pass absolute paths in the prompt and--add-dirthe destination directory.
Step 1 — Write the image prompt
Be specific — the quality of the image tracks the prompt. Include:
- Subject — what the image shows.
- Style — photo, flat illustration, 3D render, watercolor, pixel art, logo mark, etc.
- Composition — framing, background, negative space.
- Colors / mood — palette, lighting.
- Intended use — favicon, hero banner, OG card — so the model picks a sensible aspect ratio and level of detail.
For editing an existing image (restyle, variation, background removal),
give the absolute path of the source image in the prompt, --add-dir its
directory too, and ask Gemini to load it before generating the edited version.
Step 2 — Dispatch
One image (verified command shape — adapt prompt and paths):
agy --print "Use your generate_image tool to create: <detailed image prompt>. Save the final image to /abs/path/out.png. When it is saved, print IMAGE_OK followed by the file path. If you cannot generate images, print IMAGE_UNSUPPORTED and stop." \
--model "Gemini 3.1 Pro (High)" \
--print-timeout 5m \
--add-dir /abs/path \
--dangerously-skip-permissions --sandbox
--dangerously-skip-permissions --sandboxlets the job write the file without an approval TTY (there is none in--printmode). If the user runs you in review mode and objects to auto-approval, ask before dispatching.- Multiple images: dispatch them in parallel, one agy job per image —
either background several of the above commands, or reuse the gemini-swarm
dispatcher (
scripts/dispatch.sh) with oneNN-slug.prompt.mdper image (MODEL: Gemini 3.1 Pro (High)header). Never generate sequentially.
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 · 81 lines · 107 tokens per session scan A cb9748456271
gemini-imagegen is a skill published in the GitHub repository Vallykrie/gemini-swarm-skill (6 stars, last pushed 23d ago), licensed MIT. It adds 107 tokens to every session and 1,030 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
nanobanana-adc
Generate images with Google's Nano Banana Pro (Gemini 3 Pro Image) using Application Default Credentials (ADC) or a GEMINIAPIKEY. Use this when the user asks to create, generate, draw, or render an image via Google / Vertex AI / Gemini.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
chatgpt-cli
Drives ChatGPT from the terminal via cli-web-chatgpt — ask questions, generate and download images, list and view conversations, browse models, and manage OpenAI SSO auth. Use when the user wants to ask ChatGPT something, generate images with ChatGPT, or browse their ChatGPT conversations from the command line. Prefer…
pexels-cli
Searches and downloads free stock photos and videos from Pexels via the cli-web-pexels command-line tool — keyword search with orientation/size/color filters, photo and video details, downloads, photographer profiles, and collections. Use when the user asks about Pexels, free or royalty-free stock photos and videos…
unsplash-cli
Searches and downloads free Unsplash photos via the cli-web-unsplash command-line tool — keyword search with orientation/color filters, photo details (EXIF, location, tags), downloads, random photos, topics, collections, and photographer profiles. Use when the user asks about Unsplash, free stock photos, or wants to…
youtube-cli
Searches YouTube and fetches video transcripts via the cli-web-youtube command-line tool — video search, video details (views, duration, description, keywords), trending by category, channel info, and timestamped transcripts/captions with language selection and translation. Use when the user asks about YouTube…