Overview
imagine-agy is an agent skill and command-line tool that adds image generation to Claude Code by driving Google's Antigravity CLI (agy) headlessly. Claude Code cannot generate images out of the box; this package gives it that ability by routing image generation through Antigravity's first-class generate_image tool. It is distributed as an npm package and can be used either as a Claude Code skill or as a standalone text-to-image CLI.
Installation runs npx imagine-agy, which copies the skill to ~/.claude/skills/imagine-agy/ and adds a Bash(agy:*) allow-rule to ~/.claude/settings.json. The CLI can be used without Claude Code, for example npx imagine-agy "a red fox" -o fox.jpg. Options include --out, --ratio (1:1, 16:9, 9:16, 4:3, 3:4), --model, and --timeout. The package states that generation typically takes 30–60 seconds per image.
The tool addresses three undocumented failure modes of headless agy image generation: Claude Code's Bash classifier blocking agy, agy auto-denying its own tools in print mode, and agy ignoring the shell's working directory. Output is always JPEG (baseline, 300 DPI) regardless of the file name, so transparency is not available. The skill adds batching of asset sets, backgrounding long runs, on-disk verification, and one-axis iteration.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use imagine-agy to generate hero and banner art for landing pages.
- Teams use it to produce blog and social images, illustrations, textures, concept art, storyboards, and placeholder assets.
- Teams use it to create vertical phone wallpapers at a 9:16 ratio.
- Teams use it to batch a whole asset set in one run so a hero, an icon, and a background come out visually coherent.
- Teams use it to generate images straight from the terminal without Claude Code.
- Teams use it to verify generated images on disk rather than trusting the run summary.
Features
Generates images from text prompts
Works as a Claude Code skill
Provides a text-to-image CLI
Uses Google's Antigravity CLI
Creates hero art and icons
Generates illustrations from the terminal
Reviews
No reviews yet. Be the first to share your experience!
FAQ
Can Claude Code generate images?
Not on its own — Claude Code is a coding agent with no image model. This package gives it the ability by routing image generation through the Antigravity CLI, which does have one.
Does this need an API key?
No. It uses the existing Antigravity CLI sign-in, with no separate key to manage and nothing to configure.
Does it work outside Claude Code?
Yes. Running the CLI with a prompt and an output path is a standalone operation; the skill is optional.
Does it work with Cursor, Windsurf, or other AI editors?
The CLI works anywhere Node runs. The skill is in Claude Code's format, but any agent that can run shell commands can call the CLI directly.
How much does it cost?
It costs whatever the Antigravity plan charges for a generate_image call; the package adds nothing on top and has zero dependencies.
Can I generate transparent PNGs / logos with alpha?
No — output is JPEG, which has no alpha channel; the site points to its conversion options.
Can it put text in the image?
It can try, but the site advises against it because image models render words unreliably. Generate the art with space left for text and compose the type on top.
Can it edit an existing image or do img2img?
Not currently — the tool covers text-to-image only.
How many images can I generate at once?
The CLI does one per call. The skill batches a whole set in a single agy run, which also keeps them stylistically coherent.
Is this made by Google or Anthropic?
Neither. It is an independent open-source wrapper around the Antigravity CLI.