A command-line tool for generating images with Grok Imagine, an image-generation service.

Use it to generate one or more images from prompts, set aspect ratios or resolution, and save images to files or directories.

It provides a repeatable terminal-based way to create images, choose their shape and resolution, and save the results locally.

image — Command by Moore-developers

Install

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.

agentmods

npx agentmods add commands/moore-developers/grok-cli/image

Clone the repo

git clone --depth 1 https://github.com/Moore-developers/grok-cli

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 746 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00746
Opus 5	$0.00000	$0.00373
Sonnet 5	$0.00000	$0.00149
Haiku 4.5	$0.00000	$0.00075

Measured 2d ago against content hash ac5e53673f49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

docs/commands/image.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

`grok-cli image`

Purpose

Generate images with Grok Imagine.

Common Usage

grok-cli image "A cinematic skyline at sunrise"

Set aspect ratio and resolution:

grok-cli image "A cinematic skyline" --aspect-ratio 16:9 --resolution 1k

Save a base64 image to a local file:

grok-cli image "A logo mark" --output-file ./out/logo.png

Generate multiple images:

grok-cli image "A cinematic skyline" --count 4 --response-format url --json

Save multiple base64 images to a directory:

grok-cli image "A logo mark" --count 4 --output-dir ./out/logos

Script or skill usage:

grok-cli image --json --prompt "A cinematic skyline"

Parameters

PROMPT: positional image prompt.
--prompt <PROMPT>: explicit script-friendly prompt.
--json: use the standard JSON envelope.
--auth-file <PATH>: override the OAuth state file path.
--model <MODEL>: override the model for this image request only.
--aspect-ratio <RATIO>: output ratio, such as 16:9 or 1:1.
--resolution <VALUE>: output resolution, such as 1k.
--count <N>: number of images to generate, range 1..=10, default 1; maps to xAI field n.
--response-format <url|b64_json>: explicitly choose URL or base64 output.
--output-file <PATH>: require base64 output and save one local file.
--output-dir <PATH>: require base64 output and save multiple files as image-001.png, image-002.png, and so on.
--timeout <SECONDS>: request timeout, default 120.

Behavior

Default model is grok-imagine-image.
grok-cli model does not manage the image default model; pass --model directly when needed.
Access token expiry is checked before the request. If needed, the command refreshes first.
Default request uses n=1 and does not explicitly send response_format.
--count outside 1..=10 returns invalid_args.
If --output-file is omitted, the command returns an image URL or data URL.
With --output-file, the decoded file is written locally and the output reports the local path.
--output-file only supports a single image. Use --output-dir for multiple images.
--output-file and --output-dir implicitly use response_format=b64_json.
If --response-format url is passed explicitly, it cannot be combined with --output-file or --output-dir.
Successful calls are written to the local usage SQLite database under image usage.

Read the full file on GitHub · 93 lines

Changes

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.

2d ago First seen · 93 lines · 0 tokens per session scan A ac5e53673f49

Subscribe to this mod's changes

image is a command published in the GitHub repository Moore-developers/grok-cli (52 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 746 tokens. 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 2026-08-30.

Writing and docs

image

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

`grok-cli image`

Purpose

Common Usage

Parameters

Behavior

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement