Grok Image Cli

v0.2.1

Generate and edit images via Grok API from the command line. Cross-platform secure credential storage for xAI API key. Supports batch generation, aspect rati...

0· 1.4k·4 current·4 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for cyberash-dev/grok-image-cli.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Grok Image Cli" (cyberash-dev/grok-image-cli) from ClawHub.
Skill page: https://clawhub.ai/cyberash-dev/grok-image-cli
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required binaries: grok-img, node
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install grok-image-cli

ClawHub CLI

Package manager switcher

npx clawhub@latest install grok-image-cli
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description (grok-image-cli) align with requested binaries (grok-img, node) and the declared use of an xAI API key; these are reasonable for a CLI that wraps the xAI Grok Image API.
Instruction Scope
SKILL.md instructs the agent to use the grok-img CLI, manage credentials via the OS keychain, call api.x.ai over HTTPS, and optionally fetch remote images when editing — all within the stated image-generation/editing scope. There are no instructions to read unrelated system files or exfiltrate data to other endpoints.
Install Mechanism
No automated install spec is bundled with the skill (instruction-only), but the README provides standard install commands (npm install -g or git clone then npm build). These use known channels (npm, GitHub); user guidance to audit before installing is included. This is normal but the registry lacks an automated install spec.
Credentials
The CLI legitimately needs an xAI API key stored in the OS credential store and optionally accepts XAI_API_KEY as a fallback. There is a small metadata inconsistency: the registry summary showed 'no primary credential' while SKILL.md declares a cross-keychain credential and optional XAI_API_KEY — functionally this is proportional but the metadata mismatch should be corrected.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide configs. It stores only its own API key in the OS credential store (expected behavior for a CLI).
Assessment
This skill appears to do what it says: it's a CLI wrapper around xAI image APIs and requires Node and the grok-img binary plus an xAI API key stored in your OS credential store (or via XAI_API_KEY). Before installing: 1) verify the npm package and GitHub repo (check the provenance/commit referenced) and prefer auditing source if you have concerns; 2) confirm you trust the grok-img binary's origin (npm scope and publisher); 3) be aware that when you use the edit command with a remote image URL the CLI will fetch that URL over HTTPS; 4) note the minor metadata mismatch (registry claims no primary credential but SKILL.md uses a cross-keychain credential) — this is likely an editorial issue but you may want the publisher to correct it. If any of these checks fail, avoid installing or run installation in an isolated environment.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🎨 Clawdis
OSmacOS · Windows · Linux
Binsgrok-img, node
latestvk97bwm7z1ek7n5svbfv7ng9tt581hwar
1.4kdownloads
0stars
5versions
Updated 2mo ago
v0.2.1
MIT-0
macOS, Windows, Linux

grok-image-cli

A CLI for generating and editing images using the xAI Grok API. Supports multiple models: grok-imagine-image (default), grok-imagine-image-pro, grok-2-image-1212. Powered by the official @ai-sdk/xai SDK. Credentials are stored in the OS native credential store (macOS Keychain, Windows Credential Manager, Linux Secret Service) via cross-keychain.

Installation

Requires Node.js >= 20.19.0. Works on macOS, Windows, and Linux. The package is fully open source under the MIT license: https://github.com/cyberash-dev/grok-image-cli

npm install -g grok-image-cli

The npm package is published with provenance attestation, linking each release to its source commit via GitHub Actions. You can verify the published contents before installing:

npm pack grok-image-cli --dry-run

Install from source (if you prefer to audit the code before running):

git clone https://github.com/cyberash-dev/grok-image-cli.git
cd grok-image-cli
npm install && npm run build && npm link

After installation the grok-img command is available globally.

Quick Start

grok-img auth login                                                      # Interactive prompt: enter xAI API key
grok-img generate "A futuristic city skyline at night"                   # Generate with default model
grok-img generate "A futuristic city skyline at night" -m grok-imagine-image-pro  # Use pro model
grok-img edit "Make it a watercolor painting" -i ./photo.jpg             # Edit an existing image

API Key Management

Store API key (interactive prompt):

grok-img auth login

Show stored key (masked) and source:

grok-img auth status

Remove key from credential store:

grok-img auth logout

The CLI also supports the XAI_API_KEY environment variable as a fallback when no credential store entry is found.

Image Generation

grok-img generate "A collage of London landmarks in street-art style"
grok-img generate "Mountain landscape at sunrise" -n 4 -a 16:9
grok-img generate "A serene Japanese garden" -o ./my-images
grok-img generate "Photorealistic portrait" -m grok-imagine-image-pro
grok-img generate "Abstract art" -m grok-2-image-1212

Image Editing

Edit a local file or a remote URL:

grok-img edit "Change the landmarks to New York City" -i ./landmarks.jpg
grok-img edit "Render as a pencil sketch" -i https://example.com/portrait.jpg
grok-img edit "Add a vintage film grain effect" -i ./photo.jpg -a 3:2 -o ./edited

Flag Reference

generate

FlagDescriptionDefault
-m, --model <model>Model (grok-imagine-image, grok-imagine-image-pro, grok-2-image-1212)grok-imagine-image
-a, --aspect-ratio <ratio>Aspect ratio (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, 19.5:9, 9:19.5, 20:9, 9:20, auto)auto
-n, --count <number>Number of images to generate (1-10)1
-o, --output <dir>Output directory./grok-images

edit

FlagDescriptionDefault
-i, --image <path>Source image (local file path or URL)required
-m, --model <model>Model (grok-imagine-image, grok-imagine-image-pro, grok-2-image-1212)grok-imagine-image
-a, --aspect-ratio <ratio>Aspect ratioauto
-o, --output <dir>Output directory./grok-images

Security and Data Storage

The following properties are by design and can be verified in the source code:

  • xAI API key: stored in the OS native credential store via cross-keychain (macOS Keychain / Windows Credential Manager / Linux Secret Service; service: grok-image-cli, account: api-key). By design, never written to disk in plaintext. If no credential store entry is found, the CLI falls back to the XAI_API_KEY environment variable. See src/infrastructure/adapters/credential-store.adapter.ts for the implementation.
  • No config files: all settings are passed via CLI flags. Nothing is stored on disk besides the credential store entry.
  • Network: the API key is only sent to api.x.ai over HTTPS via the official @ai-sdk/xai SDK. When editing images with a remote URL (-i https://...), the SDK makes an additional outbound HTTPS request to fetch the source image. No other outbound connections are made by the CLI itself (npm/git fetches during installation are standard package manager behavior). See src/infrastructure/adapters/grok-api.adapter.ts.
  • Generated images: saved to the local output directory (default: ./grok-images). No images are cached or uploaded elsewhere.

API Reference

This CLI wraps the xAI Image Generation API via the Vercel AI SDK:

  • Generation: POST /v1/images/generations
  • Editing: POST /v1/images/edits

Documentation: https://docs.x.ai/docs/guides/image-generation

Comments

Loading comments...