image-edit

A command-line image editor that changes one or more reference images according to a text instruction, using Grok Imagine.

In plain words
What is it for?
Use it to alter a local or online image, combine up to three reference images, apply style changes, and save the edited result.
Why use it?
It lets you make image changes from a prompt without editing every visual detail by hand.

Command

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-edit
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 625 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00625
Opus 5 $0.00000 $0.00313
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00063

Measured 2d ago against content hash b7e351cc34e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

image-edit 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-edit.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grok-cli image-edit

Purpose

Edit one or more reference images with Grok Imagine.

This command is separate from image so that pure generation and reference-image editing do not share one entrypoint.

Common Usage

Edit one image:

grok-cli image-edit --image ./source.png --prompt "Make it cinematic"

Use a remote image URL:

grok-cli image-edit --image https://example.com/source.png --prompt "Change the background to sunset"

Edit multiple images, up to 3:

grok-cli image-edit \
  --image ./a.png \
  --image ./b.png \
  --image ./c.png \
  --prompt "Blend these references into one editorial image"

Save a base64 edit result:

grok-cli image-edit --image ./source.png --prompt "Make it cinematic" --output-file ./out/edited.png

Parameters

  • PROMPT: positional edit prompt.
  • --prompt <PROMPT>: explicit script-friendly prompt.
  • --image <PATH_OR_URL>: reference image input, repeatable up to 3 times; supports local paths, http(s) URLs, or data URIs.
  • --json: use the standard JSON envelope.
  • --auth-file <PATH>: override the OAuth state file path.
  • --model <MODEL>: override the model for this image edit request only.
  • --aspect-ratio <RATIO>: output ratio, such as 16:9 or 1:1.
  • --resolution <VALUE>: output resolution, such as 1k.
  • --response-format <url|b64_json>: explicitly choose URL or base64 output.
  • --output-file <PATH>: require base64 output and save one local file.
  • --timeout <SECONDS>: request timeout, default 120.

Behavior

  • Default model is grok-imagine-image.
  • One image sends official field image; multiple images send official field images.
  • Local images are encoded as data:image/<ext>;base64,... before being sent as image URLs.
  • More than 3 images returns invalid_args.
  • --output-file implicitly uses response_format=b64_json.
  • If --response-format url is passed explicitly, it cannot be combined with --output-file.
  • Successful calls are written to the local usage SQLite database under image usage.

Read the full file on GitHub · 84 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.

  1. 2d ago First seen · 84 lines · 0 tokens per session scan A b7e351cc34e4

Subscribe to this mod's changes

image-edit is a command published in the GitHub repository Moore-developers/grok-cli (52 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 625 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.