grok-imagine

grok-imagine is a skill for Claude Code from LovelaceLoom/grok-plugin-cc. It costs 64 tokens per session (516 once invoked), scanned A, original, Apache-2.0.

A skill for generating an image from a written description with xAI's Grok image-generation service. It saves the resulting image and reports where the file is located.

In plain words
What is it for?
Creating pictures, illustrations, logos, mockups, and other visual assets from text prompts.
Why use it?
It provides a direct command for creating a visual file when a text description is easier to supply than image-editing software. The saved path makes the generated result available for later use.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the grok plugin — 8 skills, 21 commands, 2 agents, 3 hooks shipped together

Good fit Creating pictures, illustrations, logos, mockups, and other visual assets from text prompts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add LovelaceLoom/grok-plugin-cc
Claude Code
/plugin install grok

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 8 skills, 21 commands, 2 agents, 3 hooks.

Wrote 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.

agentmods badge for grok-imagine

README.md
[![agentmods](https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-imagine/github.svg)](https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-imagine)
Your own site
<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-imagine"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-imagine/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.

agentmods 80×15 button for grok-imagine

Your own site · 80×15
<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-imagine"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-imagine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 516 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00064 $0.00516
Opus 5 $0.00032 $0.00258
Sonnet 5 $0.00013 $0.00103
Haiku 4.5 $0.00006 $0.00052

Measured 11d ago against content hash b262b520641b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grok-imagine 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.

plugins/grok/skills/grok-imagine/SKILL.md · 42 lines

What it actually says

Grok — Imagine (Image Generation)

Use this skill when the user wants Grok to generate an image. The companion wraps Grok's /imagine builtin, sanitizes the output, and prints the saved image path.

When to use

  • The user asks "generate an image of…", "draw…", "create a picture of…", "make a logo for…", "mockup…".
  • The user wants a visual deliverable rather than text.

Do not use this skill for:

  • Video generation → there is a separate imagine-video companion subcommand (currently slash-command only; surface to the user).
  • Image analysis (describing an existing image) — Grok-ask with the image attached is a separate flow.

How to invoke

Run exactly one bash command:

node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" imagine "<the user's image description, properly quoted>"

Common flags

  • --save-to <path> — copy the generated image to a path. If <path> ends with / or is an existing directory, the source basename is appended. Defaults to a session-internal path under ~/.grok/sessions/.
  • --model <name> — override the default imagine model.
  • --timeout <duration> — default 5 minutes. 0 to disable.
  • --json — emit machine-readable JSON instead of human-readable output.

Output rules

  • Return the companion's stdout verbatim. It includes:
    • Image: /absolute/path/to/file.jpg — the saved image path.
    • An open "<path>" line (macOS). Linux users can substitute xdg-open.
    • A Session: <id> resumption handle when present.
  • If Grok returns a content-policy refusal (no markdown image link in the response), surface the raw text so the user sees Grok's reason — do not retry silently with a softened prompt.
  • If $ARGUMENTS is empty, clarify with the user what image they want before invoking.
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. 11d ago First seen · 42 lines · 64 tokens per session scan A b262b520641b

Subscribe to this mod's changes

grok-imagine is a skill published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 516 once invoked, about $0.0003 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.

Related

Other skills, from other repositories