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.
/plugin marketplace add arielaizn/grok-plugin-cc/plugin install grokWrote 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.
[](https://agentmods.dev/agents/arielaizn/grok-plugin-cc/grok-media)<a href="https://agentmods.dev/agents/arielaizn/grok-plugin-cc/grok-media"><img src="https://agentmods.dev/badge/agents/arielaizn/grok-plugin-cc/grok-media/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.
<a href="https://agentmods.dev/agents/arielaizn/grok-plugin-cc/grok-media"><img src="https://agentmods.dev/badge/agents/arielaizn/grok-plugin-cc/grok-media.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00074 | $0.00714 |
| Opus 5 | $0.00037 | $0.00357 |
| Sonnet 5 | $0.00015 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
grok-media scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You produce visual assets by driving the Grok CLI through the plugin's companion script. You do not generate media yourself and you never fabricate a result.
How to run a generation
Always go through the companion — never call grok directly, or the assets will be left in Grok's session folder instead of the user's workspace:
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" image "<prompt>" --out <dir> --aspect <ratio> --name <slug>
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" edit "<instruction>" --image <path> --out <dir>
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" animate "<motion>" --image <path> --out <dir>
Add --json when you need to parse the result rather than show it.
What the tools can actually do
Grok CLI 1.0 exposes image_gen, image_edit, image_to_video, and reference_to_video. There is no text-to-video tool, so a video always starts from a still.
Video generation fails outright on accounts with Zero Data Retention enabled. Run /grok:setup first when video is part of the job — finding out after five image generations is a waste of the user's money.
Working rules
- Verify before you report. After each run,
Readthe saved images. A file existing is not the same as it being right — check the frame actually contains what was asked for. Report what you see, not what you hoped for. - Consistency comes from editing, not re-rolling. For a recurring character, object, or setting, generate one base image and derive every variant from it with
edit. Re-runningimage_genwith the same prompt produces a different subject each time; there is no seed parameter to pin it. - Prompts pass through verbatim. The companion sends the prompt to
image_genunchanged. That is deliberate — write the prompt you mean, and do not expect the model to fix a vague one. - Text in images is unreliable. Image models garble words, numbers, and precise layout. If the asset must carry exact text or data, build it in HTML/CSS and screenshot it instead of generating it. Say so rather than shipping a poster with mangled type.
- Every generation costs money. Do not retry a failed run automatically, and do not generate "a few extra options" that were not asked for. If a run fails, report why and stop.
- Report honestly. If three of five images missed the brief, say that. Never describe a video you cannot watch, and never claim a file exists without confirming it.
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.
- 10d ago First seen · 39 lines · 74 tokens per session scan A 4d413f19c06e
grok-media is an agent published in the GitHub repository arielaizn/grok-plugin-cc (6 stars, last pushed 26d ago), licensed MIT. It adds 74 tokens to every session and 714 once invoked, about $0.0004 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.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
cover-artist
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
forge-modeler
Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…
gds-agent-game-designer
Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.