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.
npx skills add stdevMac/grok-in-codex --skill grok-brand-mediagit clone --depth 1 https://github.com/stdevMac/grok-in-codexWrote 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/skills/stdevmac/grok-in-codex/grok-brand-media)<a href="https://agentmods.dev/skills/stdevmac/grok-in-codex/grok-brand-media"><img src="https://agentmods.dev/badge/skills/stdevmac/grok-in-codex/grok-brand-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/skills/stdevmac/grok-in-codex/grok-brand-media"><img src="https://agentmods.dev/badge/skills/stdevmac/grok-in-codex/grok-brand-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 | $0.00026 | $0.00550 |
| Opus 5 | $0.00013 | $0.00275 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
grok-brand-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- grok-brand-media — 100% identical, 2 lines differ
What it actually says
Grok brand & media recipes
Use with grok_image and grok_video (or companion image / video commands).
Output conventions
- Images →
.grok-media/image/ - Videos →
.grok-media/video/ - Grok’s tools usually write under
~/.grok/sessions/…/images|videos/. The companion copies finished assets into.grok-media/so the project path contract holds without needing shell/write_file(those stay denylisted). - Video resolution is limited by Grok’s model tier (often 480p); that is not a plugin bug.
Image recipes
README / GitHub social banner (16:9)
grok_image aspect=16:9 prompt="Dark developer-tool banner for Grok in Codex. Minimal typography, abstract node graph, high contrast, no cluttered UI chrome, space for title text on the left."
OG / link preview (1.91:1-ish → use 16:9)
grok_image aspect=16:9 prompt="Open Graph image for a SaaS launch. Bold product name area, subtle grid background, one hero metaphor only."
App icon concept (1:1)
grok_image aspect=1:1 prompt="App icon concept, simple geometric mark, readable at 32px, flat with slight depth, no text."
Edit existing asset
grok_image edit=./assets/logo.png prompt="Make it monochrome, tighter padding, production-ready PNG"
Video recipes
Animate a still
grok_video image=./.grok-media/image/hero.png duration=6 prompt="gentle camera push-in, soft parallax, premium product feel"
Multi-reference cutdown
grok_video refs=["shot1.png","shot2.png"] aspect=16:9 duration=6 prompt="product launch cutdown, clean transitions, no on-screen UI clutter"
Prompt quality tips
- One primary subject
- Name the aspect ratio and destination (banner, icon, social)
- Say what to avoid (busy UI, tiny illegible text, watermark clutter)
- Prefer background for video: set
background: true - After background jobs finish,
grok_resultlists project-local paths under.grok-media/
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 · 59 lines · 26 tokens per session scan A 213fb62be441
grok-brand-media is a skill published in the GitHub repository stdevMac/grok-in-codex (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 550 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ima2
Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.
local-image-gen
A local command-line tool for generating or editing images with Codex, Grok, or Gemini/Antigravity accounts and optional API keys.
grokodex-imagine
An image-generation tool that creates pictures from written descriptions through a local Grok service.
grok-membership-media
Use the local paid ChatGPT and Grok memberships to create website first frames and real MP4 video without developer APIs or API keys.
article-illustrations
Generate hand-drawn 16:9 article illustrations with the Grav character IP, sparse annotations, and absurd but clear visual metaphors.
gpt-image
Use this skill whenever a user asks to generate, create, draw, render, or edit images with GPT Image 2 / gpt-image-2, text-to-image, reference-image editing, inpainting, posters, typography, Chinese text, UI mockups, diagrams, or gallery prompts. Analyze the user's prompt, search the bundled Reference Gallery/craft…