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 anlostsheep/grokodex --skill grokodex-imaginegit clone --depth 1 https://github.com/anlostsheep/grokodexWrote 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/anlostsheep/grokodex/grokodex-imagine)<a href="https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-imagine"><img src="https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-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.
<a href="https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-imagine"><img src="https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-imagine.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 | $0.00058 | $0.01018 |
| Opus 5 | $0.00029 | $0.00509 |
| Sonnet 5 | $0.00012 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
grokodex-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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grokodex Imagine
Generate an image with a constrained headless Grok run (image-only; never full shell inherit).
When to use
- User asks to generate / draw / imagine an image, icon, mockup, or illustration via Grok
- Product UI concepts, logos, storyboard frames, etc.
- Not for general coding tasks →
grokodex-run - Not for X posts search →
grokodex-x-search
Tool preference
- Call MCP tool
grok_imagine(logical name; Claude may show anmcp__…prefix). - Do not use a terminal/shell tool to run
grokfor image generation. - Permission is fixed to restricted-class inside the bridge; do not pass inherit /
host_sandbox/codex_sandbox.
How to fill arguments
| Arg | Required | Default | How to set |
|---|---|---|---|
prompt |
yes | — | Detailed visual description: subject, style, colors, composition, text-in-image if any |
aspect_ratio |
no | auto |
e.g. 1:1, 16:9, 9:16, 4:3 when user cares about shape |
save_dir |
no | <cwd>/.grokodex/images |
Absolute or workspace-relative directory for outputs |
cwd |
no | host cwd | Working directory for the Grok process |
timeout_ms |
no | 120000 (bridge short path) | Raise only for slow generations |
model |
no | CLI default | Only if user asks for a specific Grok model |
Prompt tips
- Be concrete: medium, lighting, camera angle, brand constraints.
- Mention “no watermark / no UI chrome” when relevant.
- If the user wants a specific filename/location, put that path intent in
promptand setsave_dirto the parent directory. - Keep the task short: one image, clear subject. Do not chain coding context into imagine.
Interpret the result
Success (ok: true):
artifacts(primary for delivery)
Array of{ "type": "image", "path": "/abs/path/to/file.png" }.- Tell the user each path clearly so they can open the file.
- Prefer listing absolute paths from
artifacts.
text
Grok’s free-form reply; may include paths or a short description. Use as secondary narrative.meta
Often includessave_dir,aspect_ratio,duration_ms,cwd,max_turns,tools_allowlist. Mentionsave_dirif no artifacts were parsed.permission.notes
If notes say no image path was found, still checkmeta.save_dir/.grokodex/imagesand report what Grok wrote intext.
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.
- 11d ago First seen · 83 lines · 58 tokens per session scan A 3daccb68710a
grokodex-imagine is a skill published in the GitHub repository anlostsheep/grokodex (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,018 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.
Other skills, from other repositories
grok-brand-media
Prompt recipes for Grok image/video generation from Codex (OG images, README banners, launch clips).
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
spotify-player
Terminal Spotify playback/search via spogo (preferred) or spotifyplayer. Use when the user asks to play music, search for a song, skip a track, pause playback, check what is currently playing, control Spotify, list audio devices, or manage a Spotify queue from the terminal.
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
imagegen
Generate original images, artwork, product visuals, diagrams, or other raster assets with the desktop's configured image provider. Use whenever the user asks to create or generate an image.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.