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 arielaizn/grok-plugin-cc --skill grok-imagine-promptinggit clone --depth 1 https://github.com/arielaizn/grok-plugin-ccWrote 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/arielaizn/grok-plugin-cc/grok-imagine-prompting)<a href="https://agentmods.dev/skills/arielaizn/grok-plugin-cc/grok-imagine-prompting"><img src="https://agentmods.dev/badge/skills/arielaizn/grok-plugin-cc/grok-imagine-prompting/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/arielaizn/grok-plugin-cc/grok-imagine-prompting"><img src="https://agentmods.dev/badge/skills/arielaizn/grok-plugin-cc/grok-imagine-prompting.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 | $0.00079 | $0.01024 |
| Opus 5 | $0.00039 | $0.00512 |
| Sonnet 5 | $0.00016 | $0.00205 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
grok-imagine-prompting 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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompting Grok Imagine
The plugin passes your prompt to image_gen verbatim. Nothing downstream will fix a vague prompt, so it has to carry the intent on its own.
Do not generate it — build it
Image models garble exact text, numbers, and structure. They invent digits, mangle words, draw chart bars matching no data, and point diagram arrows nowhere. A more detailed prompt does not fix this, and an edit pass rarely does either.
So when the output must get specific content right — charts from real numbers, labelled diagrams, tables, UI with real copy, anything with more than a few words of text — build it in HTML/CSS and screenshot it. Generate only when what matters is how it looks: photos, illustrations, characters, scenes, textures, decorative art.
A short headline or a logotype is usually fine. A pricing table is not.
Structure
Order the prompt roughly: subject → action or pose → setting → style → composition → lighting and mood → key details.
- Lead with the subject. The opening words carry the most weight.
- Write natural prose, not comma-separated keyword tags.
- State what you want present. There is no negative prompt, and "no people" often summons people.
- One coherent scene per prompt. Two competing focal points produce a muddle.
- Two to five sentences is the sweet spot. Past that, later details start getting dropped.
Match the aspect ratio to the use: 16:9 banner or video frame, 9:16 phone or story, 1:1 avatar or icon, 4:3/3:4 print-ish.
An example
Too thin:
a coffee shop
Enough to steer:
A narrow third-wave coffee shop interior at opening time, one barista wiping down a brass espresso machine. Warm morning light rakes in through a street-facing window, catching steam and dust. Muted earth tones, matte wood, unpolished concrete. Shot at eye level on a 35mm lens, shallow depth of field, the machine sharp and the back of the room falling soft.
The second names subject, action, setting, palette, optics, and light — each of which the model can act on.
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.
- 12d ago First seen · 75 lines · 79 tokens per session scan A 180be812d244
grok-imagine-prompting is a skill published in the GitHub repository arielaizn/grok-plugin-cc (6 stars, last pushed 29d ago), licensed MIT. It adds 79 tokens to every session and 1,024 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 skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…