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 devkindhq/ideogram-ai-toolkit --skill marketing-ui-mockup-hero-generatorgit clone --depth 1 https://github.com/devkindhq/ideogram-ai-toolkitWrote 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/devkindhq/ideogram-ai-toolkit/marketing-ui-mockup-hero-generator)<a href="https://agentmods.dev/skills/devkindhq/ideogram-ai-toolkit/marketing-ui-mockup-hero-generator"><img src="https://agentmods.dev/badge/skills/devkindhq/ideogram-ai-toolkit/marketing-ui-mockup-hero-generator/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/devkindhq/ideogram-ai-toolkit/marketing-ui-mockup-hero-generator"><img src="https://agentmods.dev/badge/skills/devkindhq/ideogram-ai-toolkit/marketing-ui-mockup-hero-generator.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 | $0.00223 | $0.02357 |
| Opus 5 | $0.00112 | $0.01179 |
| Sonnet 5 | $0.00045 | $0.00471 |
| Haiku 4.5 | $0.00022 | $0.00236 |
Grade A, and why
marketing-ui-mockup-hero-generator 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing UI Mockup / Hero Generator
This skill produces one of three fixed format types, each a finished raster image rendered via Ideogram, not a mockup described in prose or built as working code:
- Landing-page hero shot — a full-bleed marketing hero with headline, subheadline, and CTA button copy baked in via Ideogram's text rendering, typically showing the product in a browser/device frame or as a standalone visual. The shot a visitor sees before scrolling.
- Device-in-context product mockup — a product's UI shown inside a physical device shell (laptop, phone, tablet, browser chrome) placed in an environmental or lifestyle context (desk surface, hand, studio backdrop). The format for pitch-deck slides and "see it in the real world" shots.
- Dashboard screenshot — a single stylized app/dashboard screen (nav, cards, charts, sidebar) rendered to look polished and "real" for App Store listings, pitch decks, or marketing pages — not a literal render of any actual live codebase.
See references/mockup-anatomy.md for each format's full compositional-layer
breakdown; read it before drafting a prompt (workflow step 2 below), not
reverse-engineered only after generation.
The two artifacts this skill produces
- A generation prompt — a paragraph, Ideogram-legible, naming every assigned compositional layer in reading order with literal copy in quotes.
- A compositional deconstruction — the structured JSON breakdown per
references/composition-spec-format.md, tagging each element with which compositional layer it belongs to so a later pass can reference "the CTA element from the hero shot" without re-describing it.
Always produce both. The paragraph prompt is what you feed the image model; the compositional deconstruction is what you save back to the vault so the mockup's structure survives past the single image.
This skill is a sibling to brand-identity-sheet, character-model-sheet, and
moodboard-generator structurally — same paragraph-prompt-plus-JSON-deconstruction
pattern — but targets marketing-visual deliverables (hero shots, device mockups,
dashboard screenshots) rather than brand systems or characters.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 4.2 KB
- examples/images/technauts-landing-hero-social-1x1.webp 40 KB
- examples/images/technauts-landing-hero.webp 22 KB
- examples/images/voicehive-dashboard-screenshot.webp 20 KB
- examples/images/voicehive-device-mockup.webp 62 KB
- examples/technauts-landing-hero.md 9.1 KB
- examples/voicehive-dashboard-screenshot.md 9.6 KB
- examples/voicehive-device-mockup.md 7.8 KB
- references/anti-slop-discipline.md 4.7 KB
- references/composition-spec-format.md 5.2 KB
- references/mockup-anatomy.md 5.8 KB
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 · 175 lines · 223 tokens per session scan A 550ecd7a9023
marketing-ui-mockup-hero-generator is a skill published in the GitHub repository devkindhq/ideogram-ai-toolkit (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 223 tokens to every session and 2,357 once invoked, about $0.0011 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
mangou-ai-motion-comics
Manages AI motion comic production projects with YAML assets and storyboards. Use when users need to initialize Mangou projects, edit storyboard or asset YAML, generate images or videos, split grid shots, stitch final videos, or debug task backfill.
gpt-image
Generate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model names, posters, typography, reference edits, and inpainting; resolve the model choice before generation.
get-prompt-from-image
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references.…
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
videoagent-image-studio
Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, with zero setup. Use when you want to generate any image without worrying about API keys.
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.