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 Gekkos-tech/agency-os --skill imagegen-mobilegit clone --depth 1 https://github.com/Gekkos-tech/agency-osWrote 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/gekkos-tech/agency-os/imagegen-mobile)<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/imagegen-mobile"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/imagegen-mobile/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/gekkos-tech/agency-os/imagegen-mobile"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/imagegen-mobile.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 | $0.00136 | $0.01317 |
| Opus 5 | $0.00068 | $0.00659 |
| Sonnet 5 | $0.00027 | $0.00263 |
| Haiku 4.5 | $0.00014 | $0.00132 |
Grade A, and why
imagegen-mobile 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile App Screen Concepts
Generate app screen images that look like a real, premium iOS/Android product — one screen per image, consistent across the whole flow, buildable by a developer who has never seen the brief.
Core rules
- One screen per image. Never a grid of 6 tiny screens in one image — text becomes noise and layouts get invented. A 6-screen flow = 6 images.
- Phone-frame mockup, subtle. Each screen sits inside a minimal premium phone frame (thin dark bezel, rounded corners, slight presentation margin on a quiet studio background). The frame signals "mobile" and hides edge artifacts — but the app content is the star: the screen fills ~80% of the image. Portrait orientation, ~9:16 to 3:4 image ratio.
- The whole flow shares one token block. Consistency across screens is the difference between "an app" and "six random dribbble shots".
Workflow
1. Plan the flow — which screens tell the product story?
Pick 4–8 screens that together explain what the app does and why it feels good. Default story arc:
1. Onboarding / welcome — brand moment, one-line promise
2. Home / dashboard — the daily view; the app's identity screen
3. Core action — the ONE thing users do (book, track, send, scan)
4. Detail view — one item opened (product, workout, transaction)
5. Secondary value screen — stats / history / social / library (pick one)
6. Profile or settings — only if it shows something distinctive
Cut screens that don't add to the story (generic login, empty settings). If the user names specific screens, use theirs. Order matters — present the set in flow order.
2. Write the token block once, reuse everywhere
Paste this verbatim into EVERY screen prompt:
APP TOKENS: [app name] — [one-line concept]. Platform: [iOS | Android].
Background: [hex]. Surface/card: [hex]. Text: [hex]. Accent: [hex] (primary actions only).
Type: [e.g. "clean geometric sans, bold large titles, quiet small labels"].
Corner radius: [e.g. 16px cards, pill buttons].
Icons: [e.g. "thin-line minimal icons, 1.5px stroke"] — same style on every screen.
Mood: [3 adjectives]. Frame: minimal dark phone frame on [quiet background hex].
What ships with it
1 file 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.
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 · 89 lines · 136 tokens per session scan A 73ece7fab418
imagegen-mobile is a skill published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 136 tokens to every session and 1,317 once invoked, about $0.0007 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
elevenlabs
Convert documents and text to audio using ElevenLabs text-to-speech. Use this skill when the user wants to create a podcast, narrate a document, read aloud text, generate audio from a file, or convert text to speech.
google-tts
Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech, create a recording of documentation or analysis, create a podcast from a document, or use Google TTS/text-to-speech.…
imagen
Generate images using Google Gemini's image generation capabilities. Use this skill when the user needs to create, generate, or produce images for any purpose including UI mockups, icons, illustrations, diagrams, concept art, placeholder images, or visual representations.
design-mobile-apps
Use when the user wants to design a mobile app or UI screens, when they mention their Sleek (sleek.design) projects, or when implementing Sleek designs in code (HTML, React Native, SwiftUI).
appllama-app-design-skill
Build native-feeling, benchmark-quality mobile app screens (Expo / React Native). Use when designing or implementing any mobile UI — screens, flows, onboarding, paywalls, tab bars, sheets, settings, empty states — or when polishing motion, navigation, typography, dark mode, or perceived performance. Enforces Apple HIG…
seedance-2-5-reference-to-video
Generate reference-guided 1080p video with ByteDance Seedance 2.5 Reference to Video on RunComfy via the runcomfy CLI. Feed up to 9 reference images, 1-3 reference video clips, and 3 reference audio files into one call and get a 4-30 second 1080p clip with native synchronized audio, identity and style locked to your…