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 agentmods add skills/zhpeng24/devkit/imagegen-frontend-mobilenpx skills add zhpeng24/devkit --skill imagegen-frontend-mobilegit clone --depth 1 https://github.com/zhpeng24/devkitWrote 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/zhpeng24/devkit/imagegen-frontend-mobile)<a href="https://agentmods.dev/skills/zhpeng24/devkit/imagegen-frontend-mobile"><img src="https://agentmods.dev/badge/skills/zhpeng24/devkit/imagegen-frontend-mobile.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00498 |
| Opus 5 | $0.00017 | $0.00249 |
| Sonnet 5 | $0.00007 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
imagegen-frontend-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 3d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Mobile Image Generation
Generate native-feeling mobile screen images and flows. This skill produces images only; it does not write SwiftUI, React Native, Flutter, HTML, or other implementation code.
Define the flow
Identify the platform, device class, audience, product task, entry state, requested screens, navigation model, brand material, and whether the images are presentation comps or frame-free implementation references.
Use exactly the requested screens when the user gives a count. Otherwise choose the minimum set needed to explain the flow; do not add filler screens. State the screen order before generation.
Keep one product system
Maintain a shared palette, type scale, spacing rhythm, component language, icon treatment, imagery style, navigation, and elevation model. Vary screen composition according to its job without letting the set drift into different products.
Respect platform conventions:
- safe areas, status/navigation regions, and keyboard states;
- native navigation and back behavior;
- touch targets, reachable primary actions, readable type, and clear hierarchy;
- believable loading, empty, error, permission, and success states when relevant.
Avoid phone-sized websites, random charts, floating-card clutter, pill overload, unreadable microcopy, fake complexity, generic purple-blue gradients, and inconsistent device frames. Do not invent product data, claims, logos, or permissions.
Generate
Use the available image-generation capability. Give each screen its own clear prompt with platform, dimensions, state, content hierarchy, navigation context, visual-system rules, and relationship to adjacent screens.
Use a subtle device frame only for presentation context. When the user asks for frame-free or implementation-ready screens, render the screen itself edge to edge. Create a fresh screen or detail image instead of cropping an earlier result.
Check and deliver
Inspect every output for safe-area correctness, readable text, touch geometry, logical transitions, consistent navigation, palette and components, unclipped content, even framing, and clear screen identity. Regenerate only failed screens.
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.
- 3d ago First seen · 42 lines · 35 tokens per session scan A a5f0860a89a8
imagegen-frontend-mobile is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 498 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
competition-ios-runtime
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for IPA runtime analysis, Frida hooks, Objective-C or Swift method tracing, Keychain inspection, SSL pinning bypass, URL scheme handling, and iOS request-signing recovery. Use when the user asks to hook an IPA, trace Objective-C or Swift…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
react-native-ease-refactor
Scan for Animated/Reanimated code and migrate to EaseView.