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 wedabro/bro-skills --skill imagegen-frontend-mobilegit clone --depth 1 https://github.com/wedabro/bro-skillsWrote 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/wedabro/bro-skills/imagegen-frontend-mobile)<a href="https://agentmods.dev/skills/wedabro/bro-skills/imagegen-frontend-mobile"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/imagegen-frontend-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/wedabro/bro-skills/imagegen-frontend-mobile"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/imagegen-frontend-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 | $0.00068 | $0.00584 |
| Opus 5 | $0.00034 | $0.00292 |
| Sonnet 5 | $0.00014 | $0.00117 |
| Haiku 4.5 | $0.00007 | $0.00058 |
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 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile App Image Direction
Generate readable, internally consistent mobile screens that feel native to the requested platform and product category.
Output contract
- Generate enough standalone screens to show the requested flow; one image must not pretend to cover several unreadable screens.
- Default to a subtle premium phone frame unless the user asks for frameless screens.
- Keep the app UI, not the device mockup, as the visual focus.
- Generate fresh screens for missing states; never crop prior images into new deliverables.
- Return images only. Do not write code.
Workflow
- Determine platform mode, audience, primary job, navigation model, and exact flow.
- Define a design bible: palette, type scale, spacing, icon style, imagery, surface treatment, and signature component.
- Map the minimum complete screen sequence, including important success, empty, error, or permission states.
- Generate screens in flow order while preserving navigation, tokens, copy tone, and component behavior.
- Check safe areas, tap-target plausibility, text size, state continuity, platform conventions, and mockup framing.
Non-negotiables
- Design for a phone viewport first; do not shrink a desktop dashboard into a handset.
- Keep primary actions reachable and hierarchy obvious at a glance.
- Use platform conventions intentionally: iOS, Android, or a consistent cross-platform neutral language.
- Avoid excessive cards, pills, floating glass, tiny labels, fake metrics, and decorative gradients.
- Keep one navigation model across the flow unless a state explicitly changes it.
- Use images and texture when they support the product; never sacrifice text readability.
- Use one coherent icon family and consistent component geometry.
- Keep onboarding concise and show product value before asking for unnecessary permissions.
Detailed reference
Read only the relevant section of references/full-guide.md:
- Platform conventions: search
PLATFORM MODE RULE. - Screen count and flow planning: search
GENERATE ENOUGH SCREENSorLOGICAL FLOW RULE. - Mockup and safe-area details: search
DEVICE MOCKUP FRAMEorSAFE AREA. - Navigation, iconography, texture, palette, or typography: search the matching heading.
- Product-category guidance: search
CATEGORY-SPECIFIC BIAS. - Regeneration and final checks: search
REGENERATION RULEorQUALITY CHECK.
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 · 49 lines · 68 tokens per session scan A e485d91c8389
imagegen-frontend-mobile is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 68 tokens to every session and 584 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
horoscope-post-batch
Returns up to 12 daily horoscopes in a single request.
barcode-get-base64
Returns a JSON envelope containing the barcode as a base64-encoded PNG string, along with its type and dimensions.
developer-utilities-get-base64
Generate a QR code for any string and return a base64-encoded PNG. Configurable size and error correction level.
quotes-post-batch
Returns up to 50 random quotes in a single request. Each quote counts as one unit of usage.
useragent-get-useragent
Parses a user agent string and returns structured information about the browser, OS, device, and bot status.
horoscope-get-{sign}
Returns a daily horoscope reading for the specified zodiac sign.