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 reatlat/fullstory-claude-plugin --skill mobile-analyzergit clone --depth 1 https://github.com/reatlat/fullstory-claude-pluginWrote 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/reatlat/fullstory-claude-plugin/mobile-analyzer)<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/mobile-analyzer"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/mobile-analyzer/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/reatlat/fullstory-claude-plugin/mobile-analyzer"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/mobile-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.01384 |
| Opus 5 | $0.00022 | $0.00692 |
| Sonnet 5 | $0.00009 | $0.00277 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
mobile-analyzer 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 10d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Analyzer
Deep-dive into mobile user experience — touch events, viewport issues, responsive design bugs, and mobile-specific conversion patterns.
When to Use
- "How does our mobile experience compare to desktop?"
- "Are mobile users having trouble with the checkout flow?"
- "Find sessions where mobile users encountered viewport issues"
- "Is the new responsive design working on tablets?"
- "What percentage of rage clicks happen on mobile vs desktop?"
- "Show me mobile sessions where users pinch-zoomed repeatedly"
Mental Model
Mobile users are different from desktop users:
- Input: Touch targets, swipe gestures, virtual keyboard
- Viewport: Smaller screen, variable sizes, landscape/portrait
- Context: On-the-go, distracted, slower connections
- Expectations: Faster, simpler, thumb-friendly
A design that works on desktop can fail catastrophically on mobile — elements overlapping, touch targets too small, keyboard covering form fields, horizontal scroll appearing.
Workflow
Step 1: Quantify mobile vs desktop
Start with the split:
fullstory:build_metric(
query="sessions by device type",
output_type="top_n"
)
→ "68% desktop, 28% mobile, 4% tablet"
Then compare key metrics across devices:
fullstory:build_metric(query="checkout conversion by device type", output_type="top_n")
fullstory:compute_metric(metric_id)
Step 2: Mobile-specific frustration signals
fullstory:get_opportunities → filter by device_type="mobile"
Mobile-specific signals to watch for:
- Pinch-zoom events: Users zooming in to read or tap — text too small, touch targets too small
- Horizontal scroll: Content wider than viewport — broken responsive layout
- Orientation change rage: Users rotating device repeatedly — layout broken in one orientation
- Keyboard overlap: Form fields obscured by virtual keyboard — user taps field, keyboard covers the submit button
Step 3: Compare mobile vs desktop by page
For key pages, compare performance:
Page: /checkout
Mobile: 12% conversion, 34% bounce, 3 rage click events per 100 sessions
Desktop: 22% conversion, 18% bounce, 1 rage click event per 100 sessions
→ Mobile conversion is nearly half of desktop. The gap needs investigation.
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.
- 10d ago First seen · 141 lines · 43 tokens per session scan A 960c87d7dd76
mobile-analyzer is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 28d ago), licensed MIT. It adds 43 tokens to every session and 1,384 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 2026-08-30.
Other skills, from other repositories
roblox-ui-design
Use for Roblox UI composition, hierarchy, visual systems, style inheritance, accessibility, and design review.
roblox-gui
Use when building Roblox menus, HUDs, shops, notifications, dialogs, or responsive cross-platform UI.
apple-polish
Design and keynote-readiness craftsmanship review of an iOS app. Evaluates through Jony Ive (visual obsession) and Steve Jobs (demo readiness) perspectives, presents prioritized findings, then orchestrates parallel agents to fix selected issues and push a TestFlight build. Use for design polish, not engineering bugs.
apple-architecture-diagram
Create WWDC-Keynote-ready, self-contained HTML architecture diagrams for Apple platform apps (iOS, macOS, watchOS, tvOS, visionOS). Activates when users ask for app architecture, system design, data flow, module structure, or technical documentation for Apple apps. Produces ultra-beautiful, drill-down capable diagrams…
apple-design
Apple platform design system, iOS 26 & macOS 26 Liquid Glass, design tokens, and accessibility-aware previews. Use when building or reviewing SwiftUI views, defining a theme or design tokens, applying Liquid Glass, organizing asset catalogs, or improving visual consistency. Trigger on "design system", "theme", "design…
apple-review
Comprehensive Apple-grade review of an iOS app covering design (Apple design leader perspective), engineering (architecture and code quality), compliance (App Store rejection risks), and keynote readiness (product story and demo quality). Use when asked for a full app review, Apple-quality audit, design critique, HIG…