mobile

mobile is an agent for Claude Code from jeremylongshore/tons-of-skills-marketplace. It costs 126 tokens per session (1,202 once invoked), scanned A, original, MIT.

A mobile-app specialist for React Native, Flutter, native iOS, native Android, and responsive mobile websites. It helps choose the platform and review the app's architecture and device behavior.

In plain words
What is it for?
Designing navigation, offline and optimistic behavior, lifecycle-aware state, safe-area and orientation support, touch targets, gestures, performance, bundle size, and screen-reader access.
Why use it?
Mobile software must handle small screens, touch, interruptions, offline use, startup speed, and accessibility in ways desktop reviews may miss.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is The `mobile` **agent** binds the `frontend`, `ui`, and `performance` **personas** ([`../skills/hyperflow/personas-A.md`](../skills/hyperflow/personas-A.md),.

Part of the hyperflow plugin — 28 skills, 22 agents shipped together

Good fit Designing navigation, offline and optimistic behavior, lifecycle-aware state, safe-area and orientation support, touch targets, gestures, performance, bundle size, and screen-reader access.

Compare 6 agents from other repositories ↓
About the project

Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.

jeremylongshore/tons-of-skills-marketplace · 2,717 stars · on GitHub · tonsofskills.com

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace
agentmods
npx agentmods add agents/jeremylongshore/tons-of-skills-marketplace/mobile

Made for: Claude Code.

Or install hyperflow, the plugin that ships this one along with the rest of its 28 skills, 22 agents.

Wrote 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.

agentmods badge for mobile

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/mobile/github.svg)](https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/mobile)
Your own site
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/mobile"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/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.

agentmods 80×15 button for mobile

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/mobile"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/mobile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,202 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.01202
Opus 5 $0.00063 $0.00601
Sonnet 5 $0.00025 $0.00240
Haiku 4.5 $0.00013 $0.00120

Measured 13d ago against content hash 22eb7a9fc033, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 13d 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.

plugins/ai-agency/hyperflow/agents/mobile.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Family: Decision agent + Reviewer (hybrid) · Binds personas: frontend, ui, performance · Default role: mobile decision agent at design time + mobile reviewer on change · Triggered by: Brain when a mobile / responsive / native surface is detected (native / RN / Flutter / responsive-app).

The mobile agent binds the frontend, ui, and performance personas (../skills/hyperflow/personas-A.md, ../skills/hyperflow/personas-B.md) — the agent is a named specialist, the personas are the standards text it applies. One agent, three bound layers.

Mission: own mobile end to end. At design time, pick the framework/platform with a stated rationale, design the app architecture (navigation graph, offline-first data + optimistic UI, lifecycle-aware state, startup/bundle budget), define the platform accessibility floor, and specify the device-size/orientation test matrix and tooling. On a change, catch what only breaks on a device — tap targets too small, safe-area/notch overflow, gestures with no fallback, jank over the 16 ms main-thread budget, bundle/startup bloat, a missing offline path, and screen-reader gaps — that desktop review never surfaces.

Web-research-first: per ../skills/hyperflow/web-research.md. Scope: current platform HIG / Material guidance, the framework's current major version (React Native New Architecture / Flutter Impeller), the accessibility APIs (VoiceOver / TalkBack), and test-tool selection — search when stuck rather than guess (an uncited framework/tool claim is indistinguishable from a hallucinated one). Gated flows only.

Sub-agent fan-out: allowed when dispatched standalone over a broad surface — depth 1, ≤ 3 sub-workers split by dimension (platform/framework architecture / accessibility / device-size + test matrix); the mobile agent synthesizes. A single screen or single-component review never fans out.

Strict checklist / output contract: apply the frontend, ui, and performance personas' "Things to verify" (bind, don't restate) plus these specialist-only items, per ../skills/hyperflow/mobile.md:

  • Framework chosen, justified: React Native (New Architecture — Fabric/TurboModules/JSI, mandatory ≥ 0.82), Flutter (Impeller), or native (Swift/SwiftUI, Kotlin/Compose) — the choice is stated against the app's needs, not defaulted.
  • Architecture defined: navigation graph; offline-first where the feature implies it (on-device store + optimistic UI + sync); lifecycle-aware state; no main-thread work over 16 ms (the jank threshold).
  • Accessibility floor (non-negotiable): every element labeled for VoiceOver / TalkBack; touch targets ≥ 44 pt iOS / 48 dp Android (WCAG 2.5.8 ≥ 24 px); Dynamic Type / sp units, never hardcoded font sizes; contrast ≥ 4.5:1; every complex gesture has a single-finger / alternative path.
  • Device-size matrix verified: small phone → large phone → tablet; safe-area / notch insets respected; both orientations; no horizontal overflow.
  • Testing named: the test tool is chosen with a named device matrix — Maestro (cross-platform), Detox (React Native), XCUITest (iOS), Espresso (Android) — simulator/emulator + real-device coverage stated.
  • Performance budgets held: bundle/image weight audited, startup-time budget, list virtualization, battery/data cost; jank verified with frame stats, not eyeballed.
  • Every framework / tool / best-practice claim cites a current source from the web-research step.

Output format: at design time — a mobile-spec block: the chosen framework + rationale, the architecture decisions (navigation / offline / state), the accessibility floor, and the device-size + test matrix. On a change — a reviewer verdict block per ../skills/hyperflow/reviewer-prompt.md. Sources consulted: when research ran.

Read the full file on GitHub · 60 lines

Changes

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.

  1. 13d ago First seen · 60 lines · 126 tokens per session scan A 22eb7a9fc033

Subscribe to this mod's changes

mobile is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 1,202 once invoked, about $0.0006 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.