mobile-agent

mobile-agent is a skill for Claude Code from datit309/supergraph. It costs 46 tokens per session (1,849 once invoked), scanned A, original, MIT.

A mobile testing and device-control skill for iOS and Android phones, tablets, simulators, and emulators. It uses Apple's WebDriverAgent and Android's UiAutomator2 to interact with apps.

In plain words
What is it for?
It is for testing Flutter, React Native, Swift, Kotlin, and Java mobile apps on connected or simulated devices, including taps, swipes, and other touch actions.
Why use it?
It lets the same user flows be tested across both mobile platforms while handling device discovery, gestures, accessibility information, and system alerts.

Skill for Claude Code

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

Part of the supergraph plugin — 44 skills, 7 agents, 6 hooks, 1 plugin shipped together

Good fit It is for testing Flutter, React Native, Swift, Kotlin, and Java mobile apps on connected or simulated devices, including taps, swipes, and other touch actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/datit309/supergraph/mobile-agent
Install

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.

Any agent
npx skills add datit309/supergraph --skill mobile-agent
Clone the repo
git clone --depth 1 https://github.com/datit309/supergraph

Made for: Claude Code.

Or install supergraph, the plugin that ships this one along with the rest of its 44 skills, 7 agents, 6 hooks, 1 plugin.

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/datit309/supergraph/mobile-agent/github.svg)](https://agentmods.dev/skills/datit309/supergraph/mobile-agent)
Your own site
<a href="https://agentmods.dev/skills/datit309/supergraph/mobile-agent"><img src="https://agentmods.dev/badge/skills/datit309/supergraph/mobile-agent/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-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/datit309/supergraph/mobile-agent"><img src="https://agentmods.dev/badge/skills/datit309/supergraph/mobile-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00046 $0.01849
Opus 5.5 $0.00018 $0.00740
Sonnet 5.5 $0.00009 $0.00370
Haiku 4.5 $0.00005 $0.00185

Measured 3d ago against content hash 1b5036829551, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mobile-agent scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/init-mobile-qa.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl --fail --max-time 5 http://127.0.0.1:8100/status
plugins/supergraph/skills/mobile-agent/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/supergraph:mobile-agent

One skill, two independent backends: WebDriverAgent (iOS) and UiAutomator2 (Android). This is an agent procedure, not an automatic device provisioning service. In DSH invoke /mobile-agent; in Claude Code use /supergraph:mobile-agent.

1. Preflight — do not skip

  1. Inspect the host's available MCP tools. Required: wda_status, wda_session_start, wda_snapshot, wda_tap for iOS; uiauto_status, uiauto_session_start, uiauto_snapshot, uiauto_tap for Android.
  2. If tools are missing, STOP execution and report BLOCKED: MCP backend not loaded. Skill frontmatter does not install or start MCP servers. Configure the relevant stdio entry from the installed plugin's absolute directory:
    • iOS: node <absolute-plugin-dir>/bin/sg-wda-mcp.js
    • Android: node <absolute-plugin-dir>/bin/sg-uiautomator2-mcp.js Restart/reconnect the host MCP connection and verify tools/list. Do not invent tools or say a shell probe is a completed UI test.
  3. Ask for platform, app identifier, target device and test flow if absent. Discover using wda_device_list / uiauto_device_list only when that backend is available.
  4. Select ONE target. Multiple USB devices do not imply isolated sessions. These servers hold one mutable session and reference map per process. Never run concurrent flows against one server instance. For multiple devices use separately configured server processes and unique forwarded ports.
  5. Verify health using the selected platform's status tool. Device discovery alone does not prove WDA/instrumentation is running. Record backend URL, selected device and status result. Keep device identifiers out of public reports.

2. Prepare the native driver

The operator must install platform SDKs and native runner. Do not install APKs, change signing, grant permissions or launch arbitrary apps without authorization.

iOS

Requires macOS/Xcode, a trusted unlocked device with Developer Mode, and a signed WebDriverAgentRunner built for that target. Obtain WDA from https://github.com/appium/WebDriverAgent and follow its current signing/build instructions. Start the runner in Xcode. For USB forwarding with current libusbmuxd:

Read the full file on GitHub · 95 lines

Files

What ships with it

3 files 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.

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. 3d ago Changed · -32 lines · -21 tokens per session 1b5036829551
  2. 16d ago First seen · 127 lines · 67 tokens per session scan A 61609ba188a3

Subscribe to this mod's changes

mobile-agent is a skill published in the GitHub repository datit309/supergraph (23 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 1,849 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.

Related

mobile-agent compared with skills from other repositories

mobile-agent next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mobile-agentdatit309/supergraphSkill234d agoMITA46Claude Code
xcode-testing-workflowgaelic-ghost/socketSkill102mo agoApache-2.0A81Claude Code, Codex
playwright-clitestdino-hq/playwright-skillSkill4193d agoMITA64Claude Code, Codex
playwright-qatestdino-hq/playwright-skillSkill4193d agoMITA83Claude Code, Codex
e2e-testdinotestdino-hq/playwright-skillSkill4193d agoMITB230Claude Code, Codex
icon-composer-app-icon-workflowgaelic-ghost/socketSkill102mo agoApache-2.0A73Claude Code, Codex
bootstrap-xcode-workspacegaelic-ghost/socketSkill102mo agoApache-2.0A36Claude Code, Codex