mobile-emulator-start

mobile-emulator-start is a skill for Claude Code, Codex from kensaurus/cursor-kenji. It costs 65 tokens per session (3,305 once invoked), scanned A, original, MIT.

A startup procedure for an Android emulator and Metro, the development server that bundles React Native apps. It handles the order needed to get an Expo or bare React Native app running.

In plain words
What is it for?
Use it to start Metro and an Android emulator, fix a stuck development loop, or investigate connection errors between Expo and the emulator.
Why use it?
It avoids duplicate development servers, occupied ports, stale processes, and launching the app before the bundle is ready.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/dev-android.mjs --launch --port 8081.

Good fit Use it to start Metro and an Android emulator, fix a stuck development loop, or investigate connection errors between Expo and the emulator.

Compare 6 skills from other repositories ↓
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/kensaurus/cursor-kenji
agentmods
npx agentmods add skills/kensaurus/cursor-kenji/mobile-emulator-start

Made for: Claude Code, Codex.

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-emulator-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/mobile-emulator-start.svg)](https://agentmods.dev/skills/kensaurus/cursor-kenji/mobile-emulator-start)
Your own site
<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/mobile-emulator-start"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/mobile-emulator-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,305 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 103
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 193
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 203
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 196
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00065 $0.03305
Opus 5 $0.00032 $0.01653
Sonnet 5 $0.00013 $0.00661
Haiku 4.5 $0.00006 $0.00331

Measured 3d ago against content hash 3c75782ef280, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mobile-emulator-start 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.

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.

1. **Inspect** — existing terminals, `curl /status`, `adb devices`
skills/mobile-emulator-start/SKILL.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mobile-emulator-start — Metro + Android emulator in a sane order

Degree of freedom: MIXED. Reuse vs fresh Metro [HIGH freedom]; port kill, boot, reverse, /status, then intent [LOW freedom — run exactly].

Deliver a working dev loop (emulator online → tunnel → bundler ready → app intent) without burning time on duplicate Metros, stale caches, or racing the dev client ahead of /status.

Pair with mobile-emulator-test for full QA; this skill focuses on bring-up + terminal hygiene.

How to reason

  1. Inspect — existing terminals, curl /status, adb devices
  2. Decide — reuse a healthy Metro vs one explicit fresh wipe
  3. Order — free ports → boot AVD → reverse → Metro → wait /status
  4. Launch — intent only after packager-status:running

Worked example

Inspect: two terminals on 8081; adb devices empty; last intent was ECONNREFUSED. Decide: kill both Metros (not a cache wipe — user asked to start, not "stale bundle"). Order: boot AVD → adb reverse → one expo start --dev-client → poll /status. Launch: am start the scheme deeplink; logcat has no immediate refused-to-Metro.

Self-critique before reporting

  • One Metro — no second cwd serving the wrong graph
  • Order held — emulator in adb devices before reverse; /status before intent
  • Size expectedwm size is 1080×2400 unless scroll-QA was requested
  • Right owner — guest/signed-in QA walk → mobile-emulator-test; crash after start → debug-error

Critical ordering (why this skill exists) [LOW freedom — run exactly]

  1. Emulator attached to adb before trusting adb reverse (or reverse again when the serial appears).
  2. curl http://127.0.0.1:<PORT>/status shows packager-status:running before am start / dev-client deeplink (avoids “Cannot connect to Expo CLI” / 127.0.0.1 refused).
  3. Helpers that enumerate devices once at startup may skip --launch / reverse if the emulator booted late — re-run reverse + intent after adb devices shows device.

Read the full file on GitHub · 295 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. 3d ago First seen · 295 lines · 65 tokens per session scan A 3c75782ef280

Subscribe to this mod's changes

mobile-emulator-start is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 9d ago), licensed MIT. It adds 65 tokens to every session and 3,305 once invoked, about $0.0003 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories