mobile-harness — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

Flagged: disables SSL verification. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by droidrun · Codex Skill · ★ 344

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is mobile-harness safe to install? View the security audit →

About mobile-harness

Portable operating instructions for AI agents controlling Android and iOS devices—locally or in the cloud. Mobile Harness is a compact Markdown harness, not an agent runtime. Its primary control path is Python's , with optional client apps where needed. Agent Setup Prompt Copy paste it into your agent: Scope Android through using local ADB with optional Portal, Portal HTTP-only, or cloud. iOS through using HTTP or cloud. Manual Install Install the full public control API: Use Python 3.11, 3.12, or 3.13 to create the venv. Tell agents which Python runtime to use: Base includes cloud support through . The extra installs , which uses internally for local Android and iOS backends. Agents should still import only . Primary API python from mobileruncore import Mobilerun m = Mobilerun() device = m.connec

ai-harnessclaude-codecodexmobile-aimobile-development

Quick Facts

Stars344
Forks32
CategoryCodex Skill
LicenseMIT
Quality Score65.6266246642864/100
Open Issues2
Last Updated2026-09-08
Created2026-06-01
Platformsclaude-code, codex
Est. Tokens~17k

Compatible Skills

These tools work well together with mobile-harness for enhanced workflows:

  • claude-code-android — semantic(0.34)+complementary+rare_topics+similar_pop+shared_platform (61%)
  • pockode — semantic(0.42)+complementary+similar_pop+shared_platform (55%)

mobile-harness alternative? Top 6 similar tools

Looking for a mobile-harness alternative? If you're comparing mobile-harness with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claude-code-android by ferrumclaudepilgrim · ⭐ 189

    Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH

  • gensee-crate by GenseeAI · ⭐ 123

    Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes,

  • claude-codex-settings by fcakyon · ⭐ 1.1k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

  • codexia by milisp · ⭐ 915

    Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control

  • memorix by AVIDS2 · ⭐ 791

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Frequently Asked Questions

What is mobile-harness?

mobile-harness is Skills for controlling Android, iOS and cloud phones. It is categorized as a Codex Skill with 344 GitHub stars.

How do I install or use mobile-harness?

You can find installation instructions and usage details in the mobile-harness GitHub repository at github.com/droidrun/mobile-harness. The project has 344 stars and 32 forks, indicating an active community.

What license does mobile-harness use?

mobile-harness is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to mobile-harness?

The top alternatives to mobile-harness on Agent Skills Hub include claude-code-android, gensee-crate, claude-codex-settings. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools