by droidrun · Codex Skill · ★ 426
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: disables SSL verification. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 426 |
| Forks | 48 |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66/100 |
| Open Issues | 7 |
| Last Updated | 2026-11-03 |
| Created | 2026-06-01 |
| Platforms | claude-code, codex |
| Est. Tokens | ~17k |
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.
These tools work well together with mobile-harness for enhanced workflows:
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.
Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH
Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes,
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM
Lightweight Agent Workstation for Codex + Claude code + keke-agent — with dots, task scheduler, git worktree &
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: