by 0xMassi · Codex Skill · ★ 109
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
go install github.com/0xMassi/pocketdev@latest
git clone https://github.com/0xMassi/pocketdevTaken from the project's README on GitHub.
Flagged: sudo usage. 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 | 109 |
| Forks | 6 |
| Language | Go |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 54/100 |
| Last Updated | 2026-06-30 |
| Created | 2026-06-29 |
| Platforms | claude-code, cli, codex, gemini, go |
| Est. Tokens | ~7k |
pocketdev Run the AI coding CLI you already pay for on a cloud box you reach from your phone. provisions an always-on Hetzner server, locks it to your private Tailscale network (no public SSH), and installs the agent you use: Claude Code, Codex, Cursor, opencode, Gemini, Grok, or Aider. You log in with your own subscription.
These tools work well together with pocketdev for enhanced workflows:
Looking for a pocketdev alternative? If you're comparing pocketdev 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.
Paste images into remote Claude Code & Codex CLI over SSH — clipboard bridging for macOS and Windows.
One TUI for every AI coding agent session — Claude Code, Codex, Cursor, and more — in sync across every device
Claude Code on your laptop and remote dev boxes, in one web page. Sessions keep running when SSH drops (no tmu
Process manager for AI agents (and humans)
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
Secure clipboard sharing over SSH for remote work and agentic coding tools.
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: