by my-claude-utils · Agent Tool · ★ 526
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx clsh-dev
npx clsh-dev setupTaken from the project's README on GitHub. Check the security audit before running it.
Flagged: sudo usage, opens a tunnel service. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
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 | 526 |
| Forks | 54 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70/100 |
| Open Issues | 5 |
| Last Updated | 2026-06-20 |
| Created | 2026-03-13 |
| Platforms | browser, claude-code, cli, node |
| Est. Tokens | ~1171k |
clsh Your Mac, in your pocket. Real terminal access from your phone. Not SSH. Not a simulation. A real PTY on your machine, streamed to your pocket. Live Demo · Getting Started · How It Works · Contributing Session Grid Claude Code on Phone Terminal + Live Preview MacBook Keyboard Skin Skin Studio — 6 Themes </td
Looking for a clsh alternative? If you're comparing clsh with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Two devs, one Claude. Share a Claude Code session in real-time with E2E encryption.
Your Claude Code, Everywhere.
A visible workspace for AI agents to collaborate as a single team.
Pixel office for AI agents and multi-agent collaboration
The IDE built for AI coding agents.
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
Explore other popular agent tool 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: