by EliranG · Claude Skill · ★ 143
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx claude-duet host --name Alice
npx claude-duet join <offer-code> --password abc123Taken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. 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 | 143 |
| Forks | 8 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 66/100 |
| Last Updated | 2026-09-08 |
| Created | 2026-03-08 |
| Platforms | browser, claude-code, cli, node |
| Est. Tokens | ~15k |
✦ claude-duet Two devs. One Claude. Pure vibes. Share your Claude Code session with a friend — real-time collaboration for AI pair programming. ⚡ Quick Start Assumes you already have Claude Code installed. Send the join command to your partner via Slack, Discord, whatever works. P2P mode (default): After your partner runs the join command, they'll get an answer code to share back with you.
Looking for a claude-duet alternative? If you're comparing claude-duet with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Mobile companion for Claude Code, Gemini CLI & OpenCode. Encrypted, remote
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Claude forgets everything when the session ends. CodeSyncer makes it remember.
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the r
Shared intelligence layer for organizations
Explore other popular claude 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: