by subicura · Claude Skill · ★ 58
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx purplemux@latest
npm install -g purplemuxTaken 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 | 58 |
| Forks | 7 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 65/100 |
| Open Issues | 18 |
| Last Updated | 2026-08-10 |
| Created | 2026-03-20 |
| Platforms | browser, claude-code, codex, node |
| Est. Tokens | ~16k |
purplemux Claude Code and Codex, many tasks at once. Faster. Every session on a single screen. Uninterrupted, even on your phone. English Türkçe Install Open http://localhost:8022 in your browser. Done. Requires Node.js 20+ and tmux. macOS or Linux. Prefer a native app? Grab the macOS Electron build from the latest release ( for Apple Silicon & Intel).
These tools work well together with purplemux for enhanced workflows:
Looking for a purplemux alternative? If you're comparing purplemux 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.
Keyboard-first desktop Kanban workspace for AI coding agents with embedded terminals, git worktrees, and hook-
A calm agent multiplexer with familiar IDE features, for macOS, with an iPhone app.
All of your agents, shells, and TUIs in one durable terminal workspace
Pixel office for AI agents and multi-agent collaboration
Two devs, one Claude. Share a Claude Code session in real-time with E2E encryption.
Your Claude Code, Everywhere.
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: