by 04mg · Agent Tool · ★ 110
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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.
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 | 110 |
| Forks | 7 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 60/100 |
| Last Updated | 2026-11-01 |
| Created | 2026-07-04 |
| Platforms | browser, node |
| Est. Tokens | ~15k |
Caw Web terminal multiplexer for AI agents. Features Run Agents in the Browser Launch Claude Code, Codex CLI, GitHub Copilot, OpenCode, Antigravity, or Pi side-by-side — Caw auto-detects which agents are installed and spins up a terminal pane for each. Agent Control Center Stop babysitting terminals.
These tools work well together with caw for enhanced workflows:
Looking for a caw alternative? If you're comparing caw 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.
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agno
🔐 SSH MCP Tool - AI-powered SSH management through MCP protocol | 基于MCP协议的SSH工具，为AI提供SSH远程操作能力
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
An MCP server to query any Postgres database in natural language.
🚀 Universal SDK for building next-gen MCP servers
Access your terminal and your AI agent from any device — phone, tablet, desktop.
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: