by caffienerd · Agent Tool · ★ 123
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. 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 | 123 |
| Forks | 14 |
| Language | JavaScript |
| Category | Agent Tool |
| Quality Score | 70/100 |
| Last Updated | 2026-04-28 |
| Created | 2026-02-19 |
| Platforms | browser, gemini, node |
| Est. Tokens | ~197k |
Terminal Start Page A sleek, fast, and feature-rich browser start page driven by an interactive terminal. Boost your productivity with semantic AI routing, direct Gemini integration, open directory search, shelf bookmarks, and a growing suite of built-in utility tools — all wrapped in a premium, modern aesthetic.
Looking for a startpage alternative? If you're comparing startpage 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.
A k9s-inspired CLI and TUI for managing Claude Code sessions — browse, search, inspect, and clean up your AI c
Transform your Claude Code terminal with atomic precision statusline. Features flexible layouts, real-time cos
Claude Code for academics — skills, agents, and setup guides
One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local
Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of cr
Native Safari browser automation for AI agents. 98 tools via AppleScript — zero overhead, keeps logins, runs s
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: