by nuphos · Codex Skill · ★ 374
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 | 374 |
| Forks | 38 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 68/100 |
| Open Issues | 75 |
| Last Updated | 2026-11-07 |
| Created | 2026-10-01 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~15k |
Nuphos The agent workspace for your team. Coding agents are single-player by default: one agent, on one laptop, in one terminal, for one person. Nuphos is where a team runs them instead — across people, across machines, and without the session ending when someone closes their lid. Features Use your existing agent. Claude Code and Codex ship today, each behind an ACP adapter.
Looking for a nuphos alternative? If you're comparing nuphos with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
open source grok bot. gawk bots automate your menial work via AI models and build you microapps to manage the
A local-first desktop app for running a team of AI agents on Claude Code, Codex, Cursor, Cline and more, on yo
Local-first project management and persistent context for OpenClaw, Claude Code, Codex, Cursor, and multi-agen
The open-source alternative to Paper.design. A multiplayer design canvas where humans and AI agents design tog
Multiplayer AI: Bring your team and agents together
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus
Explore other popular codex 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: