by jazzenchen · Codex Skill · ★ 180
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/jazzenchen/agent-hud-native-open.git
Taken from the project's README on GitHub.
| Stars | 180 |
| Forks | 31 |
| Language | Swift |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 61/100 |
| Open Issues | 7 |
| Last Updated | 2026-10-23 |
| Created | 2026-09-10 |
| Platforms | claude-code, codex |
| Est. Tokens | ~18k |
Agent HUD Your agents, at a glance. Usage, tokens and sessions for Claude Code, Codex and 16 more agents, at your Mac's notch or any screen edge. English · 简体中文 · Website · Supported agents · Documentation [!NOTE] This repository is Agent HUD's native Swift app. It was called agent-hud-open and is now agent-hud-native-open. Agent HUD continues as a cross-platform app at jazzenchen/agent-hud-open.
These tools work well together with agent-hud-native-open for enhanced workflows:
Looking for a agent-hud-native-open alternative? If you're comparing agent-hud-native-open 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.
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Curs
Vibe Island — macOS notch panel for 25 AI coding agents: Claude Code, Codex, Cursor, Gemini CLI & more. Monito
Claude Code plugin that asks several AI coding agents the same question and shows their answers side by side.
macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.
macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.
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: