by hoangperry · Codex Skill · ★ 205
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Local-first native macOS terminal with Vietnamese IME support and coding-agent observability
| Stars | 205 |
| Forks | 2 |
| Language | Swift |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 52.5839142337766/100 |
| Open Issues | 7 |
| Last Updated | 2026-09-04 |
| Created | 2026-05-20 |
| Platforms | claude-code, codex |
| Est. Tokens | ~15k |
These tools work well together with herminal for enhanced workflows:
Looking for a herminal alternative? If you're comparing herminal 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.
A native macOS terminal app built on Ghostty for running and supervising coding agents
A scrolling terminal multiplexer that tracks your AI coding agents.
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
:round_pushpin: My dotfiles for macOS using Neovim, Zsh, and Ghostty + Tmux
A native macOS terminal for agent-driven development, built on Ghostty.
Explore other popular codex skill tools:
herminal is Local-first native macOS terminal with Vietnamese IME support and coding-agent observability. It is categorized as a Codex Skill with 205 GitHub stars.
herminal is primarily written in Swift. It covers topics such as ai-agents, apple-silicon, claude-code.
You can find installation instructions and usage details in the herminal GitHub repository at github.com/hoangperry/herminal. The project has 205 stars and 2 forks, indicating an active community.
herminal is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to herminal on Agent Skills Hub include Calyx, seance, agent-deck. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: