by SidhuK · Agent Tool · ★ 185
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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 | 185 |
| Forks | 29 |
| Language | TypeScript |
| Category | Agent Tool |
| License | AGPL-3.0 |
| Quality Score | 68/100 |
| Open Issues | 8 |
| Last Updated | 2026-11-19 |
| Created | 2026-01-30 |
| Platforms | node |
| Est. Tokens | ~14k |
Glyph Join the Glyph community Share feedback, ask questions, and help shape what comes next. Join us on Discord → Offline-first desktop note-taking application. Tauri 2 shell with a React 19 / TypeScript / Vite 8 frontend and a Rust backend. Data lives entirely on-disk in a per-space directory backed by SQLite and the local filesystem. No cloud sync, no server.
These tools work well together with Glyph for enhanced workflows:
Looking for a Glyph alternative? If you're comparing Glyph 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 fast, open-source markdown editor. Graph view, plugin API, themes, Git/WebDAV sync, AI MCP — built on Tauri
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streama
Tactical AI Workspace Monitor & EDR
Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search,
跨平台官方 Codex 桌面应用的安装 / 增量更新 / 干净卸载管理器,内置国内可达的镜像自更新。Cross-platform installer & updater for the official Codex de
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: