by mattzcarey · Agent Tool · ★ 289
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/mattzcarey/zagi.gitTaken from the project's README on GitHub.
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 | 289 |
| Forks | 15 |
| Language | Zig |
| Category | Agent Tool |
| Quality Score | 68/100 |
| Open Issues | 5 |
| Last Updated | 2026-04-07 |
| Created | 2025-11-27 |
| Platforms | claude-code, cli |
| Est. Tokens | ~34k |
zagi a better git interface for agents Why use zagi? 121 git compatible commands 50% smaller output that doesn't overflow context windows 1.5-2x faster than git in all implemented commands Agent friendly features like and Three output modes: succinct (default), (git-identical), Git passthrough for non implemented commands Installation This downloads the binary and sets up as an alias to .
Looking for a zagi alternative? If you're comparing zagi 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 personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.
Commander, your AI coding commander centre for all you ai coding cli agents
Production-grade GitLab MCP server with 86 tools — full GitLab control from any AI agent (Claude, Cursor, Zed)
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: