by mmprotest · Agent Tool · ★ 114
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Some tools help. Some tools assist. Villani Code intervenes.
| Stars | 114 |
| Forks | 17 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 52.0310638192928/100 |
| Open Issues | 25 |
| Last Updated | 2026-08-08 |
| Created | 2026-03-04 |
| Platforms | claude-code, python |
| Est. Tokens | ~13k |
These tools work well together with villani-code for enhanced workflows:
Looking for a villani-code alternative? If you're comparing villani-code 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.
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
Runtime failure resolution for coding agents. Hooks into Claude Code and Codex. Catches loops, dangerous actio
Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend des
Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI
Explore other popular agent tool tools:
villani-code is Some tools help. Some tools assist. Villani Code intervenes.. It is categorized as a Agent Tool with 114 GitHub stars.
villani-code is primarily written in Python. It covers topics such as ai, ai-agent, ai-agents.
You can find installation instructions and usage details in the villani-code GitHub repository at github.com/mmprotest/villani-code. The project has 114 stars and 17 forks, indicating an active community.
The top alternatives to villani-code on Agent Skills Hub include hcom, failproofai, garcon. 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: