No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by catlog22 · Agent Tool · ★ 128
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pi-maestro-flow safe to install? View the security audit →
pi-maestro-flow 🎼 Pi 编码智能体的多智能体编排层 将一个编码智能体，变成一支协同工程团队。 中文 | English 是什么 pi-maestro-flow 是 Pi 编码智能体 的多智能体编排插件。它让一个只能串行干活的智能体，变成一支能并行调度、自主长跑、先规划后动手、全程可视的工程团队——并自带跨会话的持久化知识系统。 它由三个插件组成（装一个即得全部）： 简言之：flow 负责「编排与知识」，teammate 负责「并行执行」，cockpit 负责「看见」。 核心特性 🔀 并行多智能体调度 — 一次派出多个
| Stars | 128 |
| Forks | 20 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 62.7212971910706/100 |
| Open Issues | 4 |
| Last Updated | 2026-10-13 |
| Created | 2026-07-07 |
| Platforms | node |
| Est. Tokens | ~15k |
Looking for a pi-maestro-flow alternative? If you're comparing pi-maestro-flow with other agent tool tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Explore other popular agent tool tools:
pi-maestro-flow is Maestro workflow tools as Pi extensions — pi-teammate + pi-maestro-agent. It is categorized as a Agent Tool with 128 GitHub stars.
pi-maestro-flow is primarily written in TypeScript.
You can find installation instructions and usage details in the pi-maestro-flow GitHub repository at github.com/catlog22/pi-maestro-flow. The project has 128 stars and 20 forks, indicating an active community.
pi-maestro-flow is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to pi-maestro-flow on Agent Skills Hub include claude-plugins, tutor-skills. 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: