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 russelleNVy · Agent Tool · ★ 897
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is three-man-team safe to install? View the security audit →
russellenvy.github.io/three-man-team The Problem With AI Coding Tools AI coding tools are powerful but undisciplined. They read entire codebases when they need one function. They add features nobody asked for. They drift mid-task. They burn tokens on every session doing work that didn't need to happen. The solution isn't a better prompt. It's a process. Three Man Team gives you three agents with distinct jobs, clear handoffs, and rules that prevent the most expensive failure modes. The Architect plans and deploys. The Builder builds exactly what the brief says. The Reviewer doesn't pass work that isn't right. Why Three Agents DeepMind's multi-agent research shows teams of 3-5 with structured artifact handoffs outperform both solo agents and larger groups. Three is not arbitrary — it is the minimum for meaningful review and the maximum before coordination overhead eats the gain. The roles map to how real software ships: Someone who understands the whole system and owns the deploy Someone who builds fast and clean Someone who catches what the builder missed Quick Start Choose your install type: Per-project install (recommended) One project, one install.
| Stars | 897 |
| Forks | 113 |
| Language | Shell |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.438242037414/100 |
| Last Updated | 2026-06-09 |
| Created | 2026-03-31 |
| Platforms | claude-code, cli |
| Est. Tokens | ~348k |
These tools work well together with three-man-team for enhanced workflows:
Looking for a three-man-team alternative? If you're comparing three-man-team 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.
Copy AI conversations as clean Markdown Context Bundles — one click from ChatGPT, Claude, Gemini, DeepSeek, Gr
200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: htt
Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
Explore other popular agent tool tools:
three-man-team is A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.. It is categorized as a Agent Tool with 897 GitHub stars.
three-man-team is primarily written in Shell. It covers topics such as agent-skills, agent-workflow, ai-agents.
You can find installation instructions and usage details in the three-man-team GitHub repository at github.com/russelleNVy/three-man-team. The project has 897 stars and 113 forks, indicating an active community.
three-man-team is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to three-man-team on Agent Skills Hub include ctxport, claude-skills, claudepro-directory. 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: