Skip to content
Back to search

three-man-team

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.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/russellenvy--three-man-team/badge.svg)](/listings/russellenvy--three-man-team)

HTML

<a href="/listings/russellenvy--three-man-team"><img src="/api/listings/russellenvy--three-man-team/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**How the team runs:** Three Man Team uses one Claude Code session. Arch is your main agent. When work is ready to build, Arch spins up Bob as a subagent via Claude Code's Agent tool. When Bob is done, Arch spins up Richard the same way. You don't open three windows — everything runs inside your single session.

Choose your install type:

---

Per-project install (recommended)

One project, one install. Clone directly into your project folder.

**Step 1 — Navigate to your project folder and clone**

git clone https://github.com/russelleNVy/three-man-team.git .claude/skills/three-man-team

**Step 2 — Run setup and follow the instructions**

cd .claude/skills/three-man-team && ./setup

Setup takes over from here. It will give you the exact commands to run and the prompt to paste into Claude to get started. Follow what it prints.

---

Global install (all projects)

Install once, use in any project.

**Step 1 — Clone to your global Claude skills folder**

git clone https://github.com/russelleNVy/three-man-team.git ~/.claude/skills/three-man-team
cd ~/.claude/skills/three-man-team && ./setup

That's the one-time install. Setup will confirm everything is in place.

---

**For each project you want to use Three Man Team on:**

**Step 2 — Copy agent files into your project, then spin up Claude**

cp -r ~/.claude/skills/three-man-team/templates/project-folder/. /path/to/your/project/
cd /path/to/your/project

Open Claude Code and paste:

You are the Architect on this project. Please read new-setup.md.

Arch will handle the rest — project context file, team names, and your first session prompt.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 202 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="assets/banner.png" alt="Three Man Team" width="100%">
  3. </p>
  4. <p align="center">
  5. <a href="https://russellenvy.github.io/three-man-team/">russellenvy.github.io/three-man-team</a>
  6. </p>
  7. <p align="center">
  8. By <a href="https://russellenvy.com">RUSSΞLL AARØN</a>
  9. </p>
  10. ---
  11. ## What's New — v1.3.0
  12. - New: `manifest.md` — Arch generates this at first-time setup. Single source of truth for your install: team names, role filenames, handoff directory, repo, branch.
  13. - Improved: version check now reads a version registry (`releases/latest.json`) instead of hitting the GitHub API. Critical updates are mandatory checkpoints; non-critical ones are your choice.
  14. - Improved: Arch reads your actual files before walking through any change — no more guessing at your setup.
  15. - Removed: `VERSION` file retired. Version lives in `manifest.md`.
  16. See [all releases →](https://github.com/russelleNVy/three-man-team/releases)
  17. ---
  18. ## Three Man Team Pro
  19. Pre-built teams for developers, marketers, content creators, and more — install in minutes, start working immediately.
  20. [Join the waitlist →](https://russellenvy.com/tool/three-man-team/)
  21. ---
  22. ## The Problem With AI Coding Tools
  23. AI coding tools are powerful but undisciplined. They read entire codebases when they
  24. need one function. They add features nobody asked for. They drift mid-task. They burn
  25. tokens on every session doing work that didn't need to happen.
  26. The solution isn't a better prompt. It's a process.
  27. 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.
  28. ---
  29. ## Why Three Agents
  30. Three is not arbitrary. Solo agents drift — there's no one to catch a wrong turn. Large
  31. teams generate coordination overhead that eats the productivity gain. Three is the minimum
  32. for meaningful review and the maximum before the team starts managing itself instead of
  33. the work.
  34. The roles map to how real software ships:
  35. - Someone who understands the whole system and owns the deploy
  36. - Someone who builds fast and clean
  37. - Someone who catches what the builder missed
  38. ---
  39. ## Quick Start
  40. **How the team runs:** Three Man Team uses one Claude Code session. Arch is your main agent. When work is ready to build, Arch spins up Bob as a subagent via Claude Code's Agent tool. When Bob is done, Arch spins up Richard the same way. You don't open three windows — everything runs inside your single session.
  41. Choose your install type:
  42. ---
  43. ### Per-project install (recommended)
  44. One project, one install. Clone directly into your project folder.
  45. **Step 1 — Navigate to your project folder and clone**
  46. ```bash
  47. git clone https://github.com/russelleNVy/three-man-team.git .claude/skills/three-man-team
  48. ```
  49. **Step 2 — Run setup and follow the instructions**
  50. ```bash
  51. cd .claude/skills/three-man-team && ./setup
  52. ```
  53. Setup takes over from here. It will give you the exact commands to run and the prompt to paste into Claude to get started. Follow what it prints.
  54. ---
  55. ### Global install (all projects)
  56. Install once, use in any project.
  57. **Step 1 — Clone to your global Claude skills folder**
  58. ```bash
  59. git clone https://github.com/russelleNVy/three-man-team.git ~/.claude/skills/three-man-team
  60. cd ~/.claude/skills/three-man-team && ./setup
  61. ```
  62. That's the one-time install. Setup will confirm everything is in place.
  63. ---
  64. **For each project you want to use Three Man Team on:**
  65. **Step 2 — Copy agent files into your project, then spin up Claude**
  66. ```bash
  67. cp -r ~/.claude/skills/three-man-team/templates/project-folder/. /path/to/your/project/
  68. cd /path/to/your/project
  69. ```
  70. Open Claude Code and paste:
  71. ```
  72. You are the Architect on this project. Please read new-setup.md.
  73. ```
  74. Arch will handle the rest — project context file, team names, and your first session prompt.
  75. ---
  76. ## The Workflow
  77. <p align="center">
  78. <img src="assets/workflow.png" alt="Three Man Team Workflow" width="100%">
  79. </p>
  80. Every unit of work follows the same path. Architect plans and writes the brief. Builder reads it, shows a plan, builds, and hands off to Reviewer. Reviewer clears it or sends it back. Architect deploys with the Project Owner's go-ahead. Nothing skips a step.
  81. See a complete example from problem to deploy → [`examples/sprint-walkthrough.md`](examples/sprint-walkthrough.md)
  82. ---
  83. ## The Team
  84. <p align="center">
  85. <img src="assets/role-cards-cropped.png" alt="Arch, Bob and Richard" width="100%">
  86. </p>
  87. Three agents. Three distinct jobs. Built to work together.
  88. Architect, Builder, Reviewer are the defaults. Rename them to anything — Arch will handle it during setup.
  89. ---
  90. ## Token Optimization
  91. Every session starts with five rules baked into CLAUDE.md:
  92. ```
  93. Is this in a skill or memory? → Trust it. Skip the file read.
  94. Is this speculative? → Kill the tool call.
  95. Can calls run in parallel? → Parallelize them.
  96. Output > 20 lines you won't use → Route to subagent.
  97. About to restate what user said → Delete it.
  98. ```
  99. The token-optimizer skill ships with every install and auto-loads via CLAUDE.md — no manual setup required.
  100. For bash output compression on top of these rules, see [RTK](https://github.com/rtk-ai/rtk) —
  101. a separate tool that compresses `find`, `ls`, `grep` output before it reaches Claude's context.
  102. Not required, but recommended for heavy Claude Code CLI users. The combination of RTK (bash layer)
  103. + token-optimizer (behavior layer) is where real savings compound.
  104. See `docs/token-optimization.md` for the full discipline.
  105. ---
  106. ## Auto-Update
  107. At the start of every session, Arch fetches `releases/latest.json` — a small version registry that lists every release with a critical or non-critical flag. If you're behind, Arch walks you through the updates before anything else.
  108. Critical updates are mandatory checkpoints — they ship structural changes (like `manifest.md`) that later updates depend on. Non-critical updates are optional. Arch reads your actual files to determine what applies to your setup before suggesting anything.
  109. > "There is an update available — version 1.3.0. Before we get into today's work, I want to walk through what changed. I will look at your actual files and tell you exactly what applies to you."
  110. You decide what to apply and when. Nothing changes without your confirmation.
  111. See [releases](https://github.com/russelleNVy/three-man-team/releases) for what's changed.
  112. ---
  113. ## Templates
  114. - `templates/project-folder/` — **Start here.** Named personas (Arch, Bob, Richard), fully written and ready to use. Customize the Who You Are sections and rename to fit your team.
  115. - `templates/generic/` — Blank slate with `[CUSTOMIZE]` placeholders. Use this if you want to build your own personas from scratch or install globally across all projects.
  116. Arch handles renaming during setup — just tell it the new names.
  117. ---
  118. ## License
  119. MIT. Free forever.
  120. ---
  121. ## Built By
  122. Russell Aaron — 20+ years building and supporting software the right way. He built this team
  123. in production shipping a real SaaS platform. It works because it was used before it was
  124. published, fine tuned, and will continue to get better over time as AI models and tools evolve.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.