Agent Team Design
Design multi-agent teams with explicit memory, policy, and eval owners
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 08e1fe0
Followed the five-step procedure to design a support-triage agent team, and it forced an explicit memory owner, policy owner, and evaluation owner plus a start-with-one-agent rule that a freeform baseline design left out entirely. Single self-contained SKILL.md, installs clean with no dependencies, and the referenced agents/ example tree actually ships in the repo.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 6/10
- Docs & honesty 4/5
What Agent Team Design does
A compact procedure skill for planning multi-agent systems. Triggers when you are designing an agent team, meta-agent, or agent operating system, and returns a role list with named memory, policy, and evaluation owners plus a visible agents/ folder layout. Enforces a minimal-team discipline: start with one agent and add roles only when routing, review, or policy ownership justifies it.
How to install Agent Team Design
git clone https://github.com/agentlas-ai/Agentlas-OS
mkdir -p ~/.claude/skills
cd Agentlas-OS && cp -r skills/agent-team-design ~/.claude/skills/agent-team-design
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Agent Team Design
-
/agent-team-designDesign multi-agent teams with explicit memory, policy, and eval owners
It also activates on plain-language prompts like these:
-
design a multi-agent team for customer support triage -
help me set up an agents folder with clearly named role owners -
build a meta-agent system with explicit memory and policy owners
Frequently asked questions
- Is the Agent Team Design skill free?
- Yes. The skill itself is free from agentlas-ai/Agentlas-OS. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Agent Team Design work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Followed the five-step procedure to design a support-triage agent team, and it forced an explicit memory owner, policy owner, and evaluation owner plus a start-with-one-agent rule that a freeform baseline design left out entirely. Single self-contained SKILL.md, installs clean with no dependencies, and the referenced agents/ example tree actually ships in the repo.
- What is the Agent Team Design SkillProof Score?
- 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.
- How do I install Agent Team Design?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Agent Team Design with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.