agent-teams · travisjneuman — Claude Code skill: what it does, how to install
Teaches Claude how to compose agent teams: which tasks split well, how many teammates to spawn, and what goes into each spawn prompt. Active only once teams are enabled.
MIT 153 installs ★ 114 updated 2026-10-25
npx skills add travisjneuman/.claude --skill agent-teams -a claude-codeWhat agent-teams does
The skill gives the model a reference on composing Claude Agent Teams. It lists the tasks worth splitting: a broad code review, work that crosses several layers, a bug with no obvious cause, a comparison of approaches. It also lists the ones that are not, such as same-file edits or a tight token budget.
The skill describes six team templates. Review puts three teammates on security, performance and correctness. Feature work runs an architect who plans, an implementer who writes, and a reviewer who checks the diff. Debugging spreads 3-5 competing hypotheses and has teammates argue them out. Two more layouts cover cross-platform apps and full-stack work with per-layer file ownership. Every spawn prompt follows a five-part formula: role, directories, focus, context, deliverable.
Teams stay off until a session starts with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Without it the skill points to ordinary subagents and tells the model not to suggest a team on its own. Platform support differs: macOS and Linux get in-process plus tmux split panes, Windows only in-process, and --teammate-mode auto picks the mode.
What it helps with
- Decide whether a task needs a team or a single subagent
- Run a code review from three independent angles
- Split a full-stack task by file ownership
- Write a spawn prompt that keeps a teammate inside its directories
- Test competing theories about a bug in parallel
Example prompts for the agent
- Put together a three-reviewer team: security, performance, correctness.
- The bug's cause is unclear — give four hypotheses to separate teammates and let them argue.
- Lay out spawn prompts for a full-stack task: frontend, backend, database, each with its own directories.
How to install agent-teams
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill agent-teams -a claude-code2Manually: put the files in place
~/.claude/skills/agent-teams/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/agent-teams/
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill agent-teams -a codex2Manually: put the files in place
.agents/skills/agent-teams/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill agent-teams -a cursor2Manually: put the files in place
.cursor/skills/agent-teams/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install travisjneuman/.claude skills/agent-teams2Manually: put the files in place
.github/skills/agent-teams/SKILL.md1Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill agent-teams -a gemini-cli2Platform CLI
gemini skills install https://github.com/travisjneuman/.claude --path skills/agent-teamsManually: put the files in place
.devin/skills/agent-teams/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add travisjneuman/.claude --skill agent-teams -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about agent-teams
How do I install agent-teams in Claude Code?
Run npx skills add travisjneuman/.claude --skill agent-teams -a claude-code; the skill lands at ~/.claude/skills/agent-teams/SKILL.md.
What does agent-teams do?
It gives the model guidance on composing Claude Agent Teams: which tasks fit, how many teammates to spawn, and how to phrase each spawn prompt.
Do I need to enable anything first?
Yes. Start the session with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1; otherwise the skill falls back to ordinary subagents.
Source text
SKILL.md · MIT
--- name: agent-teams description: Team composition knowledge for Claude Code Agent Teams - when teams fit, optimal sizing, spawn prompt patterns. Use only when the user has explicitly enabled agent teams for the session. allowed-tools: [] --- # Agent Teams Composition Skill You have expertise in composing and orchestrating Claude Code Agent Teams. Use this knowledge when the user's task would benefit from parallel multi-session work. Agent teams are off by default. Use them only when the user explicitly started the session with `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`; otherwise use ordinary subagents, and don't propose teams unprompted. ## When Agent Teams Fit With teams enabled, they fit when: - The user asks for comprehensive code review (suggest 3-reviewer team) - The task involves work across multiple layers (frontend + backend + database) - The user describes a bug with unclear root cause (suggest competing hypothesis investigation) - The user wants to evaluate multiple technologies or approaches (suggest research panel) - The task can be clearly split into independent, file-separated workstreams Do NOT suggest agent teams when: - The task is sequential or involves same-file edits - A single session or subagent would suffice - The coordination overhead would exceed the benefit - The user is on a tight token budget ## Team Templates ### Full Review (3 teammates) Security reviewer + Performance reviewer + Correctness reviewer (edge cases, error paths, callers). Each reviews independently, then lead synthesizes findings. ### Feature Dev (3 teammates) Architect (plan approval required) + Implementer + Reviewer. Architect plans first, implementer follows, reviewer validates the diff by review. ### Debug Squad (3-5 teammates) Each teammate investigates a different hypothesis. Adversarial debate structure -- teammates challenge each other's theories. ### Cross-Platform (3 teammates) iOS developer + Android developer + Shared architect. Each platform teammate owns their own directory. Architect coordinates API contracts. ### Full-Stack (3 teammates) Frontend + Backend + Database. Clear file ownership per layer. Coordinate on API contracts first. ### Research Panel (3 teammates) Simplicity advocate + Performance advocate + Devil's advocate. Each evaluates from a different perspective, then synthesize. ## Spawn Prompt Formula Every spawn prompt should include: 1. Role: "You are the [role] teammate responsible for [domain]" 2. Files: "You own files in [directories]. Do not modify files outside your scope." 3. Focus: "Specifically look for / implement [details]" 4. Context: "[Project-specific information the teammate needs]" 5. Deliverable: "Report your findings as [format] / Implement [specific output]" ## Cross-Platform Awareness - macOS and Linux: full support (in-process + tmux split panes) - Windows: in-process mode only (automatic with auto setting) - Always use `--teammate-mode auto` (default) for automatic detection ## Related Documentation - `~/.claude/docs/AGENT-TEAMS.md` - Full guide with examples - `~/.claude/docs/reference/workflows/agent-teams.md` - Decision framework - `~/.claude/commands/assemble-team.md` - Quick team assembly command
© travisjneuman · MIT · travisjneuman/.claude
Similar skills
All skills for Agent setup: memory, context, orchestration →agent-teams by other authors comes first.