Team Spawn

Spawn an agent team using presets (review, debug, feature, fullstack, research, security, migration) or custom composition

Published by @Seth Hobson·from wshobson/agents·0 agent reads / 30d·0 saves·

Team Spawn

Spawn a multi-agent team using preset configurations or custom composition. Handles team creation, teammate spawning, and initial task setup.

Pre-flight Checks

  1. Verify that CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set:

    • If not set, inform the user: "Agent Teams requires the experimental feature flag. Set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in your environment."
    • Stop execution if not enabled
  2. Parse arguments from $ARGUMENTS:

    • First positional arg: preset name or "custom"
    • --name: team name (default: auto-generated from preset)
    • --members N: override default member count
    • --delegate: enter delegation mode after spawning

Phase 1: Team Configuration

Preset Teams

If a preset is specified, use these configurations:

review — Multi-dimensional code review (default: 3 members)

  • Spawn 3 team-reviewer agents with dimensions: security, performance, architecture
  • Team name default: review-team

debug — Competing hypotheses debugging (default: 3 members)

  • Spawn 3 team-debugger agents, each assigned a different hypothesis
  • Team name default: debug-team

feature — Parallel feature development (default: 3 members)

  • Spawn 1 team-lead agent + 2 team-implementer agents
  • Team name default: feature-team

fullstack — Full-stack development (default: 4 members)

  • Spawn 1 team-implementer (frontend), 1 team-implementer (backend), 1 team-implementer (tests), 1 team-lead
  • Team name default: fullstack-team

research — Parallel codebase, web, and documentation research (default: 3 members)

  • Spawn 3 general-purpose agents, each assigned a different research question or area
  • Agents have access to codebase search (Grep, Glob, Read) and web search (WebSearch, WebFetch)
  • Team name default: research-team

security — Comprehensive security audit (default: 4 members)

  • Spawn 1 team-reviewer (OWASP/vulnerabilities), 1 team-reviewer (auth/access control), 1 team-reviewer (dependencies/supply chain), 1 team-reviewer (secrets/configuration)
  • Team name default: security-team

migration — Codebase migration or large refactor (default: 4 members)

  • Spawn 1 team-lead (coordination + migration plan), 2 team-implementer (parallel migration streams), 1 team-reviewer (verify migration correctness)
  • Team name default: migration-team

Custom Composition

If "custom" is specified:

  1. Use AskUserQuestion to prompt for team size (2-5 members)
  2. For each member, ask for role selection: team-lead, team-reviewer, team-debugger, team-implementer
  3. Ask for team name if not provided via --name

Phase 2: Team Creation

  1. Use the TeamCreate tool to create the team with team_name and description
  2. For each team member, use the Agent tool with:
    • team_name: the team name
    • name: unique descriptive member name (e.g., "fullstack-lead", "frontend-impl", "security-reviewer")
    • subagent_type: the selected role (for example, agent-teams:team-lead, agent-teams:team-implementer, agent-teams:team-reviewer, agent-teams:team-debugger, or general-purpose for research)
    • prompt: Role-specific instructions referencing the appropriate agent definition
  3. Do not use the role name team-lead as the spawned member name. Team creation can reserve role-like names, so use a unique member name and address the teammate by the actual name returned by Agent or listed in ~/.claude/teams/{team-name}/config.json.

Phase 3: Initial Setup

  1. Use TaskCreate to create initial placeholder tasks for each teammate
  2. Display team summary:
    • Team name
    • Member names and roles
    • Display mode (tmux/iTerm2/in-process)
  3. If --delegate flag is set, transition to delegation mode

Output

Display a formatted team summary:

Team "{team-name}" spawned successfully!

Members:
  - {member-1-name} ({role})
  - {member-2-name} ({role})
  - {member-3-name} ({role})

Use /team-status to monitor progress
Use /team-delegate to assign tasks
Use /team-shutdown to clean up

Bundled with this artifact

2 files

Reference files that ship alongside this artifact. Agents pull these in only when the task needs them.

More on the bench

SKILL0

Skill Creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

ai-prompt-engineering+1
6
SKILL0

Bash Pro

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.

ai-prompt-engineering+3
4
SKILL0

Security Compliance Compliance Check

You are a compliance expert specializing in regulatory requirements for software systems including GDPR, HIPAA, SOC2, PCI-DSS, and other industry standards. Perform comprehensive compliance audits and provide implementation guidance for achieving and maintaining compliance.

ai-prompt-engineering+3
3