team-implement
Team Implement
Adaptive spec-driven development team that scales from 3 agents (lite) to ~9 (full) based on project complexity. All planning completes before any code changes, with explicit user approval between planning and implementation.
Prerequisites & fallback chain: read this first
Full mode needs multi-agent teams. In Claude Code that requires:
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
With the flag set, full mode spawns named teammates via the Task tool with a team_name (the team itself is created implicitly by the first such call, there's no separate "create team" step), coordinates via SendMessage, and stops a teammate with TaskStop. The exact tool signatures depend on the environment you're running in: treat any call shown below as illustrative and use whatever the local Task/SendMessage/TaskStop equivalents actually are. Do not invent a Teammate tool or similar if nothing like it exists here.
No flag, or a Task ... team_name call fails? Fall back to Lite mode: identical phase structure, but roles run as sequential Task subagents (no team_name, no cross-agent messaging) instead of a coordinated team.
No Task/subagent tool at all? Fall back further still: run every phase's steps yourself, inline, sequentially. The phase → gate → phase structure below is the workflow: teams and subagents are just two ways to parallelize it.
Delegate mode (Claude Code, full mode): Shift+Tab restricts the lead to coordination-only tools. Without it, wait for teammates to finish before touching their files yourself.