Agent Teams

This is the deep dive into Agent Teams. For basic setup, see Claude Code Integration.

Agent Teams is the headline capability. With Agent Teams enabled, Claude Code can coordinate multiple parallel workers implementing your specification simultaneously.

Set the environment variable:


export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

Run specforge init (or re-run with --force if already initialized). The CLI generates Agent Teams orchestration files:

File	Role
`orchestrator.md`	Reads the specification, analyzes the dependency graph, assigns tickets to workers, monitors progress
`worker.md`	Implements a single ticket — reads context, writes code, runs tests, reports results
`validator.md`	Reviews completed work — checks acceptance criteria, runs test suites, flags issues
`conventions.md`	Shared rules for code style, commit messages, branch naming, PR structure

Then start Claude Code and say:


Implement the active SpecForge specification

The orchestrator reads your spec, identifies actionable tickets (all dependencies satisfied), spawns workers per epic, and coordinates parallel execution. Validators check each completed ticket. The dependency graph ensures workers never collide.

ℹ️ Agent Teams is a Claude Code feature (Opus 4.6+, experimental). SpecForge doesn’t build its own orchestration on top of Claude Code — it generates the configuration that makes Agent Teams work with your dependency graph out of the box.