From epic
Designs org-level agent teams via the `epic team` CLI with subcommands for listing, showing, syncing, linking, unlinking, and viewing history. Invoke when setting up agents or /spec yields 3+ requirements.
How this skill is triggered — by the user, by Claude, or both
Slash command
/epic:teamThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill is a thin wrapper around the `epic team` CLI.
This skill is a thin wrapper around the epic team CLI.
Run in terminal:
epic team
epic team handles the full interactive flow:
HARNESS_ORG env → prompt → default "epic")~/.harness/orgs/.claude/agents/{team}/ with ## Team Context injectedFor the full spec see docs/research/team-spec.md.
epic team list # list teams in current org
epic team show {team} # config + agents + mission
epic team show {team} --playbook # full accumulated playbook
epic team sync {team} # re-copy agents to .claude/agents/
epic team link {team} # attach existing team (skip design)
epic team unlink {team} # remove .claude/agents/{team}/
epic team history {team} {agent} # show .history/ entries
npx claudepluginhub epicsagas/epic-harness --plugin epic-harnessCreates and manages dynamic teams of domain agents. Triggers: create team, agent team, team status, cleanup team.
Creates a multi-agent team composition file with purpose definition, member selection, coordination patterns, and registry integration. Use when formalizing recurring collaborative workflows.
Creates, configures, and manages agent teams: spawning teammates, delegate mode, permissions, shutdown, and cleanup. Use when setting up a new team or coordinating workers.