The benchmark fields — designed for comparison across teams.
Swarm topology with shared state. Teammates access a shared task list and communicate via a mailbox system. Parallel exploration: teammates can work on different parts of a problem simultaneously. Key distinction from sub-agents: "sub-agents only report results back to the main agent, while in agent teams agents can communicate with each other."
Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.
Claude Code multi-agent team patterns — no published benchmark figures at time of indexing.
Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.
Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.
Swarm topology enables parallel exploration without bottlenecking through a single orchestrator. Shared task list prevents work duplication. Mailbox communication allows agents to coordinate asynchronously. Complementary to sub-agents: teams for peer collaboration, sub-agents for context isolation.
Claude Code runtime with shared task list and mailbox infrastructure. Agents coordinate via message passing; each agent can spawn its own sub-agents if needed. Documented as complementary to (not a replacement for) the sub-agents pattern.
Experimental feature — behavior may change. No human-in-the-loop described in documentation. 3–5 teammates recommended for optimal coordination.
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
Swarm topology with shared task list and mailbox. Recommended size: 3–5 teammates. Distinct from sub-agents: teammates communicate with each other; sub-agents only report back to the lead.
https://code.claude.com/docs/en/agent-teamsSign in to add a proof entry.
Sign inNamed third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this team.
Sign in