👥

Claude Code Agent Teams (Experimental)

Self-ReportedCurated

Swarm teammates sharing a task list — parallel exploration on a single codebase.

Anthropic· active
Follow
Curated from Claude Code Docs — Agent Teams — not claimed by or endorsed by the organization. Metrics cited only as the source states. Absent metrics render as [unknown].

Recent activity

Version cuts and proof, newest first — the living track record.

  1. Artifact · Claude Code Agent Teams documentation published (experimental)1y ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Swarm
Agent count
3
Platform
Claude Code
Runs on
Claude Code ×3
Industries
software-delivery
Task kinds
parallel-explorationmulti-file-codingdistributed-debugging
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Swarm

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."

System wiring

Typical Swarm layout — schematic, not verified wiring
Typical role-level schematic — not verified wiringdirectsdirectsdirectscoordinates viacoordinates viacoordinates viaHuman operatorHumanoperatorHUMANGATEPeer worker APeer worker ABUILDERPeer worker BPeer worker BBUILDERPeer worker CPeer worker CBUILDERMessage busMessage busMESSAGE BUS
Node details

Typical Swarm layout — schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs → Peer worker A
  • directs → Peer worker B
  • directs → Peer worker C
BuilderPeer worker A
Tool
Peer worker A
Autonomy
Runs autonomously
Sends
  • coordinates via → Message bus
Receives
  • directs ← Human operator
BuilderPeer worker B
Tool
Peer worker B
Autonomy
Runs autonomously
Sends
  • coordinates via → Message bus
Receives
  • directs ← Human operator
BuilderPeer worker C
Tool
Peer worker C
Autonomy
Runs autonomously
Sends
  • coordinates via → Message bus
Receives
  • directs ← Human operator
Message busMessage bus
Tool
Message bus
Autonomy
Runs autonomously
Receives
  • coordinates via ← Peer worker A
  • coordinates via ← Peer worker B
  • coordinates via ← Peer worker C

How a typical Swarm team handles a task

Typical Swarm layout — schematic, not verified wiring

  1. Task arrives

    Human operator directs Peer worker A, Peer worker B, and Peer worker C.

  2. The builders execute

    Peer worker A, Peer worker B, and Peer worker C build the work. Coordination flows over Message bus.

  3. Human holds the last word

    Human operator holds final approval.

Replicate a typical Swarm setup

Typical Swarm layout — schematic, not verified wiring

Ingredients

  • HumanHuman operator
  • BuilderPeer worker A
  • BuilderPeer worker B
  • BuilderPeer worker C
  • Message busMessage bus

Setup order

  1. 1.Provision the substrate: Message bus.
  2. 2.Wire Peer worker A: it receives "directs" from Human operator. Wire Peer worker B: it receives "directs" from Human operator. Wire Peer worker C: it receives "directs" from Human operator.
  3. 3.Declare the human gate: Human operator holds final approval.
🤝
Claude Code TeammateTeammate A

Claude Code

[unknown]

🧑‍💻
Claude Code Lead AgentTeammate B

Claude Code

[unknown]

🤖
Claude Code SubagentTeammate C

Claude Code

[unknown]

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.

Task success ratenot estimated
[unknown]
evidence-linkedwhy?

Claude Code multi-agent team patterns — no published benchmark figures at time of indexing.

as of Jan 1, 2025

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

Why it works

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.

How it was built

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.

Oversight model

Experimental feature — behavior may change. No human-in-the-loop described in documentation. 3–5 teammates recommended for optimal coordination.

Proof (1)

The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactJun 1, 2025evidence-linked

    Claude Code Agent Teams documentation published (experimental)

    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-teams

Sign in to add a proof entry.

Sign in

Attestations (0)

Named 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