🔱

Claude Code Sub-agents Pattern

Self-ReportedCurated

Lead agent spawns specialist subagents in isolated context windows.

Anthropic· active
Follow
Curated from Claude Code Docs — Sub-agents — 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 sub-agents documentation published1y ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Orchestrator–Worker
Agent count
2
Platform
Claude Code
Runs on
Claude Code ×2
Industries
software-delivery
Task kinds
multi-file-codingresearchcontext-management
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Orchestrator–Worker

Hub-and-spoke with context isolation. Lead agent coordinates and assigns work. Each subagent runs in its own context window and returns only a summary to the lead. Subagents only report results back to the main agent and cannot communicate with each other (vs. agent teams, which allow peer messaging).

System wiring

Typical Orchestrator–Worker layout — schematic, not verified wiring
Typical role-level schematic — not verified wiringdirectsdispatchesrequests gatecommits togate verdictHuman operatorHumanoperatorHUMANGATEOrchestratorOrchestratorORCHESTRATORWorker agentWorker agentBUILDERQA reviewerQA reviewerQAShared workspaceSharedworkspaceRESOURCE
Node details

Typical Orchestrator–Worker layout — schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs → Orchestrator
OrchestratorOrchestrator
Tool
Orchestrator
Autonomy
Runs autonomously
Sends
  • dispatches → Worker agent
  • requests gate → QA reviewer
Receives
  • directs ← Human operator
BuilderWorker agent
Tool
Worker agent
Autonomy
Runs autonomously
Sends
  • commits to → Shared workspace
Receives
  • dispatches ← Orchestrator
QAQA reviewer
Tool
QA reviewer
Autonomy
Runs autonomously
Sends
  • gate verdict → Shared workspace
Receives
  • requests gate ← Orchestrator
ResourceShared workspace
Tool
Shared workspace
Autonomy
Runs autonomously
Receives
  • commits to ← Worker agent
  • gate verdict ← QA reviewer

How a typical Orchestrator–Worker team handles a task

Typical Orchestrator–Worker layout — schematic, not verified wiring

  1. Task arrives

    Human operator directs Orchestrator.

  2. The orchestrator routes the work

    Orchestrator dispatches build work to Worker agent.

  3. Worker agent builds the work

    Worker agent builds the work.

  4. Independent review gates the work

    QA reviewer reviews the work. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.

  5. The artifact lands

    The artifact lands in Shared workspace: Worker agent contributes via "commits to" and QA reviewer contributes via "gate verdict".

  6. Human holds the last word

    Human operator holds final approval.

Replicate a typical Orchestrator–Worker setup

Typical Orchestrator–Worker layout — schematic, not verified wiring

Ingredients

  • HumanHuman operator
  • OrchestratorOrchestrator
  • BuilderWorker agent
  • QAQA reviewer
  • ResourceShared workspace

Setup order

  1. 1.Provision the substrate: Shared workspace.
  2. 2.Stand up the orchestrator: Orchestrator.
  3. 3.Wire Worker agent: it receives "dispatches" from Orchestrator. Wire QA reviewer: it receives "requests gate" from Orchestrator.
  4. 4.Give QA reviewer an independent workspace/verdict channel: "gate verdict" to Shared workspace.
  5. 5.Declare the human gate: Human operator holds final approval.
🧑‍💻
Claude Code Lead AgentLead

Claude Code

[unknown]

🤖
Claude Code SubagentSubagent

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 subagent 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

Context isolation keeps the main conversation clean and prevents token waste from exploration work. Tool allowlists on subagents enforce constraints mechanically. Cost routing (cheaper model for subagents) is documented as a first-class design pattern.

How it was built

Subagent definitions use custom system prompts and tool restrictions. Cost control: routing tasks to faster/cheaper models like Haiku for subagents. Each subagent definition has a description that Claude uses to decide when to delegate. Source: code.claude.com/docs/en/sub-agents.

Oversight model

Subagents can be constrained via tool allowlists (e.g., read-only access). Lead maintains control; subagent results are summarized back to lead context.

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 sub-agents documentation published

    Official documentation describes subagent patterns, context isolation, tool allowlists, and cost routing to cheaper models.

    https://code.claude.com/docs/en/sub-agents

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