J. RABATIN // CLAUDE OPSFIELD MANUAL · GUIDE
Claude Code · Educational Series

Agent teams: give each subagent one clear job

A single agent doing everything hits a wall — full context, blurred focus, drifting quality. Agent teams fix that by splitting the work across specialized subagents coordinated by a lead.

Reference Guidewith a downloadable resource for your Claude Code sandbox

What's inside

  1. Why one agent stalls
  2. Give each subagent a job
  3. A lead agent coordinates
  4. Manage it from agent view
Section 01

Why one agent stalls

Every agent has one context window. Pile a big, many-part task into it and it fills up, the goals blur together, and quality slips as everything competes for attention. You've felt this when a long session starts forgetting earlier instructions.

The fix isn't a bigger prompt — it's more agents, each with a narrower job.

The failure modeA single agent is a single point of overload. Past a certain size, more instructions make it worse, not better.
Section 02

Give each subagent a job

In an agent team, each subagent has its own context window, its own prompt, and its own tool permissions. One researches, one builds, one reviews. Because each has a clean, narrow scope, each does its part well — and you can give the reviewer different (safer) tools than the builder.

This separation is what keeps quality high as the overall job grows.

researcher -> read-only, search
builder    -> edit files
reviewer   -> read + run tests
Section 03

A lead agent coordinates

A main agent assigns the work, lets the subagents run in parallel, and merges their results into a single answer. You talk to the lead; the lead manages the team. This composes with Dynamic Workflows — a workflow can spin up subagents as part of its plan.

One conductor, many players, one coherent result.

ComposableSubagents and Dynamic Workflows aren't either/or — a workflow can run a whole agent team inside it.
Section 04

Manage it from agent view

Claude Code's agent view lets you manage multiple sessions from one place — see which subagent is running, which is done, and where something is stuck. You step in only where you're needed instead of babysitting the whole thing.

That's how you run a team without losing the thread.

In your sandboxStart with two roles — a builder and a reviewer. Add specialists once the handoffs feel clean.
Free Download

The agent-team blueprint

A template for defining each subagent's role, context, tools, and how the lead combines their work.

Lead agent role
Subagent roles
Per-agent tools
Per-agent context
Handoffs
Merge step
Guardrails
Example: research
Example: build
Checklist
✓ Downloaded. Drop it in your skills/ folder and try it in your Claude Code sandbox.