Skip to main content
Agent Teams Lite uses a delegate-only orchestrator pattern where the main agent never does phase work directly. All execution happens in specialized sub-agents with fresh context.

​
Architecture Overview

┌──────────────────────────────────────────────────────────┐
│  ORCHESTRATOR (your main agent — gentleman, default, etc) │
│                                                           │
│  Responsibilities:                                        │
│  • Detect when SDD is needed                              │
│  • Launch sub-agents via Task tool                        │
│  • Show summaries to user                                 │
│  • Ask for approval between phases                        │
│  • Track state: which artifacts exist, what's next        │
│                                                           │
│  Context usage: MINIMAL (only state + summaries)          │
└──────────────┬───────────────────────────────────────────┘
               │
               │ Task(subagent_type: 'general', prompt: 'Read skill...')
               │
    ┌──────────┴──────────────────────────────────────────┐
    │                                                      │
    ▼          ▼          ▼         ▼         ▼           ▼
┌────────┐┌────────┐┌────────┐┌────────┐┌────────┐┌────────┐
│EXPLORE ││PROPOSE ││  SPEC  ││ DESIGN ││ TASKS  ││ APPLY  │ ...
│        ││        ││        ││        ││        ││        │
│ Fresh  ││ Fresh  ││ Fresh  ││ Fresh  ││ Fresh  ││ Fresh  │
│context ││context ││context ││context ││context ││context │
└────────┘└────────┘└────────┘└────────┘└────────┘└────────┘
Key insight: The orchestrator stays lightweight by delegating all work. Each sub-agent gets a fresh context window, reducing hallucinations and improving output quality.

​
The Dependency Graph

Agent Teams Lite phases follow a directed acyclic graph (DAG). Each phase has dependencies that must complete before it can run. Or let the implementer detect it from your codebase (test files alongside source). This cycle repeats for every task, ensuring test coverage grows with implementation.
See the TDD Workflow Guide for detailed examples and best practices.

​
Verification (v2.0)

The Verifier sub-agent performs real test execution:
1

Run test suite

Executes your project’s test command:
npm test
# or
pytest
# or
make test
Captures output and checks for failures.
2

Generate spec compliance matrix

Maps each requirement from the specs to test results:
RequirementStatusTest Coverage
Theme toggle switches between light/dark✅ PASSThemeToggle.test.ts:12
System preference detected on first load✅ PASSThemeContext.test.ts:34
Preference persists to localStorage✅ PASSThemeContext.test.ts:45
3

Report issues by severity

  • CRITICAL — Requirement not met, blocks merge
  • WARNING — Edge case missing, should fix
  • SUGGESTION — Nice-to-have improvement
Example:
## Verification Report

**Status**: PASSED with warnings

### Test Results
✓ 42/42 tests passing
✓ 94% code coverage (threshold: 80%)

### Spec Compliance
✓ 7/7 requirements verified

### Warnings
- Consider testing theme toggle keyboard accessibility (WCAG 2.1)

​
What’s Next?

Commands Reference

Learn all the SDD commands in detail

Sub-Agents Architecture

Dive deeper into the sub-agent system

Workflow Guide

Master the complete SDD workflow

Delta Specs

Learn how delta specs work

Build docs developers (and LLMs) love

Get started for freeTalk to us