ai-dev-standards: Agent for Claude Code

Agent Workflows & Coordination Patterns

How agents work together to accomplish complex tasks through proven coordination patterns.

---

Table of Contents

1. Overview
2. Basic Patterns
3. Advanced Patterns
4. Real-World Workflows
5. Best Practices

---

Overview

Agents can be coordinated in various patterns to accomplish complex tasks more efficiently than single-agent approaches. This document catalogs proven coordination patterns and workflows.

Key Principles:

• Separation of Concerns: Each agent has a clear responsibility
• Loose Coupling: Agents communicate through well-defined interfaces
• Composability: Patterns can be combined for complex workflows
• Fault Tolerance: Workflows handle agent failures gracefully

---

Basic Patterns

1. Sequential Pattern

Structure:

Agent A → Agent B → Agent C

Description: Agents execute one after another, with each agent's output becoming the next agent's input.

When to Use:

• Tasks have clear dependencies
• Each step builds on previous results
• Order matters

Example:

Workflow: Feature Implementation
1. Explore Agent (Medium) → Understand codebase
2. General-Purpose + frontend-builder → Design implementation
3. General-Purpose + testing-strategist → Add tests
4. Codex-Review-Workflow → Validate code

Advantages:

• Simple to understand and implement
• Clear data flow
• Easy to debug

Disadvantages:

• Slow (serial execution)
• Blocked by any agent failure
• No parallelization

---

2. Parallel Pattern

Structure:

        Agent B
       ↗
Agent A → Agent C
       ↘
        Agent D

Description: Multiple agents execute simultaneously on independent tasks, results aggregated at the end.

When to Use:

• Tasks are independent
• No dependencies between agents
• Time is critical

Example:

Workflow: Comprehensive Security Audit
Coordinator: Multi-Agent Architect

Parallel Execution:
├── Agent 1: OWASP Top 10 checks
├── Agent 2: Dependency vulnerabilities
├── Agent 3: Authentication review
├── Agent 4: Authorization review
└── Agent 5: Data validation review

Aggregation: Combine all findings into report