# Agent Coordination

> Coordinate multiple specialized Skills and Task Agents through parallel, sequential, swarm, hybrid, or iterative execution strategies. Use when orchestrating multi-worker workflows, managing dependencies, or optimizing complex task execution with quality gates.

- Skill: `d-o-hub/agent-coordination` (Agent Skill, multi-file: 6 files)
- Install (CLI): `npx skillmds@latest add d-o-hub/agent-coordination`
- Raw SKILL.md: https://api.skillmd.com/api/skills/d-o-hub/agent-coordination/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: d-o-hub (https://skillmd.com/u/d-o-hub)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/d-o-hub/agent-coordination

---


# Agent Coordination

Coordinate multiple specialized Skills and Task Agents through strategic execution patterns.

## Quick Reference

- **[Strategies](./strategies.md)** - Parallel, sequential, swarm, hybrid, iterative
- **[Skills vs Agents](./skills-agents.md)** - When to use each
- **[Quality Gates](./quality-gates.md)** - Validation checkpoints
- **[Examples](./examples.md)** - Coordination examples

## When to Use

- Orchestrating multi-worker workflows
- Managing dependencies between tasks
- Optimizing complex task execution
- Quality-critical work with validation

## CRITICAL: Skills vs Task Agents

**Skills** (via `Skill` tool): Instruction sets that guide Claude
- Examples: code-quality, architecture-validation, plan-gap-analysis

**Agents** (via `Task` tool): Autonomous sub-processes that execute
- Examples: code-reviewer, test-runner, debugger, loop-agent

**Parallel Execution**: Use single message with multiple Task calls for maximum throughput:
```markdown
[Task tool] → Agent A
[Task tool] → Agent B
[Task tool] → Agent C
All start simultaneously.
```

See **[Strategies](./strategies.md)** for coordination patterns and **[Skills vs Agents](./skills-agents.md)** for when to use each.