Native Parallel Agents
Orchestration through Claude Code's built-in Agent Tool
Overview
This skill enables coordinating multiple specialized agents through Claude Code's native agent system. Unlike external scripts, this approach keeps all orchestration within Claude's control.
When to Use Orchestration
✅ Good for:
- Complex tasks requiring multiple expertise domains
- Code analysis from security, performance, and quality perspectives
- Comprehensive reviews (architecture + security + testing)
- Feature implementation needing backend + frontend + database work
❌ Not for:
- Simple, single-domain tasks
- Quick fixes or small changes
- Tasks where one agent suffices
Native Agent Invocation
Single Agent
Use the security-auditor agent to review authentication
Sequential Chain
First, use the explorer-agent to discover project structure.
Then, use the backend-specialist to review API endpoints.
Finally, use the test-engineer to identify test gaps.
With Context Passing
Use the frontend-specialist to analyze React components.
Based on those findings, have the test-engineer generate component tests.
Resume Previous Work
Resume agent [agentId] and continue with additional requirements.
Orchestration Patterns
Pattern 1: Comprehensive Analysis
Agents: explorer-agent → [domain-agents] → synthesis
1. explorer-agent: Map codebase structure
2. security-auditor: Security posture
3. backend-specialist: API quality
4. frontend-specialist: UI/UX patterns
5. test-engineer: Test coverage
6. Synthesize all findings
Pattern 2: Feature Review
Agents: affected-domain-agents → test-engineer
1. Identify affected domains (backend? frontend? both?)
2. Invoke relevant domain agents
3. test-engineer verifies changes
4. Synthesize recommendations
Pattern 3: Security Audit
Agents: security-auditor → penetration-tester → synthesis
1. security-auditor: Configuration and code review
2. penetration-tester: Active vulnerability testing
3. Synthesize with prioritized remediation
Available Agents
| Agent |
Expertise |
Trigger Phrases |
orchestrator |
Coordination |
"comprehensive", "multi-perspective" |
security-auditor |
Security |
"security", "auth", "vulnerabilities" |
penetration-tester |
Security Testing |
"pentest", "red team", "exploit" |
backend-specialist |
Backend |
"API", "server", "Node.js", "Express" |
frontend-specialist |
Frontend |
"React", "UI", "components", "Next.js" |
test-engineer |
Testing |
"tests", "coverage", "TDD" |
devops-engineer |
DevOps |
"deploy", "CI/CD", "infrastructure" |
database-architect |
Database |
"schema", "Prisma", "migrations" |
mobile-developer |
Mobile |
"React Native", "Flutter", "mobile" |
api-designer |
API Design |
"REST", "GraphQL", "OpenAPI" |
debugger |
Debugging |
"bug", "error", "not working" |
explorer-agent |
Discovery |
"explore", "map", "structure" |
documentation-writer |
Documentation |
"write docs", "create README", "generate API docs" |
performance-optimizer |
Performance |
"slow", "optimize", "profiling" |
project-planner |
Planning |
"plan", "roadmap", "milestones" |
seo-specialist |
SEO |
"SEO", "meta tags", "search ranking" |
game-developer |
Game Development |
"game", "Unity", "Godot", "Phaser" |
Claude Code Built-in Agents
These work alongside custom agents:
| Agent |
Model |
Purpose |
| Explore |
Haiku |
Fast read-only codebase search |
| Plan |
Sonnet |
Research during plan mode |
| General-purpose |
Sonnet |
Complex multi-step modifications |
Use Explore for quick searches, custom agents for domain expertise.
Synthesis Protocol
After all agents complete, synthesize:
## Orchestration Synthesis
### Task Summary
[What was accomplished]
### Agent Contributions
| Agent | Finding |
|-------|---------|
| security-auditor | Found X |
| backend-specialist | Identified Y |
### Consolidated Recommendations
1. **Critical**: [Issue from Agent A]
2. **Important**: [Issue from Agent B]
3. **Nice-to-have**: [Enhancement from Agent C]
### Action Items
- [ ] Fix critical security issue
- [ ] Refactor API endpoint
- [ ] Add missing tests
Best Practices
- Available agents - 17 specialized agents can be orchestrated
- Logical order - Discovery → Analysis → Implementation → Testing
- Share context - Pass relevant findings to subsequent agents
- Single synthesis - One unified report, not separate outputs
- Verify changes - Always include test-engineer for code modifications
Key Benefits
- ✅ Single session - All agents share context
- ✅ AI-controlled - Claude orchestrates autonomously
- ✅ Native integration - Works with built-in Explore, Plan agents
- ✅ Resume support - Can continue previous agent work
- ✅ Context passing - Findings flow between agents
1---2name: parallel-agents3description: "Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives."4allowed-tools: Read, Glob, Grep5risk: unknown6source: community7metadata:8 source: https://skillmd.com/skills/mayurrathi/parallel-agents9---1011# Native Parallel Agents1213> Orchestration through Claude Code's built-in Agent Tool1415## Overview1617This skill enables coordinating multiple specialized agents through Claude Code's native agent system. Unlike external scripts, this approach keeps all orchestration within Claude's control.1819## When to Use Orchestration2021✅ **Good for:**22- Complex tasks requiring multiple expertise domains23- Code analysis from security, performance, and quality perspectives24- Comprehensive reviews (architecture + security + testing)25- Feature implementation needing backend + frontend + database work2627❌ **Not for:**28- Simple, single-domain tasks29- Quick fixes or small changes30- Tasks where one agent suffices3132---3334## Native Agent Invocation3536### Single Agent37```38Use the security-auditor agent to review authentication39```4041### Sequential Chain42```43First, use the explorer-agent to discover project structure.44Then, use the backend-specialist to review API endpoints.45Finally, use the test-engineer to identify test gaps.46```4748### With Context Passing49```50Use the frontend-specialist to analyze React components.51Based on those findings, have the test-engineer generate component tests.52```5354### Resume Previous Work55```56Resume agent [agentId] and continue with additional requirements.57```5859---6061## Orchestration Patterns6263### Pattern 1: Comprehensive Analysis64```65Agents: explorer-agent → [domain-agents] → synthesis66671. explorer-agent: Map codebase structure682. security-auditor: Security posture693. backend-specialist: API quality704. frontend-specialist: UI/UX patterns715. test-engineer: Test coverage726. Synthesize all findings73```7475### Pattern 2: Feature Review76```77Agents: affected-domain-agents → test-engineer78791. Identify affected domains (backend? frontend? both?)802. Invoke relevant domain agents813. test-engineer verifies changes824. Synthesize recommendations83```8485### Pattern 3: Security Audit86```87Agents: security-auditor → penetration-tester → synthesis88891. security-auditor: Configuration and code review902. penetration-tester: Active vulnerability testing913. Synthesize with prioritized remediation92```9394---9596## Available Agents9798| Agent | Expertise | Trigger Phrases |99|-------|-----------|-----------------|100| `orchestrator` | Coordination | "comprehensive", "multi-perspective" |101| `security-auditor` | Security | "security", "auth", "vulnerabilities" |102| `penetration-tester` | Security Testing | "pentest", "red team", "exploit" |103| `backend-specialist` | Backend | "API", "server", "Node.js", "Express" |104| `frontend-specialist` | Frontend | "React", "UI", "components", "Next.js" |105| `test-engineer` | Testing | "tests", "coverage", "TDD" |106| `devops-engineer` | DevOps | "deploy", "CI/CD", "infrastructure" |107| `database-architect` | Database | "schema", "Prisma", "migrations" |108| `mobile-developer` | Mobile | "React Native", "Flutter", "mobile" |109| `api-designer` | API Design | "REST", "GraphQL", "OpenAPI" |110| `debugger` | Debugging | "bug", "error", "not working" |111| `explorer-agent` | Discovery | "explore", "map", "structure" |112| `documentation-writer` | Documentation | "write docs", "create README", "generate API docs" |113| `performance-optimizer` | Performance | "slow", "optimize", "profiling" |114| `project-planner` | Planning | "plan", "roadmap", "milestones" |115| `seo-specialist` | SEO | "SEO", "meta tags", "search ranking" |116| `game-developer` | Game Development | "game", "Unity", "Godot", "Phaser" |117118---119120## Claude Code Built-in Agents121122These work alongside custom agents:123124| Agent | Model | Purpose |125|-------|-------|---------|126| **Explore** | Haiku | Fast read-only codebase search |127| **Plan** | Sonnet | Research during plan mode |128| **General-purpose** | Sonnet | Complex multi-step modifications |129130Use **Explore** for quick searches, **custom agents** for domain expertise.131132---133134## Synthesis Protocol135136After all agents complete, synthesize:137138```markdown139## Orchestration Synthesis140141### Task Summary142[What was accomplished]143144### Agent Contributions145| Agent | Finding |146|-------|---------|147| security-auditor | Found X |148| backend-specialist | Identified Y |149150### Consolidated Recommendations1511. **Critical**: [Issue from Agent A]1522. **Important**: [Issue from Agent B]1533. **Nice-to-have**: [Enhancement from Agent C]154155### Action Items156- [ ] Fix critical security issue157- [ ] Refactor API endpoint158- [ ] Add missing tests159```160161---162163## Best Practices1641651. **Available agents** - 17 specialized agents can be orchestrated1662. **Logical order** - Discovery → Analysis → Implementation → Testing1673. **Share context** - Pass relevant findings to subsequent agents1684. **Single synthesis** - One unified report, not separate outputs1695. **Verify changes** - Always include test-engineer for code modifications170171---172173## Key Benefits174175- ✅ **Single session** - All agents share context176- ✅ **AI-controlled** - Claude orchestrates autonomously177- ✅ **Native integration** - Works with built-in Explore, Plan agents178- ✅ **Resume support** - Can continue previous agent work179- ✅ **Context passing** - Findings flow between agents