Native Parallel Agents
Orchestration via Claude Code's built-in Agent Tool
Overview
Coordinate multiple specialized agents through Claude Code's native agent system. Keeps all orchestration within Claude's control (no external scripts).
When to Use
Good for:
- Tasks requiring multiple expertise domains
- Code analysis from security, performance & quality perspectives
- Comprehensive reviews (architecture + security + testing)
- Feature impl needing backend + frontend + db work
Not for:
- Single-domain tasks
- Quick fixes | 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.
W/ Context Passing
Use the frontend-specialist to analyze React components.
Based on 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: Config & code review
2. penetration-tester: Active vulnerability testing
3. Synthesize w/ prioritized remediation
Available Agents
| Agent |
Expertise |
Triggers |
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 |
DB |
"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 |
Docs |
"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 Dev |
"game", "Unity", "Godot", "Phaser" |
Claude Code Built-in Agents
| Agent |
Model |
Purpose |
| Explore |
Haiku |
Fast read-only codebase search |
| Plan |
Sonnet |
Research during plan mode |
| General-purpose |
Sonnet |
Multi-step modifications |
Use Explore for quick searches, custom agents for domain expertise.
Synthesis Protocol
After all agents complete:
## 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
- 17 specialized agents available for orchestration
- Logical order - Discovery -> Analysis -> Impl -> Testing
- Share context - Pass findings to subsequent agents
- Single synthesis - One unified report, not separate outputs
- Verify changes - Always include test-engineer for code mods
Key Benefits
- Single session - All agents share context
- AI-controlled - Claude orchestrates autonomously
- Native integration - Works w/ 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 w/ different domain expertise or when comprehensive analysis requires multiple perspectives.4---56# Native Parallel Agents78> Orchestration via Claude Code's built-in Agent Tool910## Overview1112Coordinate multiple specialized agents through Claude Code's native agent system. Keeps all orchestration within Claude's control (no external scripts).1314## When to Use1516**Good for:**17- Tasks requiring multiple expertise domains18- Code analysis from security, performance & quality perspectives19- Comprehensive reviews (architecture + security + testing)20- Feature impl needing backend + frontend + db work2122**Not for:**23- Single-domain tasks24- Quick fixes | small changes25- Tasks where one agent suffices2627---2829## Native Agent Invocation3031### Single Agent32```33Use the security-auditor agent to review authentication34```3536### Sequential Chain37```38First, use the explorer-agent to discover project structure.39Then, use the backend-specialist to review API endpoints.40Finally, use the test-engineer to identify test gaps.41```4243### W/ Context Passing44```45Use the frontend-specialist to analyze React components.46Based on findings, have the test-engineer generate component tests.47```4849### Resume Previous Work50```51Resume agent [agentId] and continue with additional requirements.52```5354---5556## Orchestration Patterns5758### Pattern 1: Comprehensive Analysis59```60Agents: explorer-agent -> [domain-agents] -> synthesis61621. explorer-agent: Map codebase structure632. security-auditor: Security posture643. backend-specialist: API quality654. frontend-specialist: UI/UX patterns665. test-engineer: Test coverage676. Synthesize all findings68```6970### Pattern 2: Feature Review71```72Agents: affected-domain-agents -> test-engineer73741. Identify affected domains (backend? frontend? both?)752. Invoke relevant domain agents763. test-engineer verifies changes774. Synthesize recommendations78```7980### Pattern 3: Security Audit81```82Agents: security-auditor -> penetration-tester -> synthesis83841. security-auditor: Config & code review852. penetration-tester: Active vulnerability testing863. Synthesize w/ prioritized remediation87```8889---9091## Available Agents9293| Agent | Expertise | Triggers |94|-------|-----------|----------|95| `orchestrator` | Coordination | "comprehensive", "multi-perspective" |96| `security-auditor` | Security | "security", "auth", "vulnerabilities" |97| `penetration-tester` | Security Testing | "pentest", "red team", "exploit" |98| `backend-specialist` | Backend | "API", "server", "Node.js", "Express" |99| `frontend-specialist` | Frontend | "React", "UI", "components", "Next.js" |100| `test-engineer` | Testing | "tests", "coverage", "TDD" |101| `devops-engineer` | DevOps | "deploy", "CI/CD", "infrastructure" |102| `database-architect` | DB | "schema", "Prisma", "migrations" |103| `mobile-developer` | Mobile | "React Native", "Flutter", "mobile" |104| `api-designer` | API Design | "REST", "GraphQL", "OpenAPI" |105| `debugger` | Debugging | "bug", "error", "not working" |106| `explorer-agent` | Discovery | "explore", "map", "structure" |107| `documentation-writer` | Docs | "write docs", "create README", "generate API docs" |108| `performance-optimizer` | Performance | "slow", "optimize", "profiling" |109| `project-planner` | Planning | "plan", "roadmap", "milestones" |110| `seo-specialist` | SEO | "SEO", "meta tags", "search ranking" |111| `game-developer` | Game Dev | "game", "Unity", "Godot", "Phaser" |112113---114115## Claude Code Built-in Agents116117| Agent | Model | Purpose |118|-------|-------|---------|119| **Explore** | Haiku | Fast read-only codebase search |120| **Plan** | Sonnet | Research during plan mode |121| **General-purpose** | Sonnet | Multi-step modifications |122123Use **Explore** for quick searches, **custom agents** for domain expertise.124125---126127## Synthesis Protocol128129After all agents complete:130131```markdown132## Orchestration Synthesis133134### Task Summary135[What was accomplished]136137### Agent Contributions138| Agent | Finding |139|-------|---------|140| security-auditor | Found X |141| backend-specialist | Identified Y |142143### Consolidated Recommendations1441. **Critical**: [Issue from Agent A]1452. **Important**: [Issue from Agent B]1463. **Nice-to-have**: [Enhancement from Agent C]147148### Action Items149- [ ] Fix critical security issue150- [ ] Refactor API endpoint151- [ ] Add missing tests152```153154---155156## Best Practices1571581. **17 specialized agents** available for orchestration1592. **Logical order** - Discovery -> Analysis -> Impl -> Testing1603. **Share context** - Pass findings to subsequent agents1614. **Single synthesis** - One unified report, not separate outputs1625. **Verify changes** - Always include test-engineer for code mods163164---165166## Key Benefits167168- **Single session** - All agents share context169- **AI-controlled** - Claude orchestrates autonomously170- **Native integration** - Works w/ built-in Explore, Plan agents171- **Resume support** - Can continue previous agent work172- **Context passing** - Findings flow between agents
georgekhananaev