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, Grep5---67# Native Parallel Agents89> Orchestration through Claude Code's built-in Agent Tool1011## Overview1213This 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.1415## When to Use Orchestration1617✅ **Good for:**1819- Complex tasks requiring multiple expertise domains20- Code analysis from security, performance, and quality perspectives21- Comprehensive reviews (architecture + security + testing)22- Feature implementation needing backend + frontend + database work2324❌ **Not for:**2526- Simple, single-domain tasks27- Quick fixes or small changes28- Tasks where one agent suffices2930---3132## Native Agent Invocation3334### Single Agent3536```37Use the security-auditor agent to review authentication38```3940### Sequential Chain4142```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 Passing4950```51Use the frontend-specialist to analyze React components.52Based on those findings, have the test-engineer generate component tests.53```5455### Resume Previous Work5657```58Resume agent [agentId] and continue with additional requirements.59```6061---6263## Orchestration Patterns6465### Pattern 1: Comprehensive Analysis6667```68Agents: explorer-agent → [domain-agents] → synthesis69701. explorer-agent: Map codebase structure712. security-auditor: Security posture723. backend-specialist: API quality734. frontend-specialist: UI/UX patterns745. test-engineer: Test coverage756. Synthesize all findings76```7778### Pattern 2: Feature Review7980```81Agents: affected-domain-agents → test-engineer82831. Identify affected domains (backend? frontend? both?)842. Invoke relevant domain agents853. test-engineer verifies changes864. Synthesize recommendations87```8889### Pattern 3: Security Audit9091```92Agents: security-auditor → penetration-tester → synthesis93941. security-auditor: Configuration and code review952. penetration-tester: Active vulnerability testing963. Synthesize with prioritized remediation97```9899---100101## Available Agents102103| Agent | Expertise | Trigger Phrases |104| ----------------------- | ---------------- | -------------------------------------------------- |105| `orchestrator` | Coordination | "comprehensive", "multi-perspective" |106| `security-auditor` | Security | "security", "auth", "vulnerabilities" |107| `penetration-tester` | Security Testing | "pentest", "red team", "exploit" |108| `backend-specialist` | Backend | "API", "server", "Node.js", "Express" |109| `frontend-specialist` | Frontend | "React", "UI", "components", "Next.js" |110| `test-engineer` | Testing | "tests", "coverage", "TDD" |111| `devops-engineer` | DevOps | "deploy", "CI/CD", "infrastructure" |112| `database-architect` | Database | "schema", "Prisma", "migrations" |113| `mobile-developer` | Mobile | "React Native", "Flutter", "mobile" |114| `api-designer` | API Design | "REST", "GraphQL", "OpenAPI" |115| `debugger` | Debugging | "bug", "error", "not working" |116| `explorer-agent` | Discovery | "explore", "map", "structure" |117| `documentation-writer` | Documentation | "write docs", "create README", "generate API docs" |118| `performance-optimizer` | Performance | "slow", "optimize", "profiling" |119| `project-planner` | Planning | "plan", "roadmap", "milestones" |120| `seo-specialist` | SEO | "SEO", "meta tags", "search ranking" |121| `game-developer` | Game Development | "game", "Unity", "Godot", "Phaser" |122123---124125## Claude Code Built-in Agents126127These work alongside custom agents:128129| Agent | Model | Purpose |130| ------------------- | ------ | -------------------------------- |131| **Explore** | Haiku | Fast read-only codebase search |132| **Plan** | Sonnet | Research during plan mode |133| **General-purpose** | Sonnet | Complex multi-step modifications |134135Use **Explore** for quick searches, **custom agents** for domain expertise.136137---138139## Synthesis Protocol140141After all agents complete, synthesize:142143```markdown144## Orchestration Synthesis145146### Task Summary147148[What was accomplished]149150### Agent Contributions151152| Agent | Finding |153| ------------------ | ------------ |154| security-auditor | Found X |155| backend-specialist | Identified Y |156157### Consolidated Recommendations1581591. **Critical**: [Issue from Agent A]1602. **Important**: [Issue from Agent B]1613. **Nice-to-have**: [Enhancement from Agent C]162163### Action Items164165- [ ] Fix critical security issue166- [ ] Refactor API endpoint167- [ ] Add missing tests168```169170---171172## Best Practices1731741. **Available agents** - 17 specialized agents can be orchestrated1752. **Logical order** - Discovery → Analysis → Implementation → Testing1763. **Share context** - Pass relevant findings to subsequent agents1774. **Single synthesis** - One unified report, not separate outputs1785. **Verify changes** - Always include test-engineer for code modifications179180---181182## Key Benefits183184- ✅ **Single session** - All agents share context185- ✅ **AI-controlled** - Claude orchestrates autonomously186- ✅ **Native integration** - Works with built-in Explore, Plan agents187- ✅ **Resume support** - Can continue previous agent work188- ✅ **Context passing** - Findings flow between agents
yunaamelia