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.4---56# Native Parallel Agents78> Orchestration through Claude Code's built-in Agent Tool910## Overview1112This 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.1314## When to Use Orchestration1516✅ **Good for:**1718- Complex tasks requiring multiple expertise domains19- Code analysis from security, performance, and quality perspectives20- Comprehensive reviews (architecture + security + testing)21- Feature implementation needing backend + frontend + database work2223❌ **Not for:**2425- Simple, single-domain tasks26- Quick fixes or small changes27- Tasks where one agent suffices2829---3031## Native Agent Invocation3233### Single Agent3435```36Use the security-auditor agent to review authentication37```3839### Sequential Chain4041```42First, use the explorer-agent to discover project structure.43Then, use the backend-specialist to review API endpoints.44Finally, use the test-engineer to identify test gaps.45```4647### With Context Passing4849```50Use the frontend-specialist to analyze React components.51Based on those findings, have the test-engineer generate component tests.52```5354### Resume Previous Work5556```57Resume agent [agentId] and continue with additional requirements.58```5960---6162## Orchestration Patterns6364### Pattern 1: Comprehensive Analysis6566```67Agents: explorer-agent → [domain-agents] → synthesis68691. explorer-agent: Map codebase structure702. security-auditor: Security posture713. backend-specialist: API quality724. frontend-specialist: UI/UX patterns735. test-engineer: Test coverage746. Synthesize all findings75```7677### Pattern 2: Feature Review7879```80Agents: affected-domain-agents → test-engineer81821. Identify affected domains (backend? frontend? both?)832. Invoke relevant domain agents843. test-engineer verifies changes854. Synthesize recommendations86```8788### Pattern 3: Security Audit8990```91Agents: security-auditor → penetration-tester → synthesis92931. security-auditor: Configuration and code review942. penetration-tester: Active vulnerability testing953. Synthesize with prioritized remediation96```9798---99100## Available Agents101102| Agent | Expertise | Trigger Phrases |103| ----------------------- | ---------------- | -------------------------------------------------- |104| `orchestrator` | Coordination | "comprehensive", "multi-perspective" |105| `security-auditor` | Security | "security", "auth", "vulnerabilities" |106| `penetration-tester` | Security Testing | "pentest", "red team", "exploit" |107| `backend-specialist` | Backend | "API", "server", "Node.js", "Express" |108| `frontend-specialist` | Frontend | "React", "UI", "components", "Next.js" |109| `test-engineer` | Testing | "tests", "coverage", "TDD" |110| `devops-engineer` | DevOps | "deploy", "CI/CD", "infrastructure" |111| `database-architect` | Database | "schema", "Prisma", "migrations" |112| `mobile-developer` | Mobile | "React Native", "Flutter", "mobile" |113| `api-designer` | API Design | "REST", "GraphQL", "OpenAPI" |114| `debugger` | Debugging | "bug", "error", "not working" |115| `explorer-agent` | Discovery | "explore", "map", "structure" |116| `documentation-writer` | Documentation | "write docs", "create README", "generate API docs" |117| `performance-optimizer` | Performance | "slow", "optimize", "profiling" |118| `project-planner` | Planning | "plan", "roadmap", "milestones" |119| `seo-specialist` | SEO | "SEO", "meta tags", "search ranking" |120| `game-developer` | Game Development | "game", "Unity", "Godot", "Phaser" |121122---123124## Claude Code Built-in Agents125126These work alongside custom agents:127128| Agent | Model | Purpose |129| ------------------- | ------ | -------------------------------- |130| **Explore** | Haiku | Fast read-only codebase search |131| **Plan** | Sonnet | Research during plan mode |132| **General-purpose** | Sonnet | Complex multi-step modifications |133134Use **Explore** for quick searches, **custom agents** for domain expertise.135136---137138## Synthesis Protocol139140After all agents complete, synthesize:141142```markdown143## Orchestration Synthesis144145### Task Summary146147[What was accomplished]148149### Agent Contributions150151| Agent | Finding |152| ------------------ | ------------ |153| security-auditor | Found X |154| backend-specialist | Identified Y |155156### Consolidated Recommendations1571581. **Critical**: [Issue from Agent A]1592. **Important**: [Issue from Agent B]1603. **Nice-to-have**: [Enhancement from Agent C]161162### Action Items163164- [ ] Fix critical security issue165- [ ] Refactor API endpoint166- [ ] Add missing tests167```168169---170171## Best Practices1721731. **Available agents** - 17 specialized agents can be orchestrated1742. **Logical order** - Discovery → Analysis → Implementation → Testing1753. **Share context** - Pass relevant findings to subsequent agents1764. **Single synthesis** - One unified report, not separate outputs1775. **Verify changes** - Always include test-engineer for code modifications178179---180181## Key Benefits182183- ✅ **Single session** - All agents share context184- ✅ **AI-controlled** - Claude orchestrates autonomously185- ✅ **Native integration** - Works with built-in Explore, Plan agents186- ✅ **Resume support** - Can continue previous agent work187- ✅ **Context passing** - Findings flow between agents
yunaamelia