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---5
6# Native Parallel Agents
7
8> Orchestration through Claude Code's built-in Agent Tool
9
10## Overview
11
12This 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.
13
14## When to Use Orchestration
15
16✅ **Good for:**
17- Complex tasks requiring multiple expertise domains
18- Code analysis from security, performance, and quality perspectives
19- Comprehensive reviews (architecture + security + testing)
20- Feature implementation needing backend + frontend + database work
21
22❌ **Not for:**
23- Simple, single-domain tasks
24- Quick fixes or small changes
25- Tasks where one agent suffices
26
27---
28
29## Native Agent Invocation
30
31### Single Agent
32```
33Use the security-auditor agent to review authentication
34```
35
36### Sequential Chain
37```
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```
42
43### With Context Passing
44```
45Use the frontend-specialist to analyze React components.
46Based on those findings, have the test-engineer generate component tests.
47```
48
49### Resume Previous Work
50```
51Resume agent [agentId] and continue with additional requirements.
52```
53
54---
55
56## Orchestration Patterns
57
58### Pattern 1: Comprehensive Analysis
59```
60Agents: explorer-agent → [domain-agents] → synthesis
61
621. explorer-agent: Map codebase structure
632. security-auditor: Security posture
643. backend-specialist: API quality
654. frontend-specialist: UI/UX patterns
665. test-engineer: Test coverage
676. Synthesize all findings
68```
69
70### Pattern 2: Feature Review
71```
72Agents: affected-domain-agents → test-engineer
73
741. Identify affected domains (backend? frontend? both?)
752. Invoke relevant domain agents
763. test-engineer verifies changes
774. Synthesize recommendations
78```
79
80### Pattern 3: Security Audit
81```
82Agents: security-auditor → penetration-tester → synthesis
83
841. security-auditor: Configuration and code review
852. penetration-tester: Active vulnerability testing
863. Synthesize with prioritized remediation
87```
88
89---
90
91## Available Agents
92
93| Agent | Expertise | Trigger Phrases |
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` | Database | "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` | Documentation | "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 Development | "game", "Unity", "Godot", "Phaser" |
112
113---
114
115## Claude Code Built-in Agents
116
117These work alongside custom agents:
118
119| Agent | Model | Purpose |
120|-------|-------|---------|
121| **Explore** | Haiku | Fast read-only codebase search |
122| **Plan** | Sonnet | Research during plan mode |
123| **General-purpose** | Sonnet | Complex multi-step modifications |
124
125Use **Explore** for quick searches, **custom agents** for domain expertise.
126
127---
128
129## Synthesis Protocol
130
131After all agents complete, synthesize:
132
133```markdown
134## Orchestration Synthesis
135
136### Task Summary
137[What was accomplished]
138
139### Agent Contributions
140| Agent | Finding |
141|-------|---------|
142| security-auditor | Found X |
143| backend-specialist | Identified Y |
144
145### Consolidated Recommendations
1461. **Critical**: [Issue from Agent A]
1472. **Important**: [Issue from Agent B]
1483. **Nice-to-have**: [Enhancement from Agent C]
149
150### Action Items
151- [ ] Fix critical security issue
152- [ ] Refactor API endpoint
153- [ ] Add missing tests
154```
155
156---
157
158## Best Practices
159
1601. **Available agents** - 17 specialized agents can be orchestrated
1612. **Logical order** - Discovery → Analysis → Implementation → Testing
1623. **Share context** - Pass relevant findings to subsequent agents
1634. **Single synthesis** - One unified report, not separate outputs
1645. **Verify changes** - Always include test-engineer for code modifications
165
166---
167
168## Key Benefits
169
170- ✅ **Single session** - All agents share context
171- ✅ **AI-controlled** - Claude orchestrates autonomously
172- ✅ **Native integration** - Works with built-in Explore, Plan agents
173- ✅ **Resume support** - Can continue previous agent work
174- ✅ **Context passing** - Findings flow between agents
kursku