Parallel Agents

1---
2name: parallel-agents
3description: 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, Grep
5---
6 
7# Native Parallel Agents
8 
9> Orchestration through Claude Code's built-in Agent Tool
10 
11## Overview
12 
13This 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.
14 
15## When to Use Orchestration
16 
17✅ **Good for:**
18- Complex tasks requiring multiple expertise domains
19- Code analysis from security, performance, and quality perspectives
20- Comprehensive reviews (architecture + security + testing)
21- Feature implementation needing backend + frontend + database work
22 
23❌ **Not for:**
24- Simple, single-domain tasks
25- Quick fixes or small changes
26- Tasks where one agent suffices
27 
28---
29 
30## Native Agent Invocation
31 
32### Single Agent
33```
34Use the security-auditor agent to review authentication
35```
36 
37### Sequential Chain
38```
39First, use the explorer-agent to discover project structure.
40Then, use the backend-specialist to review API endpoints.
41Finally, use the test-engineer to identify test gaps.
42```
43 
44### With Context Passing
45```
46Use the frontend-specialist to analyze React components.
47Based on those findings, have the test-engineer generate component tests.
48```
49 
50### Resume Previous Work
51```
52Resume agent [agentId] and continue with additional requirements.
53```
54 
55---
56 
57## Orchestration Patterns
58 
59### Pattern 1: Comprehensive Analysis
60```
61Agents: explorer-agent → [domain-agents] → synthesis
62 
631. explorer-agent: Map codebase structure
642. security-auditor: Security posture
653. backend-specialist: API quality
664. frontend-specialist: UI/UX patterns
675. test-engineer: Test coverage
686. Synthesize all findings
69```
70 
71### Pattern 2: Feature Review
72```
73Agents: affected-domain-agents → test-engineer
74 
751. Identify affected domains (backend? frontend? both?)
762. Invoke relevant domain agents
773. test-engineer verifies changes
784. Synthesize recommendations
79```
80 
81### Pattern 3: Security Audit
82```
83Agents: security-auditor → penetration-tester → synthesis
84 
851. security-auditor: Configuration and code review
862. penetration-tester: Active vulnerability testing
873. Synthesize with prioritized remediation
88```
89 
90---
91 
92## Available Agents
93 
94| Agent | Expertise | Trigger Phrases |
95|-------|-----------|-----------------|
96| `orchestrator` | Coordination | "comprehensive", "multi-perspective" |
97| `security-auditor` | Security | "security", "auth", "vulnerabilities" |
98| `penetration-tester` | Security Testing | "pentest", "red team", "exploit" |
99| `backend-specialist` | Backend | "API", "server", "Node.js", "Express" |
100| `frontend-specialist` | Frontend | "React", "UI", "components", "Next.js" |
101| `test-engineer` | Testing | "tests", "coverage", "TDD" |
102| `devops-engineer` | DevOps | "deploy", "CI/CD", "infrastructure" |
103| `database-architect` | Database | "schema", "Prisma", "migrations" |
104| `mobile-developer` | Mobile | "React Native", "Flutter", "mobile" |
105| `api-designer` | API Design | "REST", "GraphQL", "OpenAPI" |
106| `debugger` | Debugging | "bug", "error", "not working" |
107| `explorer-agent` | Discovery | "explore", "map", "structure" |
108| `documentation-writer` | Documentation | "write docs", "create README", "generate API docs" |
109| `performance-optimizer` | Performance | "slow", "optimize", "profiling" |
110| `project-planner` | Planning | "plan", "roadmap", "milestones" |
111| `seo-specialist` | SEO | "SEO", "meta tags", "search ranking" |
112| `game-developer` | Game Development | "game", "Unity", "Godot", "Phaser" |
113 
114---
115 
116## Claude Code Built-in Agents
117 
118These work alongside custom agents:
119 
120| Agent | Model | Purpose |
121|-------|-------|---------|
122| **Explore** | Haiku | Fast read-only codebase search |
123| **Plan** | Sonnet | Research during plan mode |
124| **General-purpose** | Sonnet | Complex multi-step modifications |
125 
126Use **Explore** for quick searches, **custom agents** for domain expertise.
127 
128---
129 
130## Synthesis Protocol
131 
132After all agents complete, synthesize:
133 
134```markdown
135## Orchestration Synthesis
136 
137### Task Summary
138[What was accomplished]
139 
140### Agent Contributions
141| Agent | Finding |
142|-------|---------|
143| security-auditor | Found X |
144| backend-specialist | Identified Y |
145 
146### Consolidated Recommendations
1471. **Critical**: [Issue from Agent A]
1482. **Important**: [Issue from Agent B]
1493. **Nice-to-have**: [Enhancement from Agent C]
150 
151### Action Items
152- [ ] Fix critical security issue
153- [ ] Refactor API endpoint
154- [ ] Add missing tests
155```
156 
157---
158 
159## Best Practices
160 
1611. **Available agents** - 17 specialized agents can be orchestrated
1622. **Logical order** - Discovery → Analysis → Implementation → Testing
1633. **Share context** - Pass relevant findings to subsequent agents
1644. **Single synthesis** - One unified report, not separate outputs
1655. **Verify changes** - Always include test-engineer for code modifications
166 
167---
168 
169## Key Benefits
170 
171- ✅ **Single session** - All agents share context
172- ✅ **AI-controlled** - Claude orchestrates autonomously
173- ✅ **Native integration** - Works with built-in Explore, Plan agents
174- ✅ **Resume support** - Can continue previous agent work
175- ✅ **Context passing** - Findings flow between agents
176