Parallel Agents

​

Overview

​

What This Skill Provides

• Native agent invocation: Using Antigravity’s built-in Agent Tool
• Orchestration patterns: Proven patterns for multi-agent coordination
• Sequential and parallel execution: When to run agents in sequence vs parallel
• Context passing: Sharing findings between agents
• Synthesis protocols: Combining results from multiple agents
• 17 specialized agents: Available agents and their expertise domains

​

When to Use Orchestration

• 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

• 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

​

Antigravity Built-in Agents

​

Synthesis Protocol

## 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

1. Choose relevant agents - 17 specialized agents available
2. Logical order - Discovery → Analysis → Implementation → Testing
3. Share context - Pass relevant findings to subsequent agents
4. Single synthesis - One unified report, not separate outputs
5. 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

​

Use Cases

• Comprehensive codebase analysis
• Multi-domain feature implementation
• Security audits with multiple perspectives
• Full-stack application building
• Code quality reviews from multiple angles
• Performance optimization across layers
• Migration planning and execution

​

Related Skills

• App Builder - Uses agent coordination for building apps
• Intelligent Routing - Automatic agent selection
• Behavioral Modes - Agent behavior adaptation
• Plan Writing - Planning multi-agent work

​

Which Agents Use This Skill

• orchestrator - Primary orchestrator agent that coordinates other agents
• Other agents can invoke specialist agents when needed

​

Sequential vs Parallel Execution

​

Sequential (dependencies)

1. database-architect (must complete first)
   ↓
2. backend-specialist (needs schema)
   ↓
3. frontend-specialist (needs API)
   ↓
4. test-engineer (needs all code)

​

Parallel (independent)

After core implementation:
├─ security-auditor (code review)
├─ performance-optimizer (bundle analysis)
└─ test-engineer (test generation)

[All run simultaneously]

​

Context Passing Techniques

1. Explicit context: “Based on the security findings…”
2. File references: “Review the files identified by explorer-agent”
3. Shared artifacts: Reference files created by previous agents
4. Issue tracking: Pass list of issues to next agent
5. Decision logs: Share architectural decisions

​

Error Handling in Orchestration

• If an agent fails, log error and continue with other agents
• Critical dependencies should block subsequent agents
• Provide partial synthesis even if some agents fail
• Document which agents completed successfully
• Offer to retry failed agents with different parameters