/orchestrate - Multi-Agent Coordination
$ARGUMENTS
MANDATORY: You MUST use the Agent tool
DO NOT analyze or implement this task yourself. Your only job is to decompose the task and invoke specialized agents via the Agent tool. If you attempt to do the work inline, you have failed.
Step 1 — Decompose
Analyze the task and identify 3–6 sub-domains (e.g. backend, frontend, security, testing, docs). Define clear file ownership per domain so agents don't conflict.
Present the decomposition to the user and wait for approval before Step 2.
Step 2 — Spawn agents in parallel (REQUIRED)
Call the Agent tool multiple times in a single response — one call per sub-domain. All independent agents MUST be launched in the same message to run in parallel.
Example for a feature implementation task:
Agent(subagent_type="backend-specialist", prompt="...", ...)
Agent(subagent_type="frontend-specialist", prompt="...", ...)
Agent(subagent_type="test-engineer", prompt="...", ...)
Agent(subagent_type="security-auditor", prompt="...", ...)
Each agent prompt MUST include:
- The original user task
- The specific sub-task this agent owns
- File paths this agent is allowed to modify
- Success criteria for this agent's work
Step 3 — Synthesize
After all agents complete, generate the Orchestration Report combining their findings.
Available Agents
| Agent |
Domain |
backend-specialist |
API, server logic, databases |
frontend-specialist |
React, Vue, UI components |
test-engineer |
Unit, integration, E2E tests |
security-auditor |
OWASP, vulnerabilities, auth |
database-architect |
Schema, migrations, queries |
devops-implementer |
Docker, CI/CD, infra |
performance-optimizer |
Profiling, bottlenecks |
documenter |
KB, architecture notes, runbooks |
code-reviewer |
Code quality, patterns |
tech-lead |
Architecture, standards |
Output Format
## Orchestration Report
### Task
[Original task]
### Agents Invoked
| # | Agent | Sub-task | Files | Status |
|---|-------|----------|-------|--------|
| 1 | backend-specialist | API layer | src/api/ | Done |
| 2 | frontend-specialist | UI components | src/components/ | Done |
| 3 | test-engineer | Test suite | tests/ | Done |
### Key Findings
1. **[Agent]**: Finding
2. **[Agent]**: Finding
### Summary
[Synthesis]
1---2name: orchestrate3description: "Coordinates multiple specialized agents in parallel. Triggers: orchestrate, multi-agent, parallel agents, coordinate agents."4user-invocable: true5effort: max6argument-hint: "[task]"7context: fork8agent: orchestrator9model: opus10allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, TeamCreate, TeamDelete, SendMessage, TaskCreate, TaskList, TaskUpdate, TaskGet, TaskOutput, TaskStop11---1213# /orchestrate - Multi-Agent Coordination1415$ARGUMENTS1617## MANDATORY: You MUST use the Agent tool1819**DO NOT analyze or implement this task yourself.** Your only job is to decompose the task and invoke specialized agents via the `Agent` tool. If you attempt to do the work inline, you have failed.2021## Step 1 — Decompose2223Analyze the task and identify 3–6 sub-domains (e.g. backend, frontend, security, testing, docs). Define clear file ownership per domain so agents don't conflict.2425Present the decomposition to the user and wait for approval before Step 2.2627## Step 2 — Spawn agents in parallel (REQUIRED)2829Call the `Agent` tool **multiple times in a single response** — one call per sub-domain. All independent agents MUST be launched in the same message to run in parallel.3031Example for a feature implementation task:3233```34Agent(subagent_type="backend-specialist", prompt="...", ...)35Agent(subagent_type="frontend-specialist", prompt="...", ...)36Agent(subagent_type="test-engineer", prompt="...", ...)37Agent(subagent_type="security-auditor", prompt="...", ...)38```3940Each agent prompt MUST include:411. The original user task422. The specific sub-task this agent owns433. File paths this agent is allowed to modify444. Success criteria for this agent's work4546## Step 3 — Synthesize4748After all agents complete, generate the Orchestration Report combining their findings.4950## Available Agents5152| Agent | Domain |53|-------|--------|54| `backend-specialist` | API, server logic, databases |55| `frontend-specialist` | React, Vue, UI components |56| `test-engineer` | Unit, integration, E2E tests |57| `security-auditor` | OWASP, vulnerabilities, auth |58| `database-architect` | Schema, migrations, queries |59| `devops-implementer` | Docker, CI/CD, infra |60| `performance-optimizer` | Profiling, bottlenecks |61| `documenter` | KB, architecture notes, runbooks |62| `code-reviewer` | Code quality, patterns |63| `tech-lead` | Architecture, standards |6465## Output Format6667```markdown68## Orchestration Report6970### Task71[Original task]7273### Agents Invoked74| # | Agent | Sub-task | Files | Status |75|---|-------|----------|-------|--------|76| 1 | backend-specialist | API layer | src/api/ | Done |77| 2 | frontend-specialist | UI components | src/components/ | Done |78| 3 | test-engineer | Test suite | tests/ | Done |7980### Key Findings811. **[Agent]**: Finding822. **[Agent]**: Finding8384### Summary85[Synthesis]86```
softspark