Skip to main content

​
Convoy Commands

Orchestrate multiple agents working in parallel on related tasks.

​
Overview

Convoys enable running multiple AI agents in parallel, combining their specialized expertise to tackle complex tasks more effectively. See the Convoys feature guide for conceptual overview.

​
pan convoy start

Start a new convoy with a specific template: 
# Run a parallel code review
pan convoy start code-review --files "src/**/*.ts"

# Use with pull request
pan convoy start code-review --pr-url https://github.com/org/repo/pull/123

# Target specific issue
pan convoy start code-review --issue-id MIN-123

# Specify project path
pan convoy start code-review --files "src/**/*.ts" --project-path /path/to/project
Options:
  • --files <pattern> - File pattern to analyze (e.g., “src/**/*.ts”)
  • --pr-url <url> - Pull request URL to review
  • --issue-id <id> - Issue ID to associate with convoy
  • --project-path <path> - Project path (defaults to current directory)

​
pan convoy status

Check the status of a running convoy: 
# Show most recent convoy status
pan convoy status

# Check specific convoy
pan convoy status <convoy-id>
The status command shows:
  • Overall convoy state (running, completed, failed)
  • Individual agent progress
  • Phase completion (e.g., parallel review phase vs synthesis phase)
  • Output files generated

​
pan convoy list

List all convoys (running and completed): 
# List all convoys
pan convoy list

# Filter by status
pan convoy list --status running
pan convoy list --status completed
pan convoy list --status failed

​
pan convoy stop

Stop a running convoy: 
pan convoy stop <convoy-id>
This will:
  1. Kill all running agents in the convoy
  2. Mark the convoy as failed
  3. Preserve any output generated so far

​
Built-in Convoy Templates

TemplateAgentsUse Case
code-reviewcorrectness, security, performance, synthesisComprehensive code review
planningplannerCodebase exploration and planning
triage(dynamic)Parallel issue triage
health-monitormonitorCheck health of running agents

​
code-review Template

The code-review convoy uses specialized agents for parallel review: Phase 1 - Specialized Reviews (Parallel)
  • Correctness (Haiku) - Logic errors, edge cases, type safety
  • Security (Sonnet) - OWASP Top 10, injection, XSS, auth issues
  • Performance (Haiku) - N+1 queries, blocking ops, memory leaks
Phase 2 - Synthesis (Sequential)
  • Reads all three review files
  • Removes duplicates (same issue found by multiple reviewers)
  • Prioritizes findings (blocker → critical → high → medium → low)
  • Generates unified report with action items
Output files:
  • .claude/reviews/<timestamp>-correctness.md
  • .claude/reviews/<timestamp>-security.md
  • .claude/reviews/<timestamp>-performance.md
  • .claude/reviews/<timestamp>-synthesis.md

​
Custom Convoy Templates

Create custom templates in ~/.panopticon/convoy-templates/: 
{
  "name": "lightweight-review",
  "description": "Quick security-only review",
  "agents": [
    {
      "role": "security",
      "subagent": "code-review-security",
      "parallel": false
    }
  ],
  "config": {
    "outputDir": ".claude/reviews",
    "timeout": 600000
  }
}
Then use with: 
pan convoy start lightweight-review --files "src/**/*.ts"

​
Convoy Execution Flow

pan convoy start code-review --files "src/**/*.ts"
    │
    ├─→ Phase 1 (Parallel): 3 specialized reviewers run simultaneously
    │     ├─→ Correctness (Haiku) → correctness.md
    │     ├─→ Security (Sonnet)    → security.md
    │     └─→ Performance (Haiku)  → performance.md
    │
    └─→ Phase 2 (Sequential): Synthesis agent runs after Phase 1 completes
          └─→ Synthesis reads all 3 reviews → synthesis.md