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.
When several convoys (and ordinary work agents) run at once, the dashboard’s God View gives you a single aggregate, cross-project picture of every active agent — so the conversations and the workflow stay observable side by side.
Use pan convoy status and pan convoy list for a per-convoy CLI view; reach for God View in the dashboard when you want to watch every parallel agent across all projects at a glance.
pan convoy start
Start a new convoy with a specific template:
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:
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):
pan convoy stop
Stop a running convoy:
This will:
- Kill all running agents in the convoy
- Mark the convoy as failed
- Preserve any output generated so far
Built-in Convoy Templates
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 ~/.overdeck/convoy-templates/:
Then use with:
Convoy Execution Flow