team-communication-protocols
npx machina-cli add skill wshobson/agents/team-communication-protocols --openclawTeam Communication Protocols
Protocols for effective communication between agent teammates, including message type selection, plan approval workflows, shutdown procedures, and common anti-patterns to avoid.
When to Use This Skill
- Establishing communication norms for a new team
- Choosing between message types (message, broadcast, shutdown_request)
- Handling plan approval workflows
- Managing graceful team shutdown
- Discovering teammate identities and capabilities
Message Type Selection
message (Direct Message) — Default Choice
Send to a single specific teammate:
{
"type": "message",
"recipient": "implementer-1",
"content": "Your API endpoint is ready. You can now build the frontend form.",
"summary": "API endpoint ready for frontend"
}
Use for: Task updates, coordination, questions, integration notifications.
broadcast — Use Sparingly
Send to ALL teammates simultaneously:
{
"type": "broadcast",
"content": "Critical: shared types file has been updated. Pull latest before continuing.",
"summary": "Shared types updated"
}
Use ONLY for: Critical blockers affecting everyone, major changes to shared resources.
Why sparingly?: Each broadcast sends N separate messages (one per teammate), consuming API resources proportional to team size.
shutdown_request — Graceful Termination
Request a teammate to shut down:
{
"type": "shutdown_request",
"recipient": "reviewer-1",
"content": "Review complete, shutting down team."
}
The teammate responds with shutdown_response (approve or reject with reason).
Communication Anti-Patterns
| Anti-Pattern | Problem | Better Approach |
|---|---|---|
| Broadcasting routine updates | Wastes resources, noise | Direct message to affected teammate |
| Sending JSON status messages | Not designed for structured data | Use TaskUpdate to update task status |
| Not communicating at integration points | Teammates build against stale interfaces | Message when your interface is ready |
| Micromanaging via messages | Overwhelms teammates, slows work | Check in at milestones, not every step |
| Using UUIDs instead of names | Hard to read, error-prone | Always use teammate names |
| Ignoring idle teammates | Wasted capacity | Assign new work or shut down |
Plan Approval Workflow
When a teammate is spawned with plan_mode_required:
- Teammate creates a plan using read-only exploration tools
- Teammate calls
ExitPlanModewhich sends aplan_approval_requestto the lead - Lead reviews the plan
- Lead responds with
plan_approval_response:
Approve:
{
"type": "plan_approval_response",
"request_id": "abc-123",
"recipient": "implementer-1",
"approve": true
}
Reject with feedback:
{
"type": "plan_approval_response",
"request_id": "abc-123",
"recipient": "implementer-1",
"approve": false,
"content": "Please add error handling for the API calls"
}
Shutdown Protocol
Graceful Shutdown Sequence
- Lead sends shutdown_request to each teammate
- Teammate receives request as a JSON message with
type: "shutdown_request" - Teammate responds with
shutdown_response:approve: true— Teammate saves state and exitsapprove: false+ reason — Teammate continues working
- Lead handles rejections — Wait for teammate to finish, then retry
- After all teammates shut down — Call
Teammatecleanup
Handling Rejections
If a teammate rejects shutdown:
- Check their reason (usually "still working on task")
- Wait for their current task to complete
- Retry shutdown request
- If urgent, user can force shutdown
Teammate Discovery
Find team members by reading the config file:
Location: ~/.claude/teams/{team-name}/config.json
Structure:
{
"members": [
{
"name": "security-reviewer",
"agentId": "uuid-here",
"agentType": "team-reviewer"
},
{
"name": "perf-reviewer",
"agentId": "uuid-here",
"agentType": "team-reviewer"
}
]
}
Always use name for messaging and task assignment. Never use agentId directly.
Source
git clone https://github.com/wshobson/agents/blob/main/plugins/agent-teams/skills/team-communication-protocols/SKILL.mdView on GitHub Overview
Defines structured message types and workflows for agent teams, including direct messages, broadcasts, shutdown requests, and plan approval. It also prescribes graceful shutdown procedures to standardize collaboration and reduce miscommunication.
How This Skill Works
Teams select appropriate message types (message, broadcast, shutdown_request) for tasks and updates. When a plan is needed, a teammate uses ExitPlanMode to trigger a plan_approval_request, and the lead returns a plan_approval_response with approval or feedback.
When to Use It
- Establishing communication norms for a new team
- Choosing between message types (message, broadcast, shutdown_request)
- Handling plan approval workflows
- Managing graceful team shutdown
- Discovering teammate identities and capabilities
Quick Start
- Step 1: Define and document the team’s default message-type policy (message, broadcast, shutdown_request)
- Step 2: When planning work, trigger the plan workflow by ExitPlanMode and sending plan_approval_request to the lead, then await plan_approval_response
- Step 3: For shutdown, the lead sends shutdown_request to teammates and each teammate responds with shutdown_response (approve to save state and exit, or reject with a reason)
Best Practices
- Define a default messaging policy per scenario to minimize confusion
- Use message types appropriately: direct messages for routine updates, broadcasts only for critical blockers
- Use plan_approval_request / plan_approval_response to validate plans before execution
- Prefer graceful shutdown via shutdown_request followed by shutdown_response
- Always reference teammate names and ensure interfaces are ready before integration
Example Use Cases
- A new team establishes norms by documenting when to use message vs. broadcast and how to handle shutdowns
- A teammate uses ExitPlanMode to create a plan and sends plan_approval_request to the lead for review
- The lead replies with plan_approval_response, approving the plan or providing feedback
- A teammate initiates a graceful shutdown by sending shutdown_request and the recipient responds with shutdown_response
- Status updates are sent via direct messages rather than broadcasting routine progress to all teammates