PluginBench
Skill
Pass
Audit score 90

team-communication-protocols

wshobson/agents

Structured messaging protocols for coordinating agent teams: direct messages, broadcasts, plan approval, and graceful shutdown.

What is team-communication-protocols?

Defines communication patterns for agent teams including message type selection (direct message vs. broadcast), plan approval workflows where leads review implementer plans before execution, graceful shutdown procedures, and anti-patterns to avoid. Use this when establishing communication norms for a new team, coordinating between teammates at integration points, or debugging coordination failures.

  • Choose appropriate message types: direct messages for point-to-point coordination, broadcasts only for critical shared-resource changes
  • Implement plan approval workflows where team leads review and approve implementer plans before work begins
  • Execute graceful team shutdown with rejection handling and state preservation
  • Discover teammate identities and capabilities from team config files
  • Identify and avoid communication anti-patterns like broadcasting routine updates, micromanaging, or ignoring idle teammates
  • Troubleshoot coordination failures and deadlocks between teammates

How to install team-communication-protocols

npx skills add https://github.com/wshobson/agents --skill team-communication-protocols
Claude Code
Cursor
Windsurf
Cline

How to use team-communication-protocols

  1. 1.Read the team config file at ~/.claude/teams/{team-name}/config.json to discover teammate names and capabilities
  2. 2.Choose the appropriate message type: use 'message' for direct point-to-point updates, reserve 'broadcast' only for critical shared-resource changes
  3. 3.For plan approval workflows, have the implementer call ExitPlanMode to send a plan_approval_request, then respond with plan_approval_response (approve: true/false)
  4. 4.When shutting down, send shutdown_request to each teammate and handle rejections by waiting for work to complete before retrying
  5. 5.Always use teammate names (not UUIDs or unsuffixed aliases) when sending messages or assigning tasks
  6. 6.Monitor for anti-patterns like broadcasting routine updates, sending JSON status messages, or micromanaging via messages

Use cases

Good for
  • Establishing communication norms when spawning a new agent team
  • Deciding whether to send a direct message to one teammate or broadcast to all
  • Handling a team-lead's review and approval of an implementer's plan before execution begins
  • Orchestrating graceful shutdown after all tasks complete, including handling rejections
  • Debugging why teammates are not coordinating correctly at integration points
Who it's for
  • Team leads orchestrating multi-agent workflows
  • Implementer agents coordinating with peers on shared tasks
  • Reviewers approving plans before execution
  • Anyone establishing communication norms for newly spawned agent teams

team-communication-protocols FAQ

When should I use broadcast vs. direct message?

Use direct messages (type: 'message') for routine updates, task coordination, and questions to specific teammates. Use broadcast only for critical blockers affecting everyone or major changes to shared resources. Each broadcast sends N separate messages, so use sparingly to avoid wasting API resources.

How do I handle a teammate rejecting a shutdown request?

Check the rejection reason in the shutdown_response content field. The teammate is usually still working on a task. Wait for the current task to complete, then retry the shutdown request. Never force-terminate a teammate with unsaved work.

What should I do if two teammates are deadlocked waiting on each other?

Send a direct message to one teammate with a stub or partial result to unblock it, allowing it to proceed. This breaks the circular dependency and lets work resume.

How do I discover what teammates are in my team and what they can do?

Read the config file at ~/.claude/teams/{team-name}/config.json. It contains a 'members' array with each teammate's name, agentId, and agentType. Always use the 'name' field for messaging and task assignment, never the agentId or role name.

Why is a teammate not responding to my messages?

Check the teammate's task status. If idle, it may have completed its task and is waiting for new work or shutdown. If still active, it may be mid-execution and will process messages once the current operation finishes. Verify the teammate's tools list includes SendMessage, TaskList, TaskGet, and TaskUpdate.

Full instructions (SKILL.md)

Source of truth, from wshobson/agents.


name: team-communication-protocols description: Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing communication norms for a newly spawned team, when deciding whether to send a direct message or a broadcast, when a team-lead needs to review and approve an implementer's plan before work begins, when orchestrating a graceful team shutdown after all tasks are complete, or when debugging why teammates are not coordinating correctly at integration points. version: 1.0.2

Team 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-PatternProblemBetter Approach
Broadcasting routine updatesWastes resources, noiseDirect message to affected teammate
Sending JSON status messagesNot designed for structured dataUse TaskUpdate to update task status
Not communicating at integration pointsTeammates build against stale interfacesMessage when your interface is ready
Micromanaging via messagesOverwhelms teammates, slows workCheck in at milestones, not every step
Using UUIDs instead of namesHard to read, error-proneAlways use teammate names
Ignoring idle teammatesWasted capacityAssign new work or shut down

Plan Approval Workflow

When a teammate is spawned with plan_mode_required:

  1. Teammate creates a plan using read-only exploration tools
  2. Teammate calls ExitPlanMode which sends a plan_approval_request to the lead
  3. Lead reviews the plan
  4. 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

  1. Lead sends shutdown_request to each teammate
  2. Teammate receives request as a JSON message with type: "shutdown_request"
  3. Teammate responds with shutdown_response:
    • approve: true — Teammate saves state and exits
    • approve: false + reason — Teammate continues working
  4. Lead handles rejections — Wait for teammate to finish, then retry
  5. After all teammates shut down — Call TeamDelete to remove team resources

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, role names, or unsuffixed aliases directly. If a teammate was spawned as team-lead-2, send to team-lead-2, not team-lead.

Troubleshooting

A teammate is not responding to messages. Check the teammate's task status. If it is idle, it may have completed its task and is waiting to be assigned new work or shut down. If it is still active, it may be mid-execution and will process messages once the current operation finishes.

A teammate says it cannot see SendMessage. Check the teammate agent's tools: frontmatter. Agent Teams communication tools such as SendMessage, TaskList, TaskGet, and TaskUpdate must be listed explicitly when an agent uses a restricted tool allowlist.

The lead is sending broadcasts for every status update. This is a common anti-pattern. Broadcasts are expensive — each one sends N messages. Use direct messages (type: "message") for point-to-point updates. Reserve broadcasts for critical shared-resource changes like an updated interface contract.

A teammate rejected a shutdown request unexpectedly. The teammate is still working. Check the rejection reason in the shutdown_response content field, wait for the work to finish, then retry. Never force-terminate a teammate that has unsaved work.

A plan_approval_request arrived but the request_id is missing. The teammate called ExitPlanMode without the required request context. Have the teammate re-enter plan mode, complete exploration, and call ExitPlanMode again. The request_id is generated automatically by the plan mode system.

Two teammates are waiting on each other and neither is making progress. This is a deadlock: both are blocked waiting for the other to finish first. The lead should send a direct message to one teammate with a stub or partial result so it can unblock and proceed.

Related Skills

  • team-composition-patterns — Select agent types and team size before establishing communication norms
  • parallel-feature-development — Use communication protocols to coordinate integration handoffs between parallel implementers