Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills/Git & Pull Requests
wshobson avatar

Team Communication Protocols

wshobson/agents

When you're running a team of agents, they need clear rules about when to ping each other versus blast everyone with a broadcast. This covers the three message types (direct, broadcast, shutdown), plan approval workflows where a lead reviews before an implementer starts coding, and how to gracefully tear down a team when work wraps up. The anti-patterns table is genuinely useful: it'll save you from having agents spam broadcasts for routine updates or accidentally deadlock waiting on each other. Most helpful when you're setting up a new team and need everyone on the same page about coordination, or when debugging why two agents aren't syncing at integration points.

installs
9.7K
GitHub stars
41.8K
last updated
Aug 21, 2026
View on GitHubSave

Install

$ npx -y skills add wshobson/agents --skill team-communication-protocols --agent claude-code

Installs into .claude/skills of the current project.

Files

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
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/wshobson/agents
Categories
Git & Pull Requests, Code Review & Quality, AI & Agent Building, Debugging, Productivity & Planning, Sales & Marketing

More from wshobson/agents

All 174
  • Team Composition Patterns9.7K
  • Evaluation Methodology7.3K
  • Hads6.6K
  • Block No Verify Hook6.6K
  • Signed Audit Trails Recipe6.3K
  • Protect Mcp Setup6K
  • Review Agent Setup5.3K
  • Scan4.7K
  • Recsys Pipeline Architect4.3K
  • Social Publishing3.7K
  • Before You Build3.2K
  • File Conversion3.1K
  • Ai Debt Detector3K
  • Session Guard2.9K
  • Dataset Curation2.7K
  • Eval Harness First2.7K
  • Lora Qlora Recipes2.7K
  • Finetuning Method Selection2.7K
  • Preference Optimization2.7K
  • Quantized Export2.6K
  • Checkpoint Promotion2.6K
  • Grpo Rlvr Training2.6K
  • Trace To Training Data2.6K
  • Pptx Reference Deck Analysis2.6K

Recommended

More Git & Pull Requests
1wshobson avatarteam-composition-patternswshobson/agentsDesign optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding how many agents to 9.7Kinstalls
2google-gemini avatarcode-reviewergoogle-gemini/gemini-cliUse this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maint9.7Kinstalls
3mcp-use avatarmcp-buildermcp-use/mcp-useBuild, modify, debug, or review TypeScript MCP servers with mcp-use.9.6Kinstalls
4aws avataraws-cdkaws/agent-toolkit-for-awsAuthors, deploys, and troubleshoots AWS infrastructure using CDK with TypeScript or Python. Covers best practices, stack architecture, and construct patterns. A9.5Kinstalls
5mcp-use avatarchatgpt-app-buildermcp-use/mcp-useBuild, modify, debug, or review ChatGPT Apps with mcp-use.9.4Kinstalls
6phuryn avatarstrategy-red-teamphuryn/pm-skillsRed-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by im9.3Kinstalls