
Team Communication Protocols
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.
- skills.sh installs
- 10K
- GitHub stars
- 42.4K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add wshobson/agents --skill team-communication-protocols --agent claude-codeInstalls 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"
}
Sponsors
Details
More from wshobson/agents
All 174- Team Composition Patterns10K
- Evaluation Methodology7.6K
- Hads6.9K
- Block No Verify Hook6.9K
- Signed Audit Trails Recipe6.7K
- Protect Mcp Setup6.3K
- Review Agent Setup5.6K
- Scan5K
- Recsys Pipeline Architect4.6K
- Social Publishing4K
- Before You Build3.5K
- File Conversion3.4K
- Ai Debt Detector3.4K
- Session Guard3.2K
- Dataset Curation3K
- Eval Harness First3K
- Lora Qlora Recipes3K
- Finetuning Method Selection3K
- Preference Optimization2.9K
- Quantized Export2.9K
- Pptx Reference Deck Analysis2.9K
- Grpo Rlvr Training2.9K
- Checkpoint Promotion2.9K
- Trace To Training Data2.9K