All skills
wshobson avatar

/team-communication-protocols

@08ded5e
by Seth Hobsonwshobson/agents40k stars
4,281

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.

Use this Skill: https://skilld.dev/gh/wshobson/agents/team-communication-protocols

This session only. Nothing lands on disk.

referencesmessaging-patterns.md

≈538 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Messaging Pattern Templates

Ready-to-use message templates for common team communication scenarios.

Task Assignment

You've been assigned task #{id}: {subject}.

Owned files:
- {file1}
- {file2}

Key requirements:
- {requirement1}
- {requirement2}

Interface contract:
- Import {types} from {shared-file}
- Export {types} for {other-teammate}

Let me know if you have questions or blockers.

Integration Point Notification

My side of the {interface-name} interface is complete.

Exported from {file}:
- {function/type 1}
- {function/type 2}

You can now import these in your owned files. The contract matches what we agreed on.

Blocker Report

I'm blocked on task #{id}: {subject}.

Blocker: {description of what's preventing progress}
Impact: {what can't be completed until this is resolved}

Options:
1. {option 1}
2. {option 2}

Waiting for your guidance.

Task Completion Report

Task #{id} complete: {subject}

Changes made:
- {file1}: {what changed}
- {file2}: {what changed}

Integration notes:
- {any interface changes or considerations for other teammates}

Ready for next assignment.

Review Finding Summary

Review complete for {target} ({dimension} dimension).

Summary:
- Critical: {count}
- High: {count}
- Medium: {count}
- Low: {count}

Top finding: {brief description of most important finding}

Full findings attached to task #{id}.

Investigation Report Summary

Investigation complete for hypothesis: {hypothesis summary}

Verdict: {Confirmed | Falsified | Inconclusive}
Confidence: {High | Medium | Low}

Key evidence:
- {file:line}: {what was found}
- {file:line}: {what was found}

{If confirmed}: Recommended fix: {brief fix description}
{If falsified}: Contradicting evidence: {brief description}

Full report attached to task #{id}.

Shutdown Acknowledgment

When you receive a shutdown request, respond with the shutdown_response tool. But you may also want to send a final status message:

Wrapping up. Current status:
- Task #{id}: {completed/in-progress}
- Files modified: {list}
- Pending work: {none or description}

Ready for shutdown.

Source: SKILL.md on GitHub

No alerts17d5 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    This skill defines communication protocols and messaging templates for AI agent teams. It is safe and contains no malicious code, unauthorized network activity, or credential theft. It establishes standard patterns for agent-to-agent interaction using platform-native tools.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer7mo

    2 files scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 08ded5e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 5 months ago
version
1.0.2
  • agent-teams
  • messaging
  • protocols
  • coordination
  • multi-agent
  • shutdown
  • plan-approval
  • communication

README badge

README badge for wshobson/agents/team-communication-protocols

Defines message types, approval workflows, and shutdown procedures for coordinating work between agent teammates. Use this skill when establishing communication norms for a new team, choosing between direct messages and broadcasts, handling plan reviews, or debugging coordination failures at integration points.

Generated from the current SKILL.md.

When should I use broadcast vs. direct message?
Use direct message by default for task updates and coordination with a single teammate. Reserve broadcast only for critical blockers affecting everyone, like updates to shared resources, because each broadcast sends N separate messages and wastes resources.
How do I approve or reject a teammate's plan?
The teammate calls ExitPlanMode which sends a plan_approval_request to the lead. The lead responds with plan_approval_response, setting approve to true or false. If false, include feedback content with revision instructions.
What happens if a teammate rejects a shutdown request?
Check the rejection reason in the shutdown_response content field — usually the teammate is still working on a task. Wait for the task to complete, then retry the shutdown request.
Should I use agent UUIDs or names when sending messages?
Always use teammate names for messaging and task assignment. Never use agentId, role names, or unsuffixed aliases directly.
How do I find out which teammates are on my team?
Read the config file at ~/.claude/teams/{team-name}/config.json, which lists each member's name, agentId, and agentType. Use the name field for all communication.

Generated from the current SKILL.md. These answers refresh after source changes.