multi-agent-coordination

Automatically invoked when peer agents are detected in the same project. Establishes coordination protocols, file reservations, and message-based collaboration. Triggers on SessionStart when other agents exist in the project.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "multi-agent-coordination" with this command: npx skills add zpankz/mcp-skillset/zpankz-mcp-skillset-multi-agent-coordination

Multi-Agent Coordination Protocol

You are operating in a multi-agent environment. Other agents are working on this project concurrently.

Mandatory Coordination Behavior

1. Session Initialization (Do This First)

sequence:
  1. register_agent:
      project_key: ${CWD}
      program: "claude-code"
      model: "claude-opus-4-5"
      # Name auto-generated (adjective+noun like "BlueLake")

  2. fetch_inbox:
      agent_name: ${YOUR_AGENT_NAME}
      include_bodies: true
      # Check for pending coordination messages

  3. Acknowledge any ack_required messages immediately

2. Before Editing Files

Always reserve files before editing:

file_reservation_paths:
  project_key: ${CWD}
  agent_name: ${YOUR_AGENT_NAME}
  paths: ["path/to/file.py"]  # Or glob: "src/api/*.py"
  ttl_seconds: 3600
  exclusive: true
  reason: "Implementing feature X"

If conflicts returned:

  • Check who holds the reservation
  • Send a message requesting coordination
  • Wait for response or reservation expiry

3. Communication Protocol

Notify peers of significant changes:

send_message:
  to: ["PeerAgentName"]  # Or discovered via list_agents
  subject: "Working on: [component]"
  body_md: |
    ## What I'm doing
    - Modifying X
    - Adding Y

    ## Files affected
    - `src/foo.py`
    - `src/bar.py`

    ## Coordination needed?
    Let me know if this conflicts with your work.
  importance: "normal"

4. Periodic Inbox Polling

Check inbox between major work units:

frequency: After each significant edit/commit
action: fetch_inbox → process messages → acknowledge

5. File Release on Completion

Release reservations when done:

release_file_reservations:
  agent_name: ${YOUR_AGENT_NAME}
  # Omit paths to release all

Quick Reference Commands

ActionTool
Start sessionmacro_start_session
Check peerswhois + project agents resource
Reserve filesfile_reservation_paths
Send updatesend_message
Check inboxfetch_inbox
Replyreply_message
Release filesrelease_file_reservations

Conflict Resolution

  1. File conflict: Message the holder, propose merge strategy
  2. Overlapping work: Summarize thread, align on ownership
  3. Urgent coordination: Use importance: "urgent" + ack_required: true

Exit Protocol

Before ending session:

  1. release_file_reservations (all)
  2. send_message with session summary to active peers
  3. Mark any pending inbox items as read

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

subagent-prompt-construction

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

agent-observability

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

agent-evaluation

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

mcp_agent_mail

No summary provided by upstream source.

Repository SourceNeeds Review