Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
The command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
File Explorer
2 files
Showing SKILL.md
SKILL.md
Source instructions · Read-only preview
name
eoa-remote-agent-coordinator
description
Use when coordinating remote AI agents. Trigger with task delegation or multi-agent coordination requests.
license
Apache-2.0
compatibility
Requires AI Maestro messaging system (AMP, handles routing automatically). Python 3.9+ for LSP management scripts. Requires AI Maestro installed.
metadata
{"author":"Emasoft","version":"1.2.0"}
context
fork
user-invocable
false
agent
eoa-main
workflow-instruction
Step 17
procedure
proc-execute-task
Remote Agent Coordinator
Overview
The Remote Agent Coordinator enables the EOA (Emasoft Orchestrator Agent) to delegate coding tasks to remote AI agents and human developers via the AI Maestro messaging system. This is the ONLY mechanism through which actual code is written.
Critical Principle: The orchestrator NEVER writes code. It creates precise instructions and sends them to remote agents who execute the coding work.
Prerequisites
AI Maestro messaging system (AMP) running
Python 3.9+ for LSP management scripts
Remote agents registered and available
GitHub CLI (gh) for issue management
Output
Output Type
Format
Location
Agent roster
JSON file
agent_roster.json
Task delegation messages
AI Maestro message
Sent via API
Progress reports
AI Maestro message
Received via API
Verification loop state
JSON tracking
In-memory or file
Escalation messages
AI Maestro message
Sent to orchestrator-master
Instructions
Follow these steps when coordinating remote agents:
Verify AI Maestro is running and remote agents are registered
Review the task requirements and prepare delegation instructions
Include ACK protocol instructions in every task message (see MANDATORY section below)
Send task delegation message via AI Maestro using the agent-messaging skill with complete instruction format
Wait for agent acknowledgment (timeout: 5 minutes)
Monitor progress proactively every 10-15 minutes during active work
Enforce 4-verification-loop protocol before approving any PR requests
Review completion reports against acceptance criteria
Escalate to user when architecture/security decisions are needed
Checklist
Copy this checklist and track your progress:
AI Maestro messaging system is running and accessible
Remote agents are registered and available in agent roster
Task delegation includes ACK protocol instructions block
Task delegation includes PR notification requirement
Task delegation includes complete instruction format (context, scope, interface, files, tests, completion criteria)
Agent acknowledgment received within 5 minutes
Proactive progress monitoring active (polling every 10-15 minutes)
4-verification-loop protocol enforced before PR approval
Completion report reviewed against acceptance criteria
LSP servers verified for agent's working language
All escalations resolved before considering task complete
CRITICAL: For EACH TASK, require 4 verification loops BEFORE allowing PR creation. The agent will make 5 PR requests total - respond to the first 4 with "Check your changes for errors", then approve or reject on the 5th.
RULE 15 - No Implementation: The orchestrator NEVER writes code, runs builds, edits source files, or sets up infrastructure. See rule-15-no-implementation.md.
RULE 14 - Immutable Requirements: Every task delegation MUST include requirement references, forbidden actions, and escalation protocol. See rule-14-immutable-requirements.md.
Standard message templates for agent communication
Extended Coordination Protocols
For decision trees, mid-task updates, reassignment, blockers, multi-project coordination, and verification feedback, see extended-coordination-protocols.md:
Core Decision Trees - When deciding whether to escalate, reassign, retry, or handle directly
Mid-Task Updates - When relaying requirement changes or priority shifts to agents mid-task
Reassignment Communication - When reassigning tasks between agents due to failure or recovery
Blocker Reports - When agents report blockers and the orchestrator must triage
Multi-Project Coordination - When tasks span multiple projects with cross-dependencies
Verification Feedback (Loops 2-4) - When providing progressive feedback during the 4-verification-loop cycle
