From emasoft-orchestrator-agent
Use when coordinating remote AI agents. Trigger with task delegation or multi-agent coordination requests.
npx claudepluginhub emasoft/emasoft-plugins --plugin emasoft-orchestrator-agentThis skill uses the workspace's default tool permissions.
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.
README.mdreferences/agent-communication-templates.mdreferences/agent-management-commands.mdreferences/agent-management-scripts.mdreferences/agent-management-troubleshooting.mdreferences/agent-onboarding.mdreferences/agent-registration-commands.mdreferences/agent-registration.mdreferences/agent-response-templates.mdreferences/agent-types.mdreferences/artifact-sharing-protocol.mdreferences/assignment-workflow.mdreferences/blocker-report-templates.mdreferences/bug-reporting-protocol-part1-reporting-and-classification.mdreferences/bug-reporting-protocol-part1-schema-severity.mdreferences/bug-reporting-protocol-part2-handling-and-resolution.mdreferences/bug-reporting-protocol-part2-response-escalation.mdreferences/bug-reporting-protocol-part3-error-states.mdreferences/bug-reporting-protocol-part4-verification-troubleshooting.mdreferences/bug-reporting-protocol.mdDelegates tasks to remote AI agents via AI Maestro messaging. Monitors progress, enforces verification loops, and approves PRs. Use for multi-agent delegation requests.
Provides protocols, templates, and rules for constructing subagent delegation prompts with context chains, protocol injection, and downstream declarations in agent orchestration.
Routes tasks to specialized AI agents with anti-duplication checks via task registry, quality gates, and 30-minute heartbeat monitoring. Use for coordinating 3+ agents on complex tasks.
Share bugs, ideas, or general feedback.
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.
| 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 |
Follow these steps when coordinating remote agents:
agent-messaging skill with complete instruction formatCopy this checklist and track your progress:
| Protocol | Reference | Use When |
|---|---|---|
| Acknowledgment | echo-acknowledgment-protocol.md | Task requires confirmation of receipt |
| 4-Verification Loops | verification-loops-protocol.md | Agent requests PR permission |
| Progress Monitoring | progress-monitoring-protocol.md | Tracking agent progress |
| Error Handling | error-handling-protocol.md | Agent reports being blocked |
| Escalation | escalation-procedures.md | Issue requires user decision |
CRITICAL: Remote agents DO NOT have this skill. The orchestrator MUST teach them the ACK protocol BY INCLUDING IT IN EVERY TASK DELEGATION MESSAGE.
ACK template to copy-paste: See echo-acknowledgment-protocol.md section 2.3 for the exact template block.
Full protocol details: echo-acknowledgment-protocol.md
For messaging, use the official AI Maestro skill: ~/.claude/skills/agent-messaging/SKILL.md
| Type | Purpose | When to Use |
|---|---|---|
task | Assign new coding task | Starting work on feature/fix |
fix-request | Request code fix | After PR review finds issues |
status-request | Check on progress | No update received |
approval | Approve completed work | After successful review |
escalation | Escalate to user | Architecture/security decision |
Full protocol details: messaging-protocol.md
Every task instruction MUST include:
Full template and examples: task-instruction-format.md
Include template references in EVERY task delegation:
| Template | Path | Purpose |
|---|---|---|
| ACK Response | templates/ack-response.md | How to acknowledge task receipt |
| Completion Report | templates/completion-report.md | How to report task completion |
| Status Update | templates/status-update.md | How to send progress updates |
Full details: agent-response-templates.md
Before any agent can receive real tasks, they must complete onboarding.
Quick flow:
Full onboarding guide: agent-onboarding.md
Agent registration format: agent-registration.md
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.
Full protocol with table: verification-loops-protocol.md
CRITICAL: Do not wait passively for updates - actively reach out.
Full protocol: progress-monitoring-protocol.md
Remote agents must follow FAIL-FAST:
Full protocol: error-handling-protocol.md
Prerequisites before leaving:
Full guide: overnight-operation.md
Escalate to user when:
Full procedures: escalation-procedures.md
Remote agents MUST have LSP servers installed for working languages. Verify LSP availability before assigning tasks.
LSP References:
Templates provide pre-configured setups for rapid project initialization.
| Category | Purpose |
|---|---|
| Toolchain | Language-specific dev configs |
| Handoff | Task delegation formats |
| Report | Status reporting formats |
| GitHub | Kanban and project tracking |
Full guide: toolchain-template-system.md
Template index: templates/TEMPLATE_INDEX.md
Documents are NEVER embedded in AI Maestro messages - only GitHub issue comment URLs.
Rules:
Full protocol: document-storage-protocol.md
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.
| Document | Use When |
|---|---|
| central-configuration.md | Setting up design/ directory structure |
| change-notification-protocol.md | Notifying agents of config changes |
| artifact-sharing-protocol.md | Sharing build artifacts between agents |
| bug-reporting-protocol.md | Receiving and handling bug reports |
| skill-format-comparison.md | Comparing Open Spec vs Claude Code Skills |
| skill-authoring-best-practices.md | Writing new skills |
| skill-directory-structure.md | Full skill directory structure |
| ecos-replacement-protocol.md | Agent failure or context loss replacement |
| agent-types.md | Worker agent types and role boundaries |
| assignment-workflow.md | Agent availability and task-agent matching |
| agent-communication-templates.md | Standard message templates for agent communication |
For decision trees, mid-task updates, reassignment, blockers, multi-project coordination, and verification feedback, see extended-coordination-protocols.md:
Complete examples with code: examples-remote-coordination.md
Cause: API endpoint unreachable or agent identifier incorrect.
Solution:
agent-messaging skill health checkCause: Instruction Verification Protocol not executed.
Solution:
Cause: Proactive polling not configured or agent not responding.
Solution:
agent-messaging skillCause: Same module assigned to multiple agents.
Solution:
/orchestration-status/reassign-module to move module to single agentCause: Acceptance criteria not met or 4-verification-loop not followed.
Solution:
This script helps locate design documents when coordinating with remote agents:
| Script | Purpose | Usage |
|---|---|---|
eoa_design_search.py | Search design documents for task delegation | python scripts/eoa_design_search.py --type <TYPE> --status <STATUS> |
Use eoa_design_search.py when:
The script is located at ../../scripts/eoa_design_search.py relative to this skill.