Use when notifying agents about upcoming operations, requesting acknowledgments before proceeding, or sending failure notifications after operation errors. Trigger with notification or alert events.
npx claudepluginhub emasoft/emasoft-plugins --plugin emasoft-chief-of-staffThis skill uses the workspace's default tool permissions.
Notification protocols ensure agents are properly informed about operations that affect them. Before performing operations like skill installation, agent restart, or configuration changes, the Chief of Staff must notify affected agents, wait for acknowledgment, and then proceed. This skill teaches you how to send pre-operation notifications, handle acknowledgment workflows, and report failures.
references/acknowledgment-protocol.mdreferences/ai-maestro-message-templates.mdreferences/design-document-protocol.mdreferences/edge-case-protocols.mdreferences/failure-notifications.mdreferences/message-response-decision-tree.mdreferences/op-acknowledgment-protocol.mdreferences/op-failure-notification.mdreferences/op-post-operation-notification.mdreferences/op-pre-operation-notification.mdreferences/post-operation-notifications.mdreferences/pre-operation-notifications.mdreferences/proactive-handoff-protocol.mdreferences/task-completion-checklist.mdProvides JSON templates for inter-agent messaging in AI Maestro, for task assignment, status reports, approvals, and escalations. Triggered by coordination needs.
Defines structured protocols for agent team communication: direct messages, broadcasts, plan approvals, shutdowns, and anti-patterns. Use for team norms, message selection, or coordination debugging.
Use when dispatching subagents, composing prompts for teammates, structuring handoff reports, or managing context boundaries between agents. Covers both subagent prompts and team-level messaging.
Share bugs, ideas, or general feedback.
Notification protocols ensure agents are properly informed about operations that affect them. Before performing operations like skill installation, agent restart, or configuration changes, the Chief of Staff must notify affected agents, wait for acknowledgment, and then proceed. This skill teaches you how to send pre-operation notifications, handle acknowledgment workflows, and report failures.
Before using this skill, ensure:
agent-messaging skill| Notification Type | Output |
|---|---|
| Status update | Notification sent, delivery confirmed |
| Alert | Alert sent, escalation tracked |
| Broadcast | Message sent to all agents, receipt logged |
Notification protocols are the standardized communication patterns the Chief of Staff uses to coordinate with other agents during operations. The protocols ensure:
┌───────────────────────────────────────────────────────────────────┐
│ NOTIFICATION PROTOCOLS │
├───────────────────┬───────────────────┬───────────────────────────┤
│ PRE-OPERATION │ POST-OPERATION │ FAILURE │
│ Notifications │ Notifications │ Notifications │
├───────────────────┼───────────────────┼───────────────────────────┤
│ - Warn agents │ - Confirm done │ - Report failures │
│ - Request ack │ - Ask verify │ - Provide diagnostics │
│ - Wait for ok │ - Resume work │ - Suggest recovery │
└───────────────────┴───────────────────┴───────────────────────────┘
Protocol Flow:
When to use: Before skill installation, plugin installation, agent restart, configuration changes, or any operation that will interrupt an agent.
Steps: Identify affected agents, compose notification message, send via AI Maestro, track acknowledgments, handle timeouts.
Related documentation:
When to use: After skill installation completes, after agent restart, after configuration changes apply, or after any operation that affected an agent.
Steps: Confirm operation completed, compose success message, send confirmation, request verification, log outcome.
Related documentation:
When to use: When you need agent confirmation before proceeding, when operations require agent readiness, or when coordinating multi-agent operations.
Steps: Send acknowledgment request, start timeout timer, send reminders, process response, proceed or handle timeout.
Related documentation:
CRITICAL: All ECOS components MUST use these standardized timeout values:
| ACK Type | Timeout | Reminders | Use Case |
|---|---|---|---|
| Pre-operation ACK | 60 seconds | 15s, 30s, 45s | Before disruptive operations (hibernate, restart, etc.) |
| Approval request | 2 minutes | 60s, 90s | Requesting manager approval for operations |
| Emergency handoff ACK | 30 seconds | 10s, 20s | Time-critical emergency situations |
| Health check response | 30 seconds | None | Verifying agent is alive |
Important: These timeouts are SEQUENTIAL, not parallel. Total wait time calculation:
Example: Skill installation with approval
1. Pre-operation ACK request to agent → Wait up to 60 seconds
2. Approval request to EAMA → Wait up to 2 minutes
3. Post-operation verification → Wait up to 30 seconds
─────────────────────
Total maximum wait time = 3 minutes 30 seconds
Timeout behavior:
When to use: When skill installation fails, when agent restart fails, when configuration change fails, or when any operation error occurs.
Steps: Capture error details, compose failure message, send to affected agents, provide recovery guidance, log failure.
Related documentation:
Copy this checklist and track your progress:
This example shows the full notification flow for installing a skill on an agent.
Step 1: Send Pre-Operation Notification
Use the agent-messaging skill to send a message:
code-impl-authSkill Installation Pendinghighpre-operation, message explaining the upcoming skill installation, expected downtime of 30 seconds, and that acknowledgment is requiredVerify: confirm message delivery.
Step 2: Wait for Acknowledgment (with reminders)
Use the agent-messaging skill to check for unread messages from code-impl-auth with type acknowledgment.
If no response after 30 seconds, use the agent-messaging skill to send a reminder:
code-impl-authReminder: Skill Installation Pendinghighreminder, noting 90 seconds remainingVerify: check for acknowledgment response.
Step 3: Receive Acknowledgment
Note: Use the
agent-messagingskill to send messages. The JSON structure below shows the message content.
{
"from": "code-impl-auth",
"to": "chief-of-staff",
"subject": "RE: Skill Installation Pending",
"content": {
"type": "acknowledgment",
"message": "ok",
"ready": true
}
}
Step 4: Perform Installation
Use the ai-maestro-agents-management skill to hibernate agent code-impl-auth, install the skill, then wake agent code-impl-auth.
Verify: agent is back online after wake.
Step 5: Send Post-Operation Notification
Use the agent-messaging skill to send a message:
code-impl-authSkill Installation Completenormalpost-operation, confirming that the security-audit skill has been installed, requesting the agent to verify the skill is activeVerify: confirm message delivery and await agent verification response.
After 2 minutes with no response, proceed anyway:
Log the timeout: WARNING: No acknowledgment from code-impl-auth after 2 minutes.
Use the agent-messaging skill to send a final notice:
code-impl-authProceeding Without Acknowledgmenthightimeout-notice, explaining that no response was received and the operation will proceedUse the ai-maestro-agents-management skill to hibernate agent code-impl-auth and proceed with installation.
Verify: confirm final notice was delivered.
When a skill installation fails, use the agent-messaging skill to send a failure notification:
code-impl-authSkill Installation Failedhighfailure, explaining the error (e.g., "Skill validation failed - missing required SKILL.md file"), advising the agent to continue previous work, and noting the recovery action (skill package will be fixed and installation retried)Verify: confirm message delivery.
For each target agent (code-impl-auth, test-engineer-01, docs-writer), use the agent-messaging skill to send a message:
System Maintenance in 5 Minuteshighbroadcast, explaining that system maintenance will begin in 5 minutes, all agents will be hibernated, and they should save their work and reply with "ok" when ready. Include the total recipient count and a broadcast ID for tracking.Verify: confirm delivery to all recipients and track acknowledgments.
Step-by-step runbooks for executing individual notification operations. Use these when performing a specific notification operation.
Symptoms: Agent does not receive message, no response observed.
See references/pre-operation-notifications.md Section 1.7 Troubleshooting for resolution.
Symptoms: Agent does not respond within 2 minutes.
See references/acknowledgment-protocol.md Section 3.9 Troubleshooting for resolution.
Symptoms: Agent responds with something other than "ok".
See references/acknowledgment-protocol.md Section 3.6 Response handling for resolution.
Symptoms: Agent unaware of operation failure.
See references/failure-notifications.md Section 4.8 Troubleshooting for resolution.
| Message Type | When to Use | Requires Ack |
|---|---|---|
pre-operation | Before any disruptive operation | Yes |
post-operation | After successful operation | Optional |
reminder | When awaiting acknowledgment | No |
timeout-notice | When proceeding without ack | No |
failure | When operation fails | No |
broadcast | Notifying multiple agents | Yes |
acknowledgment | Agent responding with "ok" | No |
See references/pre-operation-notifications.md for complete pre-operation documentation.
See references/post-operation-notifications.md for confirmation procedures.
See references/acknowledgment-protocol.md for detailed acknowledgment handling.
See references/failure-notifications.md for error notification procedures.
Version: 1.0 Last Updated: 2025-02-02 Target Audience: Chief of Staff Agents Difficulty Level: Intermediate