Maintain system health with incident handling and operational playbooks
Version: v3.12.0 | Archetype: Operator | Skills: 2 specialized + 15 universal
The Operator archetype ensures operational reliability for systems and services. Unlike development-focused agents, operator agents specialize in:
- Incident response — Handle issues with structured triage, investigation, and resolution
- Playbook execution — Run standard operating procedures with tracking and verification
- System health — Maintain operational continuity through proactive monitoring
For evaluators: If you need an AI that can handle incidents methodically and execute operational procedures reliably, the Operator archetype brings SRE discipline to your workflow.
Domain knowledge that compounds: Operator agents build persistent understanding of your operational environment — recurring incidents, effective runbooks, system dependencies, and resolution patterns. Unlike tools that start fresh each session, your agent accumulates operational context that makes each incident response faster and each playbook execution more reliable.
Operator agents come with 2 archetype-specific skills plus the universal AGET skills.
| Skill | Description |
|---|---|
| aget-handle-incident | Handle incidents with structured triage, impact assessment, and resolution tracking. Documents timeline and actions. |
| aget-run-playbook | Execute operational playbooks with step verification and rollback options. Tracks completion and exceptions. |
All AGET agents include session management, knowledge capture, and health monitoring:
aget-wake-up/aget-wind-down— Session lifecycleaget-create-project/aget-review-project— Project managementaget-record-lesson/aget-record-observation— Learning captureaget-check-health/aget-check-kb/aget-check-evolution— Health monitoringaget-propose-skill/aget-create-skill— Skill developmentaget-save-state/aget-file-issue— State and issue management
Operator agents use a formal vocabulary of 7 concepts organized into 2 clusters:
| Cluster | Concepts |
|---|---|
| Incident Management | Incident, Severity, Resolution, Timeline |
| Operations | Playbook, Step, Runbook |
This vocabulary enables precise communication about operational activities.
See: ontology/ONTOLOGY_operator.yaml
# 1. Clone the template
git clone https://github.com/aget-framework/template-operator-aget.git my-operator-agent
cd my-operator-agent
# 2. Configure identity
# Edit .aget/version.json:
# "agent_name": "my-operator-agent"
# "domain": "your-domain"
# 3. Verify setup
python3 -m pytest tests/ -v
# Expected: All tests passing# In Claude Code CLI
/aget-handle-incident # Respond to an incident
/aget-run-playbook # Execute operational procedure| Aspect | Ad-hoc Response | Operator Agent |
|---|---|---|
| Incidents | Reactive chaos | Structured triage and resolution |
| Procedures | Manual steps | Verified playbook execution |
| Documentation | Post-hoc | Real-time timeline |
| Rollback | Improvised | Planned reversion paths |
| Domain memory | Starts fresh each session | Accumulates operational expertise over time |
| Directory | Purpose | Owner |
|---|---|---|
.claude/skills/ |
Slash command definitions | Framework + Agent |
.claude/agents/ |
Subagent definitions | Agent |
.claude/rules/ |
Path-scoped context rules | Agent |
Skills are provided by the template. Agents and rules directories are scaffolded for your customization.
| Attribute | Value |
|---|---|
| Framework | AGET v3.12.0 |
| Archetype | Operator |
| Skills | 17 total (2 archetype + 15 universal) |
| Ontology | 7 concepts, 2 clusters |
| License | Apache 2.0 |
- AGET Framework — Core framework documentation
- Archetype Guide — All 12 archetypes explained
- Getting Started — Full onboarding guide
| Archetype | Best For |
|---|---|
| Worker | Task execution |
| Developer | Code and build processes |
| Supervisor | Fleet coordination |
AGET Framework | Apache 2.0 | Issues