원클릭으로
soar
SOAR operating loop — Scan, Orient, Act, Record. Full cluster health assessment and prioritized action.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
SOAR operating loop — Scan, Orient, Act, Record. Full cluster health assessment and prioritized action.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Auto-route tasks to the optimal tool, model, and subscription. Registry-backed provider and model truth only. Content governance enforced.
Manage overnight autonomous coding tasks
Cross-reference hardware inventory against node configs, detect discrepancies
Perpetual improvement loop. Find the weakest part of the system and make it better. Never stops. Use when continuing work, when idle, when asked to improve, or when nothing specific is requested.
Run drift detection to verify system matches architectural decisions
Structured process for making and documenting architecture decisions with ADR format
| name | soar |
| description | SOAR operating loop — Scan, Orient, Act, Record. Full cluster health assessment and prioritized action. |
| triggers | ["soar","ops check","cluster sweep"] |
Execute the full Scan-Orient-Act-Record cycle for the Athanor cluster.
!`ssh -o ConnectTimeout=3 -o BatchMode=yes foundry 'echo "FOUNDRY: UP"; nvidia-smi --query-gpu=index,name,memory.used,memory.total,temperature.gpu --format=csv,noheader 2>/dev/null; docker ps --format " {{.Names}}: {{.Status}}" 2>/dev/null | head -10' 2>/dev/null || echo "FOUNDRY: UNREACHABLE"`
!`ssh -o ConnectTimeout=3 -o BatchMode=yes workshop 'echo "WORKSHOP: UP"; nvidia-smi --query-gpu=index,name,memory.used,memory.total,temperature.gpu --format=csv,noheader 2>/dev/null; docker ps --format " {{.Names}}: {{.Status}}" 2>/dev/null | head -10' 2>/dev/null || echo "WORKSHOP: UNREACHABLE"`
!`ssh -o ConnectTimeout=3 -o BatchMode=yes vault 'echo "VAULT: UP"; docker ps --format "{{.Names}}" 2>/dev/null | wc -l; echo "containers running"; df -h / /mnt/user 2>/dev/null | tail -2' 2>/dev/null || echo "VAULT: UNREACHABLE"`
Review the live cluster state above. Check for:
Prioritize findings by severity:
Pick the single highest-priority actionable item and execute it:
After acting: