Saltar al contenido
TakoAPI
Volver a skills

nexus-safe

por mrnsmh

Coding Agents & IDEs
276Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Autonomous local System Reliability Agent for OpenClaw.

Descripción

Qué hace esta skill

Nexus-Safe monitors local system health and manages service restarts for Docker and PM2 processes. It enforces a logs-first policy and rate limiting before allowing any recovery actions. All operations run entirely on the local machine with no outbound network calls.

Unlike cloud-based monitoring agents, Nexus-Safe keeps all system data local and gates restarts behind mandatory log review and rate limits, reducing the risk of blind restart loops.

Cuándo usarla

  • Check CPU, RAM, and disk usage on a production server
  • Pull recent logs from a crashed Docker container
  • Restart a PM2 process after reviewing its error logs
  • Monitor load averages during a traffic spike
  • Audit which services are allowlisted for auto-recovery

Flujo de trabajo de ejemplo

ENTRADA

User asks: /nexus-safe recover my-api

AGENTE
  1. 1

    Checks whether my-api is in the NEXUS_SAFE_ALLOWED_PM2 allowlist

  2. 2

    Verifies that logs for my-api were retrieved within the last 5 minutes

  3. 3

    Checks the sliding window to confirm fewer than 3 restarts occurred in the past hour

  4. 4

    Executes the PM2 restart command for my-api

SALIDA

Service my-api restarted successfully; restart count updated in the rate-limit window.

Requisitos

  • docker installed and available in PATH
  • pm2 installed and available in PATH

Instalación

clawhub install mrnsmh/nexus-safe

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces