docs: add isolated copy-paste ssh/metric examples to README and example.config.yaml

example.config.yaml

@@ -38,10 +38,31 @@
 #     ...
 #     -----END OPENSSH PRIVATE KEY-----
 #   script: |                      # shell script to run over ssh
-#     echo "tmp:on:$(df -h /tmp 2>/dev/null | awk 'NR==2 {print $2}')"
+#     # status chips (name:status:info)
+#     echo "hostname:on:$(hostname)"
+#     echo "kernel:on:$(uname -sr)"
+#     echo "vulkan:on:$(vulkaninfo --summary 2>/dev/null | sed -n '/deviceName/p' | head -1 | cut -d: -f2-)"
+#     echo "docker:$(systemctl is-active docker 2>/dev/null | sed 's/active/on/; s/inactive/off/; s/failed/down/'):docker daemon"
+#     echo "nfs:$(systemctl is-active nfs-server 2>/dev/null | sed 's/active/on/; s/inactive/off/; s/failed/down/'):nfs-server"
+#
+#     # metrics (name:metric:value)
 #     echo "cpu_pct:metric:$(top -bn1 2>/dev/null | awk '/%Cpu/ {printf "%.1f", 100-$8}')"
+#     echo "load1:metric:$(cut -d' ' -f1 /proc/loadavg)"
+#     echo "ram_pct:metric:$(free -m 2>/dev/null | awk '/^Mem:/ {printf "%.1f", $3/$2*100}')"
+#     echo "ram_used:metric:$(free -m 2>/dev/null | awk '/^Mem:/ {print $3}')MB"
+#     echo "disk_root:metric:$(df -h / 2>/dev/null | awk 'NR==2 {print $5}' | tr -d '%')"
+#     echo "boot_days:metric:$(awk '{printf "%.2f", $1/86400}' /proc/uptime)"
+#     echo "cpu_temp:metric:$(sensors 2>/dev/null | awk '/Package id 0:/ {print $4; exit}' | tr -d '+°C')"
+#     echo "gpu_temp:metric:$(nvidia-smi --query-gpu=temperature.gpu --format=csv,noheader 2>/dev/null | tr -d ' ')"
+#     echo "gpu_util:metric:$(nvidia-smi --query-gpu=utilization.gpu --format=csv,noheader 2>/dev/null | tr -d ' %')"
+#
+#     # free-form section, shown raw in the machine modal
 #     echo "---"
-#     echo "kernel: $(uname -sr)"
+#     echo "uptime: $(uptime -p)"
+#     echo "load: $(cat /proc/loadavg)"
+#     echo "mem: $(free -h | awk '/^Mem:/ {print $3 "/" $2}')"
+#     echo "disk: $(df -h / | awk 'NR==2 {print $4 " free"}')"
+#     echo "top: $(ps -eo %cpu,comm --sort=-%cpu | head -4 | tr '\n' ';')"
 #
 #   Script format, one line per item:
 #     name:status:info    -> a check chip (status: on / off / down / anything)
@@ -58,7 +79,16 @@
 #   ram_pct:
 #     min: 0
 #     max: 100
-#   disk_free:
+#   disk_root:
+#     min: 0
+#     max: 100
+#   gpu_util:
+#     min: 0
+#     max: 100
+#   gpu_temp:
+#     min: 0
+#     max: 105
+#   boot_days:
 #     min: 0
 
 # ---------- machines grouped by section ----------