ReddRadar
Agent skill
health-probe
Health probes for both sides of the AGI stack — openclaw + arifOS MCP
Install this agent skill to your Project
npx add-skill https://github.com/ariffazil/arifOS/tree/main/skills/health-probe
SKILL.md
Health Probe — AGI Stack Monitor
Triggers: "health", "probe", "is everything ok", "check stack", "gateway health", "arifos health", "container health", "is arifos sick", "system status"
On Trigger — Run Full Probe
1. arifOS MCP Side
curl -sf http://arifosmcp:8080/health | jq '{status, tools_loaded, version, uptime}'
Expected: status: "healthy", tools_loaded: 13
Alert if: tools_loaded < 13 or status != "healthy"
2. OpenClaw Gateway Self
curl -sf http://localhost:18789/ | head -c 200 2>/dev/null && echo "GATEWAY_UP" || echo "GATEWAY_UNREACHABLE"
3. All Containers Status
docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}" | grep -v "^NAME"
Flag any container NOT showing healthy or Up:
unhealthy→ CRITICALExited/Restarting→ CRITICALUp X minuteswithouthealthy→ WARNING (check if has healthcheck)
4. Disk Check
df -h / | awk 'NR==2 {
used=$5+0
if (used > 85) print "DISK_CRITICAL: " used "% used"
else if (used > 75) print "DISK_WARNING: " used "% used"
else print "DISK_OK: " used "% used"
}'
5. RAM Check
free -h | awk '/^Mem:/ {
total=$2; avail=$7
print "RAM: total=" total " available=" avail
}'
docker stats --no-stream --format "{{.Name}}: {{.MemUsage}}" | sort -t'/' -k1 -rh | head -5
6. Ollama Models Available
docker exec ollama_engine ollama list 2>/dev/null | tail -n +2
7. Log the probe result
echo "{\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\",\"event\":\"health_probe\",\"agent\":\"arifOS_bot\"}" \
>> ~/.openclaw/workspace/logs/audit.jsonl
Alert Thresholds
| Metric | WARNING | CRITICAL | Action |
|---|---|---|---|
| Disk usage | >75% | >85% | Notify Arif on Telegram |
| RAM available | <3 GiB | <1.5 GiB | Notify + pause heavy tasks |
| tools_loaded | <13 | <10 | Restart arifosmcp |
| Container state | Restarting | Exited/unhealthy | docker compose up -d |
| Model count | 0 | — | docker exec ollama_engine ollama pull qwen2.5:3b |
Auto-Recovery Actions (within authority)
# Restart unhealthy arifOS
docker compose -f /mnt/arifos/docker-compose.yml restart arifosmcp
# Restart unhealthy openclaw (from host — self-restart)
docker compose -f /mnt/arifos/docker-compose.yml restart openclaw
# Clear disk if >80%
docker builder prune -f
docker image prune -f --filter "dangling=true"
Run this skill on every session start to establish baseline. Alert Arif via Telegram if CRITICAL.
Telegram Alerts (when CRITICAL)
# Send alert to Arif via Telegram bot
send_telegram_alert() {
local MESSAGE="$1"
if [ -n "${TELEGRAM_BOT_TOKEN:-}" ] && [ -n "${TELEGRAM_CHAT_ID:-}" ]; then
curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \
-d "chat_id=${TELEGRAM_CHAT_ID}" \
-d "text=⚠️ arifOS_bot: ${MESSAGE}" \
-d "parse_mode=Markdown" > /dev/null
fi
}
# Example alerts:
# send_telegram_alert "🔴 arifosmcp UNHEALTHY — tools_loaded=$(curl ...)"
# send_telegram_alert "💿 Disk ${DISK_PCT}% — run: docker builder prune -f"
# send_telegram_alert "🧠 RAM critical — available: ${RAM_AVAIL}MiB"
Note: TELEGRAM_CHAT_ID is the numeric chat ID of Arif's chat with @arifOS_bot.
To get it: message the bot, then check https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getUpdates
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ariffazil/arifOS
mcp-config-separation
ariffazil/arifOS
drift-watcher
Periodic knowledge freshness checker: detects when local configs, runbooks, or agent knowledge have drifted from the latest official docs. Reduces the stale-knowledge paradox over time. Use when: (1) periodic health checks or heartbeat runs, (2) before major operations, (3) user asks 'am I up to date', 'check for updates', 'is anything outdated', (4) after a software upgrade to verify configs still match new docs.
ariffazil/arifOS
MCP_CONFIG
ariffazil/arifOS
config-guardian
Universal governed config co-pilot. Before ANY change to ANY system: (1) check latest docs and running version (docs-first), (2) propose as diff with risk analysis, never apply directly (propose-only), (3) log every change with evidence and rollback (change ledger). Works for OpenClaw, Docker, PostgreSQL, Nginx, arifOS, or any software. Triggers on: 'change config', 'fix settings', 'update', 'propose patch', 'explain config', 'validate config', 'why did we change X'. Enforces propose-only workflow — human applies via git.
ariffazil/arifOS
drift-watcher
Periodic knowledge freshness checker: detects when local configs, runbooks, or agent knowledge have drifted from the latest official docs. Reduces the stale-knowledge paradox over time. Use when: (1) periodic health checks or heartbeat runs, (2) before major operations, (3) user asks 'am I up to date', 'check for updates', 'is anything outdated', (4) after a software upgrade to verify configs still match new docs.
ariffazil/arifOS
config-guardian
Universal governed config co-pilot. Before ANY change to ANY system: (1) check latest docs and running version (docs-first), (2) propose as diff with risk analysis, never apply directly (propose-only), (3) log every change with evidence and rollback (change ledger). Works for OpenClaw, Docker, PostgreSQL, Nginx, arifOS, or any software. Triggers on: 'change config', 'fix settings', 'update', 'propose patch', 'explain config', 'validate config', 'why did we change X'. Enforces propose-only workflow — human applies via git.
Didn't find tool you were looking for?