name: analyst-watchdog version: 1.0.0 description: Automated monitoring agent that watches an API scoreboard, detects milestones, writes findings to markdown, and alerts via file-based triggers. Use when you need an autonomous agent that monitors a system and produces structured analysis without human intervention. metadata: {"openclaw": {"emoji": "📊", "requires": {"bins": ["python3"], "env": []}, "primaryEnv": null, "network": {"outbound": false, "reason": "Reads from a local API endpoint (localhost). All output is written to local files."}}}

Analyst Watchdog

An autonomous monitoring agent pattern: watch a system, detect changes, write findings, alert when thresholds are crossed. Runs on a schedule (LaunchAgent or cron) without human intervention.

Pattern

API Endpoint → Poll → Detect Changes → Write FINDINGS.md
                                      → Write OUTBOX.md (for orchestrator)
                                      → Write ALERT_TELEGRAM.md (urgent)

What It Monitors

Configurable, but the reference implementation tracks:

• Model evaluation scores hitting milestones (n=50, 100, 150, 200)
• Promotion events (model proven equivalent to cloud baseline)
• Score anomalies (sudden drops or improvements)
• System health degradation

Alert Tiers

Files

• scripts/analyst_agent.py — Reference watchdog implementation