Openclaw Monitor

# Monitoring Skill

System health monitoring for OpenClaw — tracks token spend, task success rates, cron health, and skill usage.

## Commands
```
monitor status                                          # Health summary
monitor tokens [--period 7d|30d] [--by model|skill]    # Token report
monitor crons                                           # Cron health
monitor tasks [--failed]                                # Task history
monitor cost [--period month|week]                      # Cost breakdown
monitor ingest token|task|cron                          # Manual ingestion
monitor aggregate [--date YYYY-MM-DD]                   # Daily aggregates
monitor refresh                                         # Regenerate interchange
monitor backup [--output path]                          # Backup DB
monitor restore <file>                                  # Restore DB
```

## Interchange
- `ops/capabilities.md` — Command reference (shareable)
- `ops/health.md` — Status indicators only (shareable, no costs/tokens)
- `state/status.md` — Full detailed status (private)
- `state/token-spend.md` — Token/cost breakdown (private)

# openclaw-monitor

[![Tests](https://img.shields.io/badge/tests-10%20passing-brightgreen)]() [![Node](https://img.shields.io/badge/node-%3E%3D18-blue)]() [![License: MIT](https://img.shields.io/badge/license-MIT-yellow)]()

> System health monitoring — token spend, task success rates, cron health, and cost analysis.

Track everything your AI agents are spending and doing. Monitor token usage by model and skill, watch task success rates, keep tabs on cron job health, and generate cost breakdowns — all from the command line with `.md` interchange reports.

## Features

- **Token spend tracking** — ingest and report on token usage by model and skill
- **Task success rates** — track success, failure, and timeout rates
- **Cron health** — monitor job execution with pass/fail and duration stats
- **Cost analysis** — breakdowns by model, day, week, or month
- **Daily aggregation** — automatic rollup of metrics into daily summaries
- **Status dashboard** — quick system health summary with emoji indicators
- **Interchange reports** — generate `.md` files for cross-skill visibility
- **Backup & restore** — full database backup and recovery

## Quick Start

```bash
cd skills/monitoring
npm install

# Quick health check
node src/cli.js status

# Ingest some events
node src/cli.js ingest token --model gpt-4 --in 1500 --out 500 --cost 0.045 --skill crm
node src/cli.js ingest task --command "deal-sync" --status success --duration 1200

# View reports
node src/cli.js tokens --period 7d --by model
node src/cli.js cost --period week
```

## CLI Reference

### Reports

```bash
monitor status                          # System health summary
monitor tokens [--period <7d>] [--by <model|skill>]   # Token usage report
monitor tasks [--failed]                # Task history (optionally failures only)
monitor crons                           # Cron job health
monitor cost [--period <week|month>]    # Cost breakdown
```

### Event Ingestion

```bash
monitor ingest token --model <model> --in <n...