A lightweight operational monitoring tool to track agent health, API usage, and performance metrics through a text-based dashboard.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install arc-metrics-dashboard
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install arc-metrics-dashboard using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Metrics Dashboard?
The Metrics Dashboard is a specialized tool designed to provide deep visibility into the lifecycle and performance of autonomous agents. It solves the problem of agents operating in a vacuum by providing a structured way to answer critical questions regarding task completion rates, API consumption, and system stability. By utilizing this component of Openclaw Skills, developers can gain a clear understanding of their agent's operational health and resource usage.
This skill enables developers to record events, measure durations, and increment counters using a simple command-line interface. Whether you are tracking the cost of Large Language Model (LLM) calls or monitoring the frequency of specific errors, the Metrics Dashboard synthesizes this data into human-readable reports and exportable formats for further analysis.
Metrics Dashboard Use Cases
- Tracking API usage and associated costs across different LLM providers.
- Measuring the average duration of complex task workflows to identify bottlenecks.
- Monitoring error rates and specific failure points like verification or solver errors.
- Generating daily or weekly operational reports for agent performance reviews.
- Exporting metric data to CSV or JSON for integration with external business intelligence tools.
How Metrics Dashboard Works
- The agent or user invokes a command to record a specific metric type such as a counter, timer, or gauge.
- The system appends the metric data, including custom tags and timestamps, to a local JSON file.
- Data is organized chronologically in daily storage files to ensure high performance and easy rotation.
- When requested, the dashboard engine aggregates these daily logs to calculate averages, totals, and error percentages.
- The results are rendered as a clean, text-based dashboard in the terminal or exported as structured data for external use.
Metrics Dashboard Setup
To begin using the Metrics Dashboard within your Openclaw Skills environment, ensure Python 3 is installed and follow these steps:
# Verify your Python environment
python3 --version
# Record your first metric to initialize storage
python3 scripts/metrics.py record --name initial_setup --value 1
# View the current dashboard status
python3 scripts/metrics.py dashboard
Metrics Dashboard Data Schema & Taxonomy
Metrics are stored locally to maintain privacy and performance. The data is organized as follows:
| Component | Detail |
|---|---|
| Storage Location | ~/.openclaw/metrics/ |
| File Format | Daily JSON files (e.g., 2023-10-27.json) |
| Metric Types | counter, timer, event, gauge |
| Metadata | Supports custom JSON tags (e.g., provider, model, task_id) |
| Export Options | Standardized JSON and CSV formats |
Metrics Dashboard Advanced Features
- Tag-based filtering to segment performance data by specific models or task types.
- Integrated error tracking that logs specific failure messages for rapid debugging.
- Compliance audit trail integration to link operational metrics with security logs.
- Automated uptime calculation based on the frequency of recorded heartbeat events.
- High-precision timers for measuring millisecond-level latencies in API responses.
SKILL.md
Loading
Related Openclaw Skills
Memory Pruner
A specialized utility to automatically prune, compact, and manage the size of AI agent memory and log files.
Free Worker Dispatch
A smart routing utility that saves money by delegating routine content, research, and coding tasks to free AI models via OpenRouter.
Department Manager
A command-line orchestration layer for delegating tasks and managing specialized AI agent departments like a CEO.
Compliance Checker
Policy-based security assessment and compliance tracking for AI agent skills.
Security Audit
A unified security assessment tool that chains scanners and verifiers to harden and secure your entire agent skill ecosystem.
ARC Security MCP Server
A high-fidelity security intelligence service providing real-time auditing, static analysis, and semantic threat detection for the AI agent ecosystem.
Featured*
