CacheForge Stats for Openclaw

A terminal-based dashboard for monitoring CacheForge LLM usage, token savings, and performance metrics.

tkuehnl
v1.0.1
Feb 20, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install cacheforge-stats

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install cacheforge-stats 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 CacheForge Stats?

CacheForge Stats is a specialized observability and diagnostic tool designed for developers who want to maximize the efficiency of their LLM workflows. By integrating directly into your development environment, this skill provides a comprehensive terminal dashboard that visualizes exactly where your tokens are going and how much you are saving through prompt caching. It is a vital component for those managing production-grade agents using Openclaw Skills who need to justify AI infrastructure costs.

The skill bridges the gap between raw API calls and actionable business intelligence. It allows you to monitor token reduction rates and check the health of your cache performance in real-time. Whether you are debugging high costs or optimizing response times, this tool provides the transparency required to run lean, high-performance AI operations.

CacheForge Stats Use Cases

  • Visualizing real-time CacheForge usage and total financial savings through a terminal interface.
  • Monitoring token reduction rates to validate the effectiveness of caching strategies.
  • Analyzing cost savings breakdowns to report on AI infrastructure efficiency.
  • Identifying high-usage models or providers to optimize API key allocation.
  • Reviewing historical performance metrics over specific windows like 7-day or 30-day periods.

How CacheForge Stats Works

  1. The skill authenticates with the CacheForge backend using the CACHEFORGE_API_KEY stored in your environment.
  2. It sends requests to specific account endpoints, including billing, usage, and breakdown services.
  3. The Python-based dashboard engine processes the raw JSON response to calculate savings ratios and performance metrics.
  4. It renders a structured terminal view featuring charts, tables, and summaries for immediate analysis.
  5. Users can refine the output using CLI flags to filter data by model, provider, or specific time windows.

CacheForge Stats Setup

To install and configure CacheForge Stats, ensure you have Python 3 installed and follow these steps:

  1. Set your mandatory environment variables:
export CACHEFORGE_API_KEY="your_api_key_here"
export CACHEFORGE_BASE_URL="https://app.anvil-ai.io"
  1. Run the full dashboard to verify the connection:
python3 skills/cacheforge-stats/dashboard.py dashboard

CacheForge Stats Data Schema & Taxonomy

The skill organizes and displays data according to the following metadata taxonomy:

Data Point Description
Usage Metrics Total token counts including input, output, and cached tokens.
Savings Data Monetary value saved through cache hits and token optimization.
Breakdown Categorization of usage by specific LLM model, provider, or API key.
Performance Cache hit rates and reduction percentages to measure efficiency.
Billing Info Account-level financial status and usage limits.

CacheForge Stats Advanced Features

  • Interactive terminal dashboard for high-level observability of AI operations.
  • Detailed breakdown analysis to pinpoint specific models driving costs within Openclaw Skills workflows.
  • Configurable time-window filtering (e.g., --window 7d) for granular temporal reporting.
  • Savings-focused reporting mode to highlight the return on investment (ROI) of prompt caching.
  • Direct integration with CacheForge API v1 endpoints for accurate, real-time data retrieval.

SKILL.md


Loading

METADATA

Requires
Bins python3
Github Stars: 0
forks: 0

Featured*