Track token burn, spend, and model mix across multiple coding-agent tools from one local monitoring workflow.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Monitor coding-agent token spend with Splitrail"
slug: "monitor-coding-agent-token-spend-with-splitrail"
description: "Track token burn, spend, and model mix across multiple coding-agent tools from one local monitoring workflow."
github_stars: 159
verification: "security_reviewed"
source: "https://github.com/Piebald-AI/splitrail"
author: "Piebald AI"
publisher_type: "organization"
category: "Monitoring & Alerts"
framework: "Multi-Framework"
tool_ecosystem:
github_repo: "Piebald-AI/splitrail"
github_stars: 159
---
# Monitor coding-agent token spend with Splitrail
Track token burn, spend, and model mix across multiple coding-agent tools from one local monitoring workflow.
## Prerequisites
Splitrail binary, local agent usage logs or supported agent installations
## Installation
Use the upstream install or setup path that matches your environment:
- cargo run
Basic usage or getting-started notes:
- Splitrail is a **fast, cross-platform, real-time token usage tracker and cost monitor for**:
- Run one command to instantly review all of your CLI coding agent usage. Upload your usage data to your private account on the [Splitrail Cloud](https://splitrail.dev) for safe-keeping and cross-machine usage aggregati...
- Splitrail can run as an [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) server, allowing AI assistants to query your usage statistics programmatically.
- Source: https://github.com/Piebald-AI/splitrail
- Extracted from upstream docs: https://raw.githubusercontent.com/Piebald-AI/splitrail/HEAD/README.md
## Documentation
- https://github.com/Piebald-AI/splitrail
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/monitor-coding-agent-token-spend-with-splitrail/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.