analytics

Token-Monitor: Track AI Costs

Name: Token-Monitor: Track AI Costs
Author: Javis603

Get real-time token and cost insights with Token-Monitor, a multi-device sync widget for AI tools, designed for founders using Claude Code, Codex, and more.

1,599 stars144 forksJavaScriptGuide quality 9/10Updated 8/22/2026100% free · open source

What it does

Token-Monitor provides real-time insights into token and cost usage for AI tools like Claude Code and Codex, with multi-device sync capabilities.

When to use it

•When you need to track and manage AI token usage across multiple devices and team members
•When you want to monitor and limit AI costs in real-time to avoid unexpected expenses
•When you are using multiple AI tools and need a unified dashboard to monitor token and cost usage

Ready-to-paste prompt

Open `config.json` and add your Claude Code API key: `{ "claudeCode": { "apiKey": "YOUR_API_KEY_HERE" } }`

Heads up: Make sure you have Node.js (version 16 or higher) installed on your system, as Token-Monitor requires it to run

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/token-monitor && curl -fsSL https://workflowstacks.com/api/skills/token-monitor/claude-skill -o ~/.claude/skills/token-monitor/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Token-Monitor: Track AI Costs works

Codeflow

Free to inspect

Token-Monitor: Track AI Costs is a very large JavaScript project (~80k lines across 270 code files, plus 301 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size

Very large codebase

~80k lines · 270 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Node.js

Needs API keys (.env)

JavaScript 91%CSS 4%HTML 2%Swift 2%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
package.json
Dependencies and the commands it exposes
4
.env.example
The API keys and settings you must provide
5
src/electron/main.js
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic246 files

site/Frontend / UI59 files

worker/Backend / API22 files

docs/Documentation12 files

scripts/Helper scripts24 files

native/Folder15 files

tests/Tests — proof it works304 files

.github/CI / automation (GitHub Actions)65 files

READMEHas testsDocumentedCI checksMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/token-monitor && curl -fsSL https://workflowstacks.com/api/skills/token-monitor/claude-skill -o ~/.claude/skills/token-monitor/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

Javis603

Language

JavaScript