TokenTracker — AI Agent Cost & Usage Monitor

    2

    Track token spend across AI providers, set monthly budgets, get Telegram alerts on cost spikes, and generate daily/weekly reports.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    TokenTracker — AI Agent Cost & Usage Monitor

    Example session with this skill installed

    Generate a cost report for the last 7 days and check my current budget status for agent-alpha and researcher-bot.

    • Read your context and instructions
    • Compiled the tokentracker

    [REPORT - LAST 7 DAYS]
    Total Spend: $14.22 / Budget: $50.00 (28.4%)

    • agent-alpha (gpt-4o): $8.45 (12,400 tokens)
    • researcher-bot (claude-3-5-sonnet): $5.77 (8,100 tokens)
      ALERT: Daily spend increased by 15% vs yesterday.
      Telegram notification sent to @dev_admin.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    TokenTracker is a lightweight, self-hosted CLI tool that gives you complete visibility and control over your AI token usage and spending across any OpenAI-compatible provider.

    It tracks every API call, calculates real costs in real-time, enforces monthly budgets, and sends intelligent Telegram alerts when you're approaching or exceeding your limits.

    Key Features:

    • Track usage per agent, per model, and per task
    • Set custom monthly budgets with alerts at 80%, 90%, and 100%
    • Generate beautiful daily/weekly reports with breakdowns
    • Continuous "watch" mode with automated daily summaries
    • Supports DeepSeek V4 Flash, GPT-4o, GPT-4.1, Claude Sonnet 4, Claude Haiku, and any custom OpenAI-compatible endpoint
    • Local-first — your data never leaves your server
    • One-command install and setup

    Installation:

    npm install -g tokentracker
    tokentracker setup
    tokentracker watch
    

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    • Requires manual integration via CLI or module for tracking.
    • Local NDJSON storage lacks multi-device sync.
    • Telegram is currently the only supported alert channel.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 6 months ago

    Accounts
    Telegram

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Environment Variables

    Allowed Hosts

    api.telegram.org
    Listed6 months ago

    What's inside

    Frequently Asked Questions

    TokenTracker solves the "bill shock" problem by providing real-time visibility into consumption across all your AI agents, allowing you to set hard budgets and receive proactive Telegram alerts before costs spiral.

    It works with any OpenAI-compatible endpoint, including OpenAI (GPT-4o), Anthropic (Claude 3.5 Sonnet/Haiku), DeepSeek, and local providers like Ollama or vLLM.

    No, your data is stored locally on your own server or machine; TokenTracker is a local-first CLI tool that ensures your usage logs and API keys never leave your controlled environment.

    Setup is a simple three-step process: install via npm, run the setup wizard to configure your budget and Telegram bot token, and start the 'watch' command to begin monitoring.

    Yes, the tool allows you to categorize and track usage by specific agent IDs, models, or individual tasks, giving you a granular breakdown of which projects are consuming the most tokens.

    New in Agents & Orchestration