AI Agent Usage

    1

    Local token and cost report across the coding agents already on this machine. Costs are list-price estimates. Prompts and responses are never read.

    $5

    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

    AI Agent Usage

    Example session with this skill installed

    What did my coding agents cost over the last 7 days, and which model cost the most?

    • Read your context and instructions
    • Compiled the ai agent usage

    Last 7 days: $15.51 estimated across 338 calls. By model, Claude Sonnet is the largest share. One model is unpriced (26k tokens) and is left out of the total, not counted as $0. Costs are public list prices, not an invoice.

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

    About this skill

    Reports token use and estimated cost from the coding agents already installed on the buyer's machine: Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Pi, Cowork, and Antigravity.

    The agent runs the local CLI. It does not open transcripts, session logs, or editor databases. The tool stores counts, ids, names, and byte sizes only.

    Costs are public list-price estimates, not an invoice. Unmatched models stay unpriced and are never shown as $0. A later price-list change prices new calls only.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Requires the ai-agent-usage checkout and Bun. Does not read agents that are not installed. Does not model long-context surcharges. Calls that already have a cost are not repriced when a list changes.

    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 4 days ago

    Accounts
    GitHub
    Software
    BunGit

    Permissions

    Allowed Hosts

    github.com

    File Scopes

    ~/.local/share/agent-usage/usage.db
    local
    coding-agent
    logs

    Reads agent metadata only. Does not read prompts, responses, or tool output.

    Listed4 days ago

    What's inside

    Frequently Asked Questions

    No. The tool stores counts, ids, names, and byte sizes only. Prompts, responses, thinking text, and tool output stay on your machine and are not read.

    No. Costs are estimates at public list price. Long-context surcharges are not included. Unmatched models are left unpriced.

    New in LLM Ops