Spend Tracker

    1

    Per-model and per-session Claude Code usage report from your local transcripts, with interactive and background claude -p calls split out.

    $3

    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 CLIMuseMuseDotsDots+21 more

    Spend Tracker

    Example session with this skill installed

    python3 spend_tracker.py

    • Read your context and instructions
    • Compiled the spend tracker

    INTERACTIVE table by model (calls, input, output, cache_rd, est $), HOOK table for logged claude -p calls, TOTAL est., and top interactive sessions by cost.

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

    About this skill

    See where your Claude Code usage goes. Spend Tracker reads the session transcripts Claude Code already writes and reports tokens and estimated cost per model and per session. No instrumentation needed.

    What you get

    • spend_tracker.py, a single stdlib-only Python file.
    • Per-model table: calls, input, output and cache-read tokens, estimated dollars.
    • Top sessions by cost, monthly filter (--month YYYY-MM or all), --json output.
    • Optional log for background claude -p calls. Those write no transcript, so call log_hook_call() after each one to include them, using the CLI-reported total_cost_usd.
    • Prices are placeholders you can override with a JSON file (CLAUDE_SPEND_PRICES). Token counts are exact; dollars are estimates.

    Everything is read locally. Nothing is sent anywhere.

    Tested on real transcripts and with logged hook calls.

    Dollar figures are list-price estimates from a placeholder price table; check and override the prices for your account. Ignores subscription plans, discounts and batch pricing. Reads only transcripts on the local machine; deleted transcripts are gone from the report. Models whose id matches no price key show tokens with $0.

    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 any payment.

    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 13 days ago

    Requires

    Python 3.9+
    Claude Code

    Permissions

    File Scopes

    claude
    config
    dir
    /projects/**/*.jsonl
    (read)
    /spend/spend.db
    (read/write)
    $CLAUDE_SPEND_PRICES
    JSON
    file
    (read
    optional)

    No network access.

    Listed13 days ago

    What's inside

    Frequently Asked Questions

    Per-model and per-session Claude Code usage report from your local transcripts, with interactive and background claude -p calls split out.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use Spend Tracker on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in LLM Ops