Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    claude code usage dashboard

    1

    Analyze local Claude Code transcripts to report token usage and estimate API-equivalent costs.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    claude code usage dashboard

    claude code usage dashboard

    Example session with this skill installed

    Show me a breakdown of my Claude Code usage and estimated costs for the last 7 days.

    • Read your context and instructions
    • Compiled the claude code usage

    I have analyzed your local Claude Code transcripts from the last 7 days.

    Claude Code Usage Report (Last 7 Days)

    Window Totals

    • Today: 45,201 tokens, $0.68, 12 responses
    • Last 7 days: 284,150 tokens, $4.26, 82 responses
    • Last 30 days: 1,120,400 tokens, $16.81, 310 responses

    By Model

    ModelInputCache WriteCache ReadOutputCost
    claude-3-7-sonnet-20250219150,20045,00080,0008,950$3.45
    claude-3-5-haiku-2024102242,000005,200$0.81

    Top 5 Projects

    • api-gateway: 92,100 tokens ($1.38)
    • frontend-ui: 75,400 tokens ($1.13)
    • auth-service: 55,200 tokens ($0.83)
    • utils-lib: 40,300 tokens ($0.60)
    • docs-site: 21,150 tokens ($0.32)

    Cost is an API-equivalent estimate at list prices, not your bill. Pro, Max and Team plans are billed differently.

    Next steps

    1. Run node scripts/usage.mjs serve to view these trends in a browser dashboard.
    2. To see usage for a specific project only, use the --include <alias> filter.
    3. If you work on multiple machines, use export to sync this data to a shared volume.

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

    About this skill

    Claude Code logs usage data locally, making it difficult to track total spend or compare activity across multiple development machines. This skill parses local transcripts to provide a clear view of token consumption and estimated API costs without sending your data to external servers.

    What it does

    • Token tracking aggregates input, output, and cache hit/miss tokens from local session logs.
    • Cost estimation calculates API-equivalent spending based on current Anthropic list prices.
    • Multi-machine sync combines usage from different workstations via a shared folder export.
    • Visual dashboard launches a local browser interface for charts and project-level breakdowns.
    • Granular filtering isolates usage by specific projects, time ranges, or model types.

    How it works

    1. Verify environment by checking for Node 18+ on the host system.
    2. Scan transcripts located in the default Claude configuration directories.
    3. Generate report using the preview command for terminal summaries or serve for the web UI.
    4. Aggregate shards if the user provides a shared directory containing exports from other machines.

    Frameworks & tools

    Built with Node.js. Uses Chart.js via CDN for the web dashboard. Requires no external database or account.

    Why this beats prompting it yourself

    Manual calculation of cache-aware token pricing is error-prone and tedious. This skill automates the parsing of complex local session files and handles cross-machine data deduplication that a basic prompt cannot access or process reliably.

    Use cases

    • Audit weekly Claude Code spend across a distributed engineering team.
    • Identify which local projects are consuming the most tokens.
    • Compare the cost-efficiency of different models during development tasks.
    • Export usage history before decommissioning a temporary dev environment.

    Known limitations

    Requires Node 18 or higher. Only tracks usage recorded in local transcript files. Estimates reflect list API prices which may differ from Pro or Team plan billing.

    Requires Node 18+. Pricing estimates use API list rates and may not match Pro/Team plan billing. Shared dashboard requires internet for Chart.js CDN.

    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 5 days ago

    Requires

    Cloudflare
    cc-logbook
    Node.js

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Environment Variables

    Allowed Hosts

    cdnjs.cloudflare.com
    ${host}
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    The dashboard parses your local Claude Code session logs to calculate input, output, and cache tokens, then applies current Anthropic pricing to provide a visual breakdown of your development spend.

    No data is sent to external servers; the skill runs entirely on your local machine and uses a local browser interface to display charts from your own transcript files.

    Yes, you can export session shards to a shared folder, allowing the skill to aggregate usage data from multiple workstations into a single unified report.

    This skill is a standalone Node.js utility designed specifically to work with Claude Code's local transcript architecture; it requires Node 18+ to be installed on your system.

    The tool distinguishes between input, output, and cache hits/misses to provide an accurate estimate based on Anthropic's tiered pricing for prompt caching.

    You receive the full skill package, including the CLI parser, the web-based dashboard interface, and documentation for local installation and multi-machine syncing.

    New in LLM Ops