Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    LLM Spend Receipt

    1

    Convert LLM usage exports into automated daily spend receipts with cache analysis and cost caps.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    LLM Spend Receipt

    LLM Spend Receipt

    Example session with this skill installed

    Run a spend receipt for usage.csv dated 2025-05-14. The typical daily spend is $5.00. Focus on the 'project_id' tag.

    • Read your context and instructions
    • Compiled the llm spend receipt

    Spend receipt processed for 2025-05-14. Identified a cost spike driven by prompt cache misses in the production workspace.

    Spend receipt — 2025-05-14

    Total: $12.45
    Cache: 12% of input tokens were hits (~$0.85 vs miss-price)
    Tokens: 1.2M in / 450k out / 180k cache-read / 50k cache-write
    Requests: 1,420

    By model

    • claude-3-5-sonnet $8.10 65% 800k in / 300k out cache 15%
    • claude-3-opus $4.35 35% 400k in / 150k out cache 5%

    By tag

    • production-api $9.50 76%
    • staging-tests $2.95 24%

    Blew up

    • production-api — $9.50 (76% of day)
    • day is 2.49× typical ($5.00)

    Cap

    • production-api: hard-cap near $6.50/day
    • claude-3-5-sonnet: cache hit 15% — reorder the prompt (static prefix first, variable text last)
    • account: page if a day exceeds $7.50 (1.5× typical)

    Next steps

    • Review the production-api system prompt to increase cache hits.
    • Apply the $6.50 hard-cap in the provider dashboard for the production-api key.
    • Update typical_usd to $10.00 if this new volume is the new baseline.

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

    About this skill

    The problem

    Usage dashboards are often buried behind auth walls or cluttered with irrelevant metrics. Developers lack a simple, automated way to see exactly where their daily LLM budget went without manual reconciliation.

    What it does

    • Parses provider usage CSVs or API responses into a phone-sized text receipt.
    • Calculates real cache-hit rates to show actual savings versus list prices.
    • Identifies "blow-up" events where a specific model or tag consumed a disproportionate share of the daily budget.
    • Generates actionable caps, such as hard-cap suggestions or prompt reordering for better caching.
    • Distinguishes between cache-miss, cache-read, and cache-write token buckets for accurate pricing.

    Frameworks & tools

    Python 3.10+ standard library (csv, pathlib). Supports any provider exporting CSV usage data (Anthropic, OpenAI, etc.).

    Why this beats prompting it yourself

    General-purpose prompts often fail at token bucket math, incorrectly pricing cached tokens as standard input tokens. This skill enforces strict normalization across different header aliases and ensures $0 rows from local or seat-based models are retained for an accurate view of total system load.

    Use cases

    • Automate a morning Slack/email notification showing yesterday's total model spend.
    • Audit a large agent run to see if caching strategies are actually reducing costs.
    • Identify runaway jobs in a multi-tenant environment using tag-based grouping.
    • Set baseline 'typical spend' alerts to catch billing spikes before the invoice arrives.

    Known limitations

    It is a daily operator view, not an accounting tool for invoice disputes or tax reconciliation. It does not perform multi-month forecasting.

    Requires Python 3.10+. Does not perform multi-month forecasting or invoice reconciliation. Accuracy depends on user-provided rates if the CSV lacks a cost column.

    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 2 months ago

    Requires

    Python

    Permissions

    Environment Variables
    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This skill parses raw usage data from providers like OpenAI and Anthropic to generate a simplified daily receipt, highlighting specific costs, cache-hit savings, and potential billing anomalies.

    The skill is designed to process standard CSV usage exports and JSON API responses; it is compatible with any Python-based agent environment or CI/CD pipeline.

    Unlike generic prompts, this skill uses a specialized normalization engine to correctly categorize and price cache-miss, cache-read, and cache-write tokens, which often have different price points.

    You will receive the core Python processing engine, pre-configured templates for daily receipts, and documentation on how to hook the output into notification services like Slack or Email.

    Setup is straightforward: you simply point the skill to your provider's usage export file or API endpoint, and it will output a formatted summary without requiring complex database configurations.

    This skill is a tactical FinOps tool for daily spend monitoring and optimization; it is not intended for long-term financial forecasting or formal tax and accounting reconciliation.

    New in Agents & Orchestration