Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Token Unit Economics

    1

    Builds structured per-unit cost models for tokens, infra, and support with automated sensitivity analysis.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Token Unit Economics

    Token Unit Economics

    Example session with this skill installed

    Generate a unit economics model for 'QueryWriter' where a unit is one 'generated report'. Volume is 5000/mo. Rates as of 2024-05-20: $10/1M input, $30/1M output. 500 input/200 output tokens.

    • Read your context and instructions
    • Compiled the token unit economics

    I have generated the unit economics model for QueryWriter. The analysis shows the relationship between token consumption, fixed infra amortization, and support overhead.

    Unit Economics: QueryWriter

    Product: QueryWriter
    Unit: Generated Report
    Base Volume: 5,000 / month
    Rates As Of: 2024-05-20
    Currency: USD
    Status: Ready

    Not tax, legal, or investment advice.

    Unit Definition

    One generated report covers the end-to-end lifecycle from user prompt submission to the final Markdown delivery.

    Frozen Rates

    ItemRateUnit
    Cache-miss Input$10.00per 1M tokens
    Output$30.00per 1M tokens
    Support Hourly$50.00per hour
    Fixed Infra$250.00per month

    Costs

    • Tokens: (500/1M * 10) + (200/1M * 30) = $0.0110
    • Infra (Fixed): 250 / 5000 = $0.0500
    • Support: 0 mins = $0.0000
    • Total Per Unit: $0.0610

    Unit Table

    MetricPer UnitMonthly (5k units)
    Tokens$0.0110$55.00
    Infra (Amortized)$0.0500$250.00
    Support$0.0000$0.00
    Total Cost$0.0610$305.00
    Priceunsetunset

    Sensitivity Analysis (Total Cost Per Unit)

    Volume0.5x (2.5k)1x (5k)2x (10k)
    Cost$0.1110$0.0610$0.0360
    Token Multiplier0.7x1x1.5x
    Cost$0.0577$0.0610$0.0665

    Next Steps

    1. Review the docs/unit-economics.md file for full arithmetic.
    2. Provide a price_per_unit to calculate contribution margins.
    3. Load the pricing-one-pager skill to determine list pricing based on these costs.

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

    About this skill

    The problem

    Predicting the profitability of an AI feature is difficult when token costs, infrastructure overhead, and human support burdens are spread across different billing cycles. Calculating margins without a structured model leads to underpriced products and unexpected cloud bill shocks.

    What it does

    • Calculates granular token costs by separating cache-miss, output, cache-read, and cache-write buckets.
    • Amortizes fixed infrastructure lumps and variable egress costs across specific unit volumes.
    • Models human support costs based on per-unit minute requirements and loaded hourly rates.
    • Generates a 3-axis sensitivity table covering volume fluctuations, token multipliers, and support scaling.
    • Produces a standardized docs/unit-economics.md artifact for team-wide financial alignment.

    Frameworks & tools

    This is a methodology-driven skill compatible with any agent environment capable of file system operations (read/write) and basic arithmetic. It integrates with WORKFORCE.md specifications for multi-agent coordination.

    Why this beats prompting it yourself

    General prompts often conflate cache-hit rates with expensive input tokens, leading to wildly inaccurate cost projections. This skill enforces a strict procedure that prevents price invention, handles fixed vs. variable infra correctly, and includes non-negotiable legal disclaimers to ensure financial data is handled responsibly.

    Use cases

    • Determining the cost-per-session for a new LLM-powered chat interface.
    • Evaluating how a 50% increase in token usage affects unit margins.
    • Calculating the minimum volume required to cover monthly fixed hosting seats.
    • Auditing the support burden of a specific feature before setting a list price.

    Known limitations

    Does not provide tax, legal, or investment advice. It cannot access live bank or processor accounts. It models single units only and does not perform multi-option TCO comparisons.

    Single-unit modeling only. No live financial integrations. Does not set list prices or provide tax/investment advice. Requires buyer-supplied rates and dated volume inputs.

    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

    Read Files
    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This skill analyzes four distinct token cost buckets (cache-miss, output, cache-read, and cache-write) alongside infrastructure and human support overhead to provide a high-fidelity view of your actual cost-per-unit.

    The skill is designed for any AI agent environment with file system access and basic math capabilities, and it is specifically optimized for systems using WORKFORCE.md orchestration.

    You receive the core logic for the unit economics methodology, a standardized documentation template, and the automated sensitivity analysis workflow for your agent.

    It generates a structured docs/unit-economics.md file that includes a 3-axis sensitivity table, allowing your team to visualize how margins change as token volume and support needs scale.

    No, this skill is a methodology-driven modeling tool; it does not require access to live financial accounts or sensitive API billing keys to function.

    The skill handles single-unit profitability modeling for specific features or agents, rather than comparing multiple different software vendors or performing total cost of ownership (TCO) audits.

    New in Finance & Accounting