Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Customer-Concentration Agent

    1

    Stress-test revenue quality and customer risk, concentration, stickiness, the 'what if we lost the top customer' scenario, and the gaps to close.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Customer-Concentration Agent

    Customer-Concentration Agent

    Example session with this skill installed

    Use the Customer-Concentration Agent on Project Sentinel (Sentinel Fire & Safety, Inc.). The data I have is in the CIM (24 pages, sections on revenue composition, customers, concentration, contracts and change of control), the unaudited financial statements and my call notes. Printed page numbers.

    The CIM says the base is "well diversified". Test that claim against the data and tell me how fragile the revenue is.

    • Read your context and instructions
    • Compiled the customer-concentration agent

    Customer concentration: Project Sentinel

    Data used: CIM p.7, p.8, p.9, p.18, p.19, p.22; FS p.4; Call p.1. TTM revenue is $6.21M (CIM p.6). Mine = my arithmetic.

    1. Concentration

    Account (CIM p.9)TTM revenueShare
    A, Northgate Property Group$1,366,00022.0%
    B$544,0008.8%
    C$431,0006.9%
    D$388,0006.2%
    E$301,0004.8%
    Top five$3,030,00048.8%
    Accounts 6 to 10 (implied)about $0.76Mabout 12.2%
    Top ten (CIM: "approximately 61%")about $3.79M61%
    All other accounts (implied)about $2.42M39%

    The claim fails its own test. The CIM says "no single customer representing more than 15% of revenue" (CIM p.8). Its next section says Northgate "represents approximately 22%" (CIM p.9). A 15% ceiling on $6.21M is $931,500; Northgate exceeds it by $434,500 (mine). Management repeated the claim on the call: "nobody's over fifteen percent" (Call p.1). Accounts 6 to 10 are not listed, and the number of customers is not stated.

    2. Stickiness

    • Written agreements, "typically multi-year with automatic renewal terms" (CIM p.18). Term, renewal dates and termination rights are not given.
    • 78% "recurring" (CIM p.7), defined as all revenue from accounts with an active inspection agreement, including repair and call-out for them (CIM p.22). So some of the 78% moves with building age and incident volume (CIM p.7).
    • Churn, retention and rebid history: not stated.
    • Switching cost: the inspection records sit in a 2009 system whose export is untested (CIM p.16). That is a transition risk for you, not necessarily protection for the seller.
    • Change of control: the seller has not reviewed provisions that "may" be triggered by a sale (CIM p.19). Whether Northgate's agreement has one is unknown.

    3. If we lost the top customer

    Revenue falls from $6.21M to $4.84M, down 22.0% (mine). Profit impact cannot be read from the documents, because customer margin and fixed costs are not provided. An illustration only, assuming Northgate earns the average reported margin of 17.4% (assumption, mine): reported EBITDA of $1.08M would fall by about $238,000, to about $842,000, down 22%. Because fixed costs such as technicians and vehicles would not leave with the customer, the real loss could be larger.

    4. Questions that close the gaps

    1. Northgate: term, renewal date, termination and consent clauses, pricing history, who holds the relationship.
    2. Full customer revenue schedule: all accounts, with the number of customers.
    3. Revenue by type (fixed inspection fee vs repair vs call-out) for each of the top five.
    4. Churn and rebid history for three years, including any lost account.
    5. Is Northgate one entity or a group of properties under separate agreements?

    This is an analytical aid and not investment, legal, tax or accounting advice. The Project Sentinel documents are synthetic test data.

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

    About this skill

    Stress-test revenue quality and customer risk, concentration, stickiness, the 'what if we lost the top customer' scenario, and the gaps to close. Use whenever you have customer or revenue-mix data, or when asked to 'check customer concentration', 'how fragile is this revenue', or 'what's the churn risk'.

    Works with

    Any agent that reads the SKILL.md standard and can read attached documents. No scripts, no network access, no installs.

    Known limitations

    It works only from the documents you provide and cannot verify anything outside them. Analysis, not investment, legal, tax or accounting advice; check the output against the source documents.

    About the author

    Original work, listed by its author: part of the free, MIT-licensed open-deal-kit,

    https://github.com/MariusGithub13/open-deal-kit

    The hosted version that writes a fully cited diligence brief across a whole data room is Deal OS:

    https://getdealos.tech/sandbox?utm_source=agensi&utm_medium=marketplace&utm_campaign=customer-concentration-agent

    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 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    Stress-test revenue quality and customer risk, concentration, stickiness, the 'what if we lost the top customer' scenario, and the gaps to close.

    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 Customer-Concentration Agent 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 Finance & Accounting