Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Multiple Sanity-Checker

    1

    Give a plain reality check on price before you anchor, the implied multiple shown, whether it's rich/cheap/fair for the profile, what you'd be betting on,...

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Multiple Sanity-Checker

    Multiple Sanity-Checker

    Example session with this skill installed

    Use the Multiple Sanity-Checker skill. I am thinking of offering $5.0M enterprise value, cash-free and debt-free, for Project Sentinel (Sentinel Fire & Safety, Inc.). That $5.0M is my own idea, not a number from the documents; no asking price has been given.

    From the financial statements (page 4): reported EBITDA $1.08M, seller-adjusted EBITDA $1.42M. Profile from the CIM and financials: TTM revenue $6.21M, prior years $5.78M and $5.34M, 78% recurring (defined broadly), largest customer about 22%, founder-held licence, unaudited statements. Am I overpaying?

    • Read your context and instructions
    • Compiled the multiple sanity-checker

    Multiple sanity check: $5.0M for Project Sentinel

    1. Implied multiple (calculation shown)

    EBITDA basisEBITDA$5.0M / EBITDA
    Reported (FS p.4)$1.08M4.63x
    Seller-adjusted (FS p.4)$1.42M3.52x
    Adjusted less the $210,000 owner-compensation add-back (mine)$1.21M4.13x
    Adjusted without the $65,000 settlement add-back, if it was not booked in the period (mine)$1.355M3.69x

    The honest multiple is not 3.5x. The $1.42M includes $340,000 of add-backs, 31.5% of reported EBITDA, none backed by documents yet. If you must hire a manager to replace the owner, 4.1x is closer.

    2. Is that reasonable, rich or cheap for this profile?

    Working band I am using: roughly 3.5x to 5.5x EBITDA for a business of this size and profile. That is general benchmark reasoning (my estimate), not a market database or a formal valuation, so challenge it.

    Pushes up: code-driven demand, 78% recurring on the seller's definition, growth of 8.2% and 7.4% (FS p.2, mine, years undated), a two-decade history.

    Pushes down: top account about 22% and top ten about 61% (CIM p.9), founder-held licence (CIM p.14), unaudited statements (FS p.5), "recurring" includes repair work (CIM p.22), 2009 system with untested export (CIM p.16).

    View: $5.0M is inside the band on every basis, in the lower-to-middle part. It is not an overpayment on the seller's number, and it is fair, not cheap, on a realistic number. That conclusion depends on the add-backs surviving, which is unproven.

    3. What you would be betting on

    • That the $130,000 of non-owner add-backs ($65,000 + $41,000 + $24,000) survives a change of ownership, and that the $210,000 owner add-back survives a replacement-manager cost. If only $1.21M is real, you pay 4.1x.
    • That Northgate ($1,366,000, CIM p.9) stays through the transition.
    • That the founder's licence can be transferred or replaced (CIM p.14).
    • That the 2009 system's data can be extracted (CIM p.16).

    4. The case for offering less

    • Revenue does not reconcile: TTM $6.21M against tax-year 2025 receipts of $5.95M, a $260,000 gap (Tax p.1; mine). Until explained, the earnings base is soft.
    • Losing Northgate would remove 22.0% of revenue. The EBITDA effect cannot be sized because customer margin is not in the materials.
    • A structure can bridge it without cutting the headline: tie part of the $5.0M to Northgate staying for a stated period, or to the add-backs being proven.

    Missing inputs

    Gross margin, cash flow, capex, debt and working capital are not in the materials, so this check is on EBITDA only.

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

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

    About this skill

    Give a plain reality check on price before you anchor, the implied multiple shown, whether it's rich/cheap/fair for the profile, what you'd be betting on, and the case for offering less. Use before anchoring on a price or making an offer, or when asked to 'am I overpaying', 'sanity-check this multiple', or 'is this price reasonable'.

    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 from the price, earnings and business profile you give it and uses general benchmark reasoning. It does not use a market database and is not a formal valuation.

    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=multiple-sanity-checker

    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

    Give a plain reality check on price before you anchor, the implied multiple shown, whether it's rich/cheap/fair for the profile, what you'd be betting on,...

    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 Multiple Sanity-Checker 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