Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsRed-Flag Scanner
Scan early deal material for the warning signs that quietly kill deals, concentration, owner dependence, lumpy revenue, add-back abuse, deferred capex, each...
$9
Red-Flag Scanner
Example session with this skill installed
Use the Red-Flag Scanner skill. This is everything I have so far on Project Sentinel (Sentinel Fire & Safety, Inc.): the CIM (24 pages), the management-prepared financial statements (5 pages, unaudited), the 2025 tax return (2 pages) and my notes from a management call (1 page). Page numbers are the printed footers.
Scan for the things that quietly kill deals. Rank the flags, quote the evidence, say why each matters and what question it raises. Label anything unconfirmed "to verify" and do not invent concerns.
- Read your context and instructions
- Compiled the red-flag scanner
Red-flag scan: Project Sentinel
Sources: CIM, FS (financial statements), Tax (2025 return), Call (buyer's call notes). Arithmetic marked "mine" is my own calculation.
Ranked flags
| # | Flag | Severity |
|---|---|---|
| 1 | Customer concentration, and the CIM contradicts itself | High |
| 2 | Owner and licence dependence | High |
| 3 | Add-back load in adjusted EBITDA | High |
| 4 | Revenue figures do not reconcile | Medium |
| 5 | System of record with untested data export | Medium |
| 6 | Change-of-control provisions unreviewed | Medium |
| 7 | "Recurring" includes repair work | Medium |
| 8 | Legal settlement called one-time | To verify |
1. Customer concentration. Evidence: "no single customer representing more than 15% of revenue" (CIM p.8), then "Northgate Property Group represents approximately 22% of total revenue" at $1,366,000 (CIM p.9). Top ten about 61% (CIM p.9); the five listed accounts total $3,030,000, 48.8% of $6.21M (mine). Why it matters: losing Northgate removes 22.0% of revenue. Question: what are Northgate's contract term, renewal date and termination rights?
2. Owner and licence dependence. Evidence: the founder "holds the state-issued fire protection contractor license under which all Company work is performed" and the buyer must "evaluate how the licence transfers or is replaced at close" (CIM p.14). Management is the founder plus an operations manager and an office administrator (CIM p.13). Question: who else could hold the licence, and what does the state require?
3. Add-backs. Evidence: reported EBITDA $1.08M adjusted to $1.42M by $210,000 owner compensation, $65,000 legal settlement, $41,000 vehicle and travel and $24,000 charity (FS p.4). That is $340,000, 31.5% of reported EBITDA (mine). The seller itself says each adjustment "should be independently assessed" (FS p.4). Question: what documents support each one?
4. Revenue does not reconcile. Evidence: TTM revenue $6.21M (CIM p.6, FS p.2) against tax-year 2025 gross receipts of $5,950,000 (Tax p.1), a $260,000 gap, 4.2% of TTM (mine). The periods are not stated to match. Question: which twelve months does each cover?
5. Data continuity. Evidence: the seller notes data export from the 2009 system "has not been tested" (CIM p.16); management said "exporting the data out is no problem at all" (Call p.1). The two statements conflict.
6. Change of control. Evidence: the seller "has not undertaken a review" of consent or assignment provisions (CIM p.19). Not known whether Northgate's agreement has one.
7. Recurring definition. Evidence: 78% is "inclusive of any repair or call-out work performed for those accounts" (CIM p.22), and repair work "varies with building age and incident volume" (CIM p.7).
8. Legal settlement (to verify). Evidence: "one legal settlement in the prior year" (CIM p.17); management said it was "a one-time matter" (Call p.1). Nature and counterparty are not in the materials.
Checked, not raised
Declining revenue (the three figures rise: $5.34M, $5.78M, $6.21M, FS p.2), margin erosion, deferred capex and supplier exposure: the materials contain no data to flag them. That is not a clean bill of health; it is missing data.
This scan 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
Scan early deal material for the warning signs that quietly kill deals, concentration, owner dependence, lumpy revenue, add-back abuse, deferred capex, each cited and ranked. Use on any early document, or when asked to 'find the red flags', 'what could go wrong here', or 'scan this for risks'.
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:
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 4 days ago
- Passed all security checks, Safe to install