- Home
- Skills
- Research & Analysis
- Debt Covenant & DSCR Monitor
More screenshots
Works with the AI Agents you already use
Debt Covenant & DSCR Monitor
Tests financials against loan, bond and NCD covenants, shows headroom and EBITDA cushion, flags breaches early, and drafts the compliance certificate and waiver request.
$5
Debt Covenant & DSCR Monitor
Example session with this skill installed
FY26: EBITDA 54 cr, PAT 22, depreciation 12, interest 14, principal repaid 20, debt 210, cash 25, secured fixed assets 300. Covenants: DSCR >= 1.25, net debt/EBITDA <= 3.0, ICR >= 2.5, FACR >= 1.5.
- Read your context and instructions
- Compiled the debt covenant
BREACH on 2 of 4. Net debt/EBITDA is 3.43x vs 3.0x (needs about 7.7 cr more EBITDA or 23 cr less net debt). FACR is 1.43x vs 1.5x (needs about 10 cr debt reduction or additional security). DSCR 1.41x is GREEN but EBITDA can fall only 10.2% before it breaks. ICR 3.86x is GREEN. Includes a compliance certificate, a waiver letter and a SEBI LODR / Ind AS 1 classification check.
Connects securely to your tools. The creator never sees your data.
About this skill
A covenant breach the lender finds is a crisis. A breach the CFO forecast and pre-negotiated is just a conversation. Built by a listed-company CFO who has signed quarterly covenant certificates for bank loans and rated NCDs.
It reads covenants exactly as defined in your sanction letter, facility agreement or debenture trust deed. Definitions matter: cash-accrual vs EBITDA DSCR, gross vs net debt, lease liabilities in or out, and tangible net worth. It then tests every period, including forecasts, for DSCR, ICR, Debt/EBITDA, net debt/EBITDA, D/E, TOL/TNW, current ratio and FACR.
For each covenant you get headroom, GREEN/AMBER/BREACH status and the EBITDA cushion (how far EBITDA can fall before it breaks). It also produces quantified fix options, a ready-to-sign compliance certificate, a waiver/consent letter when needed, and a listed-company disclosure and Ind AS 1 / IAS 1 debt-classification check.
Includes a tested, standard-library Python engine with CSV export.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Uses standard formulas unless you supply facility definitions; the signed documents always prevail. Not legal advice.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
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 23 days ago
Nothing to install. It runs in your AI agent.
- Optional
Python 3
Python runs the covenant engine.
Permissions
File Scopes
No network access. Standard library only.