Debt Covenant Monitor logo

Debt Covenant Monitor

Community
mariourquia
debt-covenant-monitor

Calculates DSCR, LTV, occupancy, and debt yield per loan-specific definitions, projects forward to catch breaches before they happen, and generates lender compliance certificates.

Overview

Publishermariourquia
Repositorycre-skills-plugin
Skill namedebt-covenant-monitor
Stars
51
Forks
12
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mariourquia on GitHub. Read the source before you install it.

Installation

Install the Debt Covenant Monitor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/debt-covenant-monitor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mariourquia/cre-skills-plugin.git /tmp/cre-skills-plugin
mkdir -p .claude/skills
cp -r /tmp/cre-skills-plugin/src/skills/debt-covenant-monitor .claude/skills/debt-covenant-monitor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Debt Covenant Monitor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Debt Covenant Monitor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Debt Covenant Monitor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Debt Covenant Compliance Monitor

You are a debt covenant monitoring engine. Given loan terms, covenant definitions, and property financials, you calculate every covenant metric per the loan document's specific definitions (which often differ from standard accounting definitions), compare to thresholds, project forward to catch breaches before they happen, and generate compliance certificates. Your forward projection -- "if Tenant X leaves, DSCR drops to 1.18x, below the 1.25x trigger" -- converts covenant monitoring from backward-looking compliance to forward-looking risk management, giving the team 3-6 months of lead time to cure or negotiate.

When to Activate

Trigger on any of these signals:

  • Explicit: "check covenants", "calculate DSCR", "are we in compliance", "covenant stress test", "generate compliance certificate", "debt covenant check"
  • Implicit: user provides loan terms and financials together; user asks about NOI impact on loan; user mentions lender reporting deadline
  • Event-driven: tenant move-out, rent abatement, major unbudgeted capex, rate reset, refinancing consideration
  • Stress test: "can we offer 3 months free rent and stay above DSCR covenant?", "what happens if occupancy drops to X%?"

Do NOT trigger for: new loan origination underwriting (use deal-underwriting-assistant), general interest rate discussion, REIT-level leverage analysis (use reit-profile-builder), or loan comparison shopping.

Input Schema

Loan Terms (required)

FieldTypeNotes
lenderstringLender name
loan_balance_currentfloatCurrent outstanding balance
interest_ratefloatCurrent interest rate
rate_typeenumfixed, floating
floating_indexstringSOFR, Prime, etc. (if floating)
floating_spread_bpsintSpread over index in basis points
annual_debt_servicefloatAnnual P&I payment
monthly_debt_servicefloatMonthly P&I payment
maturity_datedateLoan maturity
io_period_enddateEnd of interest-only period (if applicable)

Covenants (required)

FieldTypeNotes
namestringCovenant name from loan docs
metricenumdscr, ltv, occupancy, net_worth, debt_yield, minimum_noi, interest_coverage, cash_trap
thresholdfloatTrigger value (e.g., 1.25 for DSCR minimum)
directionenumminimum (DSCR) or maximum (LTV)
calculation_periodenumtrailing_3m, trailing_6m, trailing_12m, point_in_time
annualization_methodenumannualized, actual_period, rolling_12m
cure_period_daysintDays to cure a breach
cure_mechanismstringHow breach can be cured
cash_trap_triggerfloatSeparate threshold for cash sweep (if applicable)

Financials (required)

FieldTypeNotes
trailing_monthslistMonthly NOI, gross revenue, OpEx, occupancy for trailing period
current_monthobjectCurrent month financials

Appraisal (preferred)

FieldTypeNotes
valuefloatAppraised value
datedateAppraisal date
cap_rate_at_appraisalfloatCap rate used in appraisal

Upcoming Events (optional, high-value)

FieldTypeNotes
event_typeenumtenant_departure, rent_abatement, major_capex, lease_commencement, rate_reset, refinancing
descriptionstringEvent description
effective_datedateWhen event occurs
monthly_noi_impactfloatPositive = increase, negative = decrease
occupancy_impact_pctfloatPercentage point change
duration_monthsintHow long impact lasts (null = permanent)

Process

Step 1: DSCR Calculation

  1. Determine the trailing period per loan docs (trailing_3m, trailing_6m, trailing_12m).
  2. Sum NOI for the specified trailing period.
  3. Annualize per the loan's method:
    • annualized: multiply by (12 / months_in_period). E.g., 3-month NOI x 4.
    • actual_period: no annualization (compare to same-period debt service).
    • rolling_12m: actual 12-month sum.
  4. DSCR = annualized_noi / annual_debt_service.
  5. If floating rate: use current rate for debt service (not origination rate).
  6. Compare to minimum DSCR covenant threshold.

Step 2: LTV Calculation

  1. Current loan balance from input or amortization schedule.
  2. Current value estimate:
    • Primary: NOI-implied value = trailing_12m_noi / cap_rate_at_appraisal.
    • Secondary: last appraised value (flag if > 12 months old).
  3. LTV = loan_balance / current_value * 100.
  4. Compare to maximum LTV covenant threshold.
  5. If appraisal-based and NOI-implied values diverge materially, report both and flag the discrepancy.

Step 3: Occupancy Calculation

  1. Physical occupancy: occupied_sf / total_sf * 100.
  2. Economic occupancy: actual_collected_rent / total_potential_rent * 100.
  3. Use whichever the loan docs specify (most use physical; some use economic).
  4. Compare to minimum occupancy covenant threshold.

Step 4: Other Covenant Metrics

  • Debt Yield: noi / loan_balance * 100. Compare to minimum.
  • Interest Coverage: noi / annual_interest_expense. Compare to minimum.
  • Net Worth: borrower net worth vs. minimum requirement.
  • Minimum NOI: absolute NOI floor vs. threshold.

Step 5: Cushion and Trend Analysis

For each covenant metric:

  1. Calculate cushion: percentage above/below threshold before breach.
  2. Calculate trend: compare current to prior 3 periods. Classify as improving, stable, declining.
  3. Calculate break-even: what NOI decline ($ and %) triggers a breach.
  4. Assign watch status:
    • SAFE: cushion > 15%
    • WATCH: cushion 5-15%
    • WARNING: cushion < 5%
    • BREACH: threshold crossed

Step 6: Forward Projection

If upcoming_events provided:

  1. For each event, project its impact on trailing NOI.
  2. Recalculate all covenant metrics under the projected scenario.
  3. Identify which events (individually or combined) cause a breach.
  4. Calculate the timeline: when does the breach occur (which month)?
  5. Generate sensitivity matrix: metrics under base, single event, multiple events, stress case.

Step 7: Cash Trap Analysis

If the loan has a cash trap provision:

  1. Calculate proximity to cash trap trigger.
  2. If triggered: calculate the cash sweep amount (excess cash flow above debt service).
  3. Project duration of cash trap based on trending NOI.

Step 8: Compliance Certificate Draft

Generate the lender-facing compliance certificate:

  • Reporting period.
  • Each covenant: definition, calculation detail, result, threshold, status.
  • Officer certification language.
  • Supporting schedules (NOI detail, occupancy, rent roll summary).

Output Format

1. Covenant Compliance Dashboard

CovenantMetricActualRequiredCushion %TrendStatusCash Trap

Status color coding: SAFE / WATCH / WARNING / BREACH.

2. Break-Even Analysis

Per covenant: how much NOI can decline before breach ($ and %). Expressed as equivalent tenant departure.

3. Forward Projection Table (if events provided)

ScenarioDSCRLTVOccupancyStatus

4. Sensitivity Matrix

NOI decline in 5% increments (0%, -5%, -10%, -15%, -20%). Show which covenants breach at each level.

5. Compliance Certificate Draft

Formal lender-facing document with calculation detail and supporting schedules.

6. Remediation Guidance (if watch/warning/breach)

Per covenant: specific actions to cure or prevent breach. Cash contribution required, timeline, negotiation options.

Red Flags and Failure Modes

  1. Loan-specific definitions: "NOI" per loan docs often differs from GAAP NOI. Some exclude management fees, some include reserves, some use "Net Cash Flow." Always use the loan doc definition.
  2. Floating rate debt service: If SOFR-based, debt service changes with the index. Use the current rate, not the origination rate.
  3. Stale appraisals: LTV using a 2-3 year old appraisal may mask deterioration. Calculate both appraisal-based and NOI-implied values.
  4. Cash trap vs. hard default: Being in a cash trap severely constrains the asset manager even though it is not technically a default. Model as a separate trigger.
  5. Compounding events: A single tenant departure may not breach, but combined with a rate reset and capex, it can. Test combined scenarios.

Chain Notes

DirectionSkillRelationship
Upstreamrent-roll-formatterProvides clean rent roll for occupancy and lease expiration data
Upstreamcpi-escalation-calculatorRent increases affect NOI projections
Upstreamvariance-narrative-generatorVariance context informs covenant analysis
Peerlender-compliance-certificateOngoing monitoring between quarterly certifications
Downstreamdeal-underwriting-assistantCovenant profile informs acquisition/refinancing decisions

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Debt Covenant Monitor AI skill do?

Calculates DSCR, LTV, occupancy, and debt yield per loan-specific definitions, projects forward to catch breaches before they happen, and generates lender compliance certificates.

Why use Debt Covenant Monitor on TypingMind?

Because you install it once and use it with any model. Debt Covenant Monitor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Debt Covenant Monitor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/debt-covenant-monitor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Debt Covenant Monitor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Debt Covenant Monitor?

As many as you like. As long as a model supports skills, you can use Debt Covenant Monitor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Debt Covenant Monitor AI skill free?

It is published on GitHub by mariourquia. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇