refinance-analysis

refinance-analysis is a command for Claude Code from alexclowe/awesome-claude-cowork-plugins. It costs 14 tokens per session (854 once invoked), scanned A, original, MIT.

A mortgage refinance analysis tool that compares a borrower's current loan with a proposed replacement loan. It includes a break-even timeline, meaning how long it takes savings to cover refinancing costs.

In plain words
What is it for?
Use it to compare current and proposed loan balances, rates, terms, payments, mortgage insurance, and closing costs. It can organise scenarios for lower payments, shorter terms, or cash-out refinancing.
Why use it?
A lower interest rate or payment may not outweigh closing costs, especially if the borrower moves soon. It helps show the costs, savings, and time needed to recover those costs.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the mortgage-broker plugin — 1 skill, 3 commands shipped together

Good fit Use it to compare current and proposed loan balances, rates, terms, payments, mortgage insurance, and closing costs. It can organise scenarios for lower payments, shorter terms, or cash-out refinancing.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alexclowe/awesome-claude-cowork-plugins/refinance-analysis
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-plugins

Made for: Claude Code.

Or install mortgage-broker, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for refinance-analysis

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/refinance-analysis/github.svg)](https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/refinance-analysis)
Your own site
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/refinance-analysis"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/refinance-analysis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for refinance-analysis

Your own site · 80×15
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/refinance-analysis"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/refinance-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 854 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00854
Opus 5.5 $0.00006 $0.00342
Sonnet 5.5 $0.00003 $0.00171
Haiku 4.5 $0.00001 $0.00085

Measured 23d ago against content hash e090f9077080, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refinance-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

mortgage-broker/commands/refinance-analysis.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a mortgage lending assistant helping a mortgage broker create refinance analysis reports for borrowers.

The user will provide details about a borrower's current mortgage and proposed refinance terms — this may include current rate, balance, remaining term, proposed rate, closing costs, and the borrower's goals (lower payment, shorter term, cash-out). Your job is to generate a clear analysis that helps the borrower make an informed decision.

Refinance analysis format

REFINANCE ANALYSIS

Prepared for: [Borrower name or placeholder]
Date: [Current date or as provided]
Loan Officer: [To be signed]
Property: [Address or placeholder]

CURRENT LOAN:
- Original Loan Amount: $[Amount]
- Current Balance: $[Amount]
- Interest Rate: [Rate %]
- Loan Type/Term: [e.g., 30-year fixed]
- Monthly P&I: $[Amount]
- Remaining Term: [Months/Years]
- PMI: $[Amount/month] or N/A

PROPOSED REFINANCE:
- New Loan Amount: $[Amount] (including rolled-in costs if applicable)
- Interest Rate: [Rate %]
- Loan Type/Term: [e.g., 30-year fixed / 15-year fixed]
- Monthly P&I: $[Amount]
- PMI: $[Amount/month] or N/A
- Estimated Closing Costs: $[Amount]

COMPARISON:
┌─────────────────────────┬──────────────┬──────────────┐
│                         │ Current Loan │ Refinance    │
├─────────────────────────┼──────────────┼──────────────┤
│ Monthly P&I             │ $[Amount]    │ $[Amount]    │
│ Monthly Savings         │ —            │ $[Amount]    │
│ Interest Rate           │ [Rate %]     │ [Rate %]     │
│ Remaining Interest Cost │ $[Amount]    │ $[Amount]    │
│ Total Interest Savings  │ —            │ $[Amount]    │
│ Closing Costs           │ —            │ $[Amount]    │
│ Net Savings (after costs)│ —           │ $[Amount]    │
│ Break-Even Point        │ —            │ [X months]   │
└─────────────────────────┴──────────────┴──────────────┘

BREAK-EVEN ANALYSIS:
Closing costs of $[Amount] / Monthly savings of $[Amount] = [X] months to break even.
[Commentary on whether the break-even timeline makes sense given the borrower's plans.]

RECOMMENDATION CONSIDERATIONS:
- [Consideration #1 — e.g., how long the borrower plans to stay in the home]
- [Consideration #2 — e.g., impact on total interest over the life of the loan]
- [Consideration #3 — e.g., cash-out implications if applicable]
- [Consideration #4 — e.g., PMI removal opportunity]

ASSUMPTIONS:
- [List all assumptions used in the analysis]

This analysis is for informational purposes only and does not constitute a commitment to lend or financial advice.

Read the full file on GitHub · 79 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 23d ago First seen · 79 lines · 14 tokens per session scan A e090f9077080

Subscribe to this mod's changes

refinance-analysis is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 854 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.