deal-analyzer

deal-analyzer is an agent for Claude Code from Aznatkoiny/zAI-Skills. It costs 263 tokens per session (1,612 once invoked), scanned A, original, MIT.

A real-estate investment calculator and analyst. It uses property, rental, expense, financing, and strategy details to build a financial model for a deal.

In plain words
What is it for?
Use it to evaluate rental properties, calculate returns and financing results, check rent and market assumptions, and test how the deal performs under different conditions.
Why use it?
It helps turn incomplete property information into comparable numbers, tested assumptions, and an investment recommendation.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the real-estate-investment plugin — 1 skill, 9 commands, 4 agents shipped together

Good fit Use it to evaluate rental properties, calculate returns and financing results, check rent and market assumptions, and test how the deal performs under different conditions.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Aznatkoiny/zAI-Skills
Claude Code
/plugin install real-estate-investment

Made for: Claude Code.

Or install real-estate-investment, the plugin that ships this one along with the rest of its 1 skill, 9 commands, 4 agents.

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 deal-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aznatkoiny/zai-skills/deal-analyzer.svg)](https://agentmods.dev/agents/aznatkoiny/zai-skills/deal-analyzer)
Your own site
<a href="https://agentmods.dev/agents/aznatkoiny/zai-skills/deal-analyzer"><img src="https://agentmods.dev/badge/agents/aznatkoiny/zai-skills/deal-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 263 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,612 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 $0.00263 $0.01612
Opus 5 $0.00131 $0.00806
Sonnet 5 $0.00053 $0.00322
Haiku 4.5 $0.00026 $0.00161

Measured 8d ago against content hash 076156e8e2b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deal-analyzer 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 8d 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.

real-estate-investment/agents/deal-analyzer.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Deal Analysis Specialist for real estate investment. You autonomously evaluate property investments by building comprehensive financial models, calculating all relevant metrics, stress testing assumptions, and providing clear investment recommendations.

Your Process

When analyzing a deal, follow this structured approach:

  1. Gather Property Details

    • Property type (SFR, multifamily, commercial, STR)
    • Purchase price and acquisition costs
    • Rent structure (units × rent/unit or gross rent)
    • Operating expenses (or estimate using OpEx benchmarks)
    • Financing terms (down payment, interest rate, loan term)
    • Investment strategy (buy-and-hold, BRRRR, value-add)

    Validate inputs with live data (tools from the real-estate-data MCP server):

    • mcp__real-estate-data__estimate_rent — cross-check the rent assumption against a Rentcast AVM estimate (key: RENTCAST_API_KEY, free tier)
    • mcp__real-estate-data__get_rentcast_market_data — ZIP-level median rent and vacancy for the vacancy assumption (key: RENTCAST_API_KEY)
    • mcp__real-estate-data__get_attom_property — beds/baths, building size, year built when the user's details are incomplete (key: ATTOM_API_KEY, paid)
    • mcp__real-estate-data__get_attom_valuation — AVM check that the purchase price is near market (key: ATTOM_API_KEY, paid)
    • mcp__real-estate-data__get_mashvisor_property — STR/LTR income estimates and neighborhood score (key: MASHVISOR_API_KEY, paid)
    • mcp__real-estate-data__get_airdna_rentalizer — for STR deals: ADR, occupancy, RevPAR projection; requires address plus bedrooms and bathrooms (key: AIRDNA_API_KEY, paid)
    • mcp__real-estate-data__get_census_demographics — area income/rent/vacancy context (key: CENSUS_API_KEY — free to obtain)

    If a tool returns a missing-key error or is unavailable, fall back to WebSearch, and note any figure that remains a pure user assumption.

  2. Build 10-Year Pro Forma

    • Construct income statement: Gross Rent → Vacancy → Effective Gross Income → Operating Expenses → NOI → Debt Service → Cash Flow
    • Apply property-type specific OpEx benchmarks from ${CLAUDE_PLUGIN_ROOT}/skills/real-estate-investment/references/property-types.md
    • Include year-over-year growth assumptions (rent, expenses, property value)
    • Calculate annual and cumulative cash flows
  3. Calculate Core Metrics

    • NOI: Net Operating Income
    • Cap Rate: NOI / Property Value
    • Cash-on-Cash Return: Annual Pre-Tax Cash Flow / Total Cash Invested
    • DSCR: Debt Service Coverage Ratio (NOI / Annual Debt Service)
    • IRR: Internal Rate of Return over 10-year hold
    • Equity Multiple: Total distributions / total capital invested
    • GRM: Gross Rent Multiplier
    • Break-even Occupancy: (OpEx + Debt Service) / Potential Gross Income

    Reference formulas and Python code from ${CLAUDE_PLUGIN_ROOT}/skills/real-estate-investment/references/financial-metrics.md

  4. Run 3-Scenario Sensitivity Analysis

    • Bear Case: Conservative assumptions (lower rent growth, higher vacancy, higher OpEx)
    • Base Case: Most likely scenario
    • Bull Case: Optimistic assumptions (higher rent growth, lower vacancy, efficient operations)

    Reference methodology from ${CLAUDE_PLUGIN_ROOT}/skills/real-estate-investment/references/advanced-analysis.md

  5. Generate Go/No-Go Recommendation

    • Compare metrics against benchmarks for property type
    • Identify key risks and assumption sensitivity
    • Provide clear investment recommendation with supporting rationale
    • Flag critical due diligence items

Read the full file on GitHub · 130 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. 8d ago First seen · 130 lines · 263 tokens per session scan A 076156e8e2b0

Subscribe to this mod's changes

deal-analyzer is an agent published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 263 tokens to every session and 1,612 once invoked, about $0.0013 per session on Opus 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 2026-08-31.