real-estate-comping

real-estate-comping is a skill for Claude Code from DataSift-Ty-Personal/SiftStack. It costs 107 tokens per session (2,113 once invoked), scanned A, original, MIT.

A property-valuation process based on comparable sales, meaning nearby or similar properties that recently sold. It uses one method when sale prices are publicly recorded and another when they are not, and produces a report, spreadsheet, and comparison table.

In plain words
What is it for?
Use it to identify the property's valuation method, analyze comparable sales, estimate after-repair value, and generate valuation deliverables for a real-estate deal.
Why use it?
It provides a structured way to estimate a property's after-repair value for wholesaling. It focuses on valuation and comparable sales, so it does not create renovation budgets or a repair scope.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the deal-analyzer plugin — 3 skills, 1 command shipped together

Good fit Use it to identify the property's valuation method, analyze comparable sales, estimate after-repair value, and generate valuation deliverables for a real-estate deal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/datasift-ty-personal/siftstack/real-estate-comping
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.

Any agent
npx skills add DataSift-Ty-Personal/SiftStack --skill real-estate-comping
Clone the repo
git clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStack

Made for: Claude Code.

Or install deal-analyzer, the plugin that ships this one along with the rest of its 3 skills, 1 command.

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 real-estate-comping

README.md
[![agentmods](https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/real-estate-comping.svg)](https://agentmods.dev/skills/datasift-ty-personal/siftstack/real-estate-comping)
Your own site
<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/real-estate-comping"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/real-estate-comping.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,113 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 $0.00107 $0.02113
Opus 5 $0.00053 $0.01056
Sonnet 5 $0.00021 $0.00423
Haiku 4.5 $0.00011 $0.00211

Measured 7d ago against content hash 705350ca5cad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

real-estate-comping 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_excel_report.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/deal-analyzer/skills/real-estate-comping/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Real Estate Comping Skill

Perform appraiser-grade property valuations using the Two-Bucket method for disclosure states or the Triangulation method for non-disclosure states. This skill is strictly about comparable sales analysis and ARV determination — it does not estimate rehab costs, renovation budgets, or scope of work. If the user needs rehab cost estimation, direct them to the appropriate skill for that.

Workflow Overview

  1. Identify property location → Determine state from address
  2. Route to correct methodology → Disclosure or Non-Disclosure framework
  3. Execute 9-step analysis → Follow the appropriate prompt framework
  4. Generate deliverables → PDF summary report + Excel breakdown + comps table

State Detection & Routing

Determine state type from property address:

  • Non-Disclosure States (sold prices not publicly recorded): TX, UT, WY, NM, ID, MT, ND, AK, KS, MS, LA, MO
  • Disclosure States: All other US states

Routing:

  • Non-disclosure state → Read references/non-disclosure-prompt.md
  • Disclosure state → Read references/disclosure-prompt.md

Quick Reference

Framework States Key Method Price Source
Disclosure Most US states Two-Bucket (Unrenovated vs Renovated PPSF) MLS sold prices
Non-Disclosure TX, UT, WY, NM, ID, MT, ND, AK, KS, MS, LA, MO Triangulation (LLP + DOM, Deed of Trust, Tax Ratio) Derived estimates

Core Comping Rules (Both Frameworks)

These rules apply regardless of disclosure status:

Comp Selection Filters

  • Age: ≤90 days preferred, 6 months max
  • Subdivision: Same micro-pocket, do not cross major roads
  • GLA: ±100 sqft ideal, ±250 sqft outer bound
  • Property type: Match elevation style (ranch↔ranch, 2-story↔2-story)
  • Build year: ±10 years

Feature Adjustments (by price tier)

See references/adjustment-cheatsheet.md for complete adjustment values.

Quick reference:

Feature <$500k Tier >$500k Tier
Bedroom +$10k +$25k
Bathroom ±$10k ±$10k
Garage +$10-25k +$10-25k
Traffic (backing) -$10k -10-15%
Traffic (fronting) -$20k -20%

Read the full file on GitHub · 214 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 214 lines · 107 tokens per session scan A 705350ca5cad

Subscribe to this mod's changes

real-estate-comping is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed 3d ago), licensed MIT. It adds 107 tokens to every session and 2,113 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories