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.
npx skills add miron-tech/wholesaler-claude-skills --skill comp-analyzergit clone --depth 1 https://github.com/miron-tech/wholesaler-claude-skillsWrote 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.
[](https://agentmods.dev/skills/miron-tech/wholesaler-claude-skills/comp-analyzer)<a href="https://agentmods.dev/skills/miron-tech/wholesaler-claude-skills/comp-analyzer"><img src="https://agentmods.dev/badge/skills/miron-tech/wholesaler-claude-skills/comp-analyzer/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.
<a href="https://agentmods.dev/skills/miron-tech/wholesaler-claude-skills/comp-analyzer"><img src="https://agentmods.dev/badge/skills/miron-tech/wholesaler-claude-skills/comp-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.03709 |
| Opus 5.5 | $0.00030 | $0.01484 |
| Sonnet 5.5 | $0.00015 | $0.00742 |
| Haiku 4.5 | $0.00008 | $0.00371 |
Grade A, and why
comp-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 29d 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.
How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Comp Analyzer Skill
Purpose: Pull comps, calculate ARV, and generate a deal-ready analysis — without spending 30 minutes on Zillow, PropStream, or county records.
PREREQUISITE
- Perplexity MCP — for searching recent sales, market data, and property values
- Firecrawl MCP — for scraping Zillow, Redfin, Realtor.com, and county assessor sites for detailed comp data
WHAT THIS SKILL DOES
- Researches comparable sales within a specified radius of the subject property
- Pulls comp data from multiple sources (Zillow, Redfin, county records)
- Calculates ARV using $/sqft analysis with adjustments
- Applies the 70% rule to determine maximum allowable offer
- Produces a professional comp report you can share with buyers
- Flags when comp data is thin or unreliable
WHAT THIS SKILL DOES NOT DO
- Does not access MLS directly (uses public data sources)
- Does not replace a professional appraisal
- Does not guarantee values — estimates based on available public data
- Does not pull off-market sales that aren't in public records yet
INPUTS NEEDED
| Input | Required | Example |
|---|---|---|
| Subject property address | Yes | "4821 Cedar Ln, Memphis, TN 38118" |
| Property details | Yes | "3/2, 1,100 sqft, built 1960" |
| Property condition | Yes | "Needs full rehab" or "Cosmetic updates only" or "Turn-key" |
| Comp radius | Helpful | "0.5 mile" (default: 1 mile) |
| Time window | Helpful | "Last 60 days" (default: 90 days) |
| Purpose | Helpful | "Making an offer," "Building a deal package for buyers," "Validating my ARV" |
| Estimated repairs | Helpful | "$40,000" (if known) |
GOAL
- Primary: Give the wholesaler a defensible ARV they can use to make offers and sell to buyers with confidence
- Secondary: Save 30+ minutes of manual comp research per property
FRAMEWORK: The 4-Pass Comp Process
Pass 1 — Wide Search (Perplexity)
Cast a wide net to find recent sales in the area.
Perplexity query:
perplexity_ask: "What [beds]/[baths] single family homes have sold within 1 mile of [address] in the last 90 days? I need specific addresses, sale prices, square footage, sale dates, and property condition (remodeled vs. original). Focus on comparable properties — similar size, similar age, similar construction."
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.
- 29d ago First seen · 354 lines · 76 tokens per session scan A 01667822ef1a
comp-analyzer is a skill published in the GitHub repository miron-tech/wholesaler-claude-skills (53 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 3,709 once invoked, about $0.0003 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 2026-10-09.
comp-analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| comp-analyzermiron-tech/wholesaler-claude-skills | Skill | 53 | 1mo ago | MIT | A | 76 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |