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 hoangtng/real-estate-agents --skill cma-generatorgit clone --depth 1 https://github.com/hoangtng/real-estate-agentsWrote 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/hoangtng/real-estate-agents/cma-generator)<a href="https://agentmods.dev/skills/hoangtng/real-estate-agents/cma-generator"><img src="https://agentmods.dev/badge/skills/hoangtng/real-estate-agents/cma-generator/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/hoangtng/real-estate-agents/cma-generator"><img src="https://agentmods.dev/badge/skills/hoangtng/real-estate-agents/cma-generator.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 | $0.00105 | $0.01391 |
| Opus 5.5 | $0.00042 | $0.00556 |
| Sonnet 5.5 | $0.00021 | $0.00278 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
cma-generator 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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CMA Generator
Produces a complete, professional Comparative Market Analysis for residential properties. The output is structured to be used directly in a listing presentation or shared with a seller client.
What You Need From the User
Before generating the CMA, collect:
- Subject property address (or neighborhood + city if no specific address)
- Property specs: beds, baths, square footage, lot size, year built, garage
- Condition & updates: kitchen remodel, roof age, HVAC age, flooring, notable features
- Any known comparable sales (optional — generate placeholders if none provided)
- Market context: city/zip, current market posture if known
If specs are missing, generate a CMA template with clearly marked [FILL IN] placeholders.
Output Format
Produce the full CMA in this exact structure:
## Comparative Market Analysis
**Property:** [Address or "Subject Property"]
**Prepared by:** Marcus, Listing Agent | [Date]
**Market:** [City, State] — [Neighborhood]
---
### Subject Property Summary
| Feature | Detail |
|----------------|-------------------------|
| Address | [address] |
| Beds / Baths | [X] BD / [X] BA |
| Square Footage | [X,XXX] SF |
| Lot Size | [X,XXX] SF / [X] acres |
| Year Built | [XXXX] |
| Garage | [X]-car [attached/det.] |
| Condition | [Excellent/Good/Fair] |
| Notable Updates| [list] |
---
### Active Competition
*What buyers are choosing between right now*
| Address | List Price | $/SF | DOM | Beds/Baths | Key Notes |
|---------|-----------|------|-----|------------|-----------|
| [comp] | $[X] | $[X] | [X] | [X]/[X] | [diff] |
| [comp] | $[X] | $[X] | [X] | [X]/[X] | [diff] |
| [comp] | $[X] | $[X] | [X] | [X]/[X] | [diff] |
---
### Sold Comparables (last 90–120 days)
*What the market has actually paid*
| Address | Sold Price | $/SF | DOM | SP/LP% | Adjustments vs. Subject |
|---------|-----------|------|-----|--------|------------------------|
| [comp] | $[X] | $[X] | [X] | [X]% | [+/- feature notes] |
| [comp] | $[X] | $[X] | [X] | [X]% | [+/- feature notes] |
| [comp] | $[X] | $[X] | [X] | [X]% | [+/- feature notes] |
---
### Price Adjustments to Subject Property
| Adjustment Factor | Amount | Notes |
|----------------------------|------------|----------------------------------|
| Location premium/discount | ±$[X] | [reason] |
| Condition delta | ±$[X] | [reason] |
| Size adjustment | ±$[X] | $[X]/SF × [X] SF difference |
| Feature adjustments | ±$[X] | [pool / view / garage / updates] |
| **Net Adjustment** | **±$[X]** | |
---
### Market Conditions
- **Active inventory:** [X] homes in this price range
- **Monthly absorption rate:** [X] homes/month
- **Months of supply:** [X] months → [Seller's / Balanced / Buyer's] market
- **Average DOM:** [X] days | **Average SP/LP:** [X]%
---
### Recommended Pricing Strategy
| Scenario | Price | Expected DOM | Strategy |
|--------------|----------|--------------|-------------------------------------------|
| Conservative | $[X] | [X–X] days | Fastest sale, maximum offers, least risk |
| **Market** ✅ | **$[X]** | [X–X] days | **Best balance of speed and net proceeds**|
| Aggressive | $[X] | [X+] days | Tests ceiling — risk of extended DOM |
**Recommendation:** List at **$[X]**
[2–3 sentence plain-language explanation of why this price, what the risk of going higher is, and what the seller can realistically expect at this price point.]
---
### Pricing Objection Responses
**If seller says "Zillow says more":**
Zillow uses tax records and public data — it can't account for your [specific update], the distressed sale it included in your comps, or current buyer demand in this micro-market. The MLS data I'm using reflects what qualified buyers have actually paid in the last 90 days.
**If seller says "let's try higher for 30 days":**
After 21+ days on market, buyers assume something is wrong — even if there isn't. Correctly-priced homes in this area averaged [X] days and [X]% of list price. Overpriced-then-reduced homes averaged [Y] days and [Y]% of original list. The first two weeks are your best window.
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.
- 1mo ago First seen · 118 lines · 105 tokens per session scan A cd181199e643
cma-generator is a skill published in the GitHub repository hoangtng/real-estate-agents (28 stars, last pushed 5mo ago), licensed MIT. It adds 105 tokens to every session and 1,391 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
wealth-structure
A framework for thinking about wealth through ownership, responsibility, leverage, and avoiding risks that could end your progress.
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
spend-forecast
Forecast Claude Code spend to the end of the week or month from the daily session trend on the Agent Monitor dashboard — moving average of daily spend × days remaining, added to spend-to-date. Uses /api/analytics dailysessions, /api/pricing/cost, and /api/sessions for a per-day cost curve. Use when projecting cost or…
Coinbase Automation
Coinbase Automation: list and manage cryptocurrency wallets, accounts, and portfolio data via Coinbase CDP SDK.
agent-fintech-engineer
This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.
financial-expert
A financial research skill for China and Hong Kong securities, funds, company finances, economic indicators, research reports, announcements, news, and business-risk data. It returns data and neutral analysis rather than placing trades or recommending investments.