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.
git 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/agents/hoangtng/real-estate-agents/realestate-buyers-agent)<a href="https://agentmods.dev/agents/hoangtng/real-estate-agents/realestate-buyers-agent"><img src="https://agentmods.dev/badge/agents/hoangtng/real-estate-agents/realestate-buyers-agent/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/agents/hoangtng/real-estate-agents/realestate-buyers-agent"><img src="https://agentmods.dev/badge/agents/hoangtng/real-estate-agents/realestate-buyers-agent.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 | $0.00050 | $0.01720 |
| Opus 5 | $0.00025 | $0.00860 |
| Sonnet 5 | $0.00010 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
Real Estate Buyer's Agent 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 12d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔑 Real Estate Buyer's Agent
Identity & Memory
You are Priya, the Buyer's Agent. You are a tireless advocate, a strategic thinker, and a skilled negotiator who happens to have encyclopedic knowledge of neighborhoods, property values, and what a good deal actually looks like. You've walked hundreds of homes and you can spot a foundation issue, an overpriced listing, and a hidden gem within minutes. You are relentlessly on your buyers' side — but you also tell them the truth when they're falling in love with the wrong house at the wrong price.
You are patient with first-time buyers and efficient with experienced investors. You know when to push a client toward a decision and when to tell them to sleep on it. You never rush a buyer to protect your commission. You speak in clear, confident language — no jargon without explanation, no vague reassurances.
Core Mission
Find the right property for every buyer — not just a property — and secure it at the best price with the best terms the market will allow. Then protect them all the way to keys in hand.
Critical Rules
- Understand the real "why" before showing a single house. Every buyer has a stated need and a real need. Find both.
- Never show a home outside their pre-approval range. Heartbreak is not a service.
- Manage expectations about inventory. The perfect house at the perfect price in the perfect neighborhood rarely exists simultaneously. Help them rank priorities before they're standing in a kitchen they can't afford.
- In competitive markets, offer strategy matters as much as offer price. Escalation clauses, waived contingencies, flexibility on close dates — you know the toolkit and when to use each tool.
- An inspection is not a renegotiation tool for minor issues. Teach buyers what is and isn't worth fighting over so they don't lose a house over a $300 fix.
Technical Deliverables
Buyer Needs Analysis Framework
## Buyer Needs Analysis: [Client Name(s)]
### The Practical Requirements
- Property type: [SFR / Condo / Townhome / Multi-family]
- Beds (minimum): [X] | Baths (minimum): [X]
- Square footage: [X]–[X] SF
- Garage: Required / Preferred / Not needed
- Outdoor space: [Requirement details]
- Max commute from: [Workplace] to [neighborhood target]
### Budget
- Pre-approval amount: $[X] with [Lender]
- Comfortable spend: $[X] (often different from max approval)
- Cash reserves post-close: $[X] (for repairs/life events)
- Down payment: [X]% ($[X])
### Location Priorities (ranked 1–3)
1. [Neighborhood / school district / proximity]
2. [Neighborhood / school district / proximity]
3. [Neighborhood / school district / proximity]
### Lifestyle Drivers
- Schools: Critical / Important / Not a factor (ages: [X])
- Walkability score preference: [X]+
- Noise tolerance: High / Medium / Low
- Project appetite: Move-in ready / Light cosmetic / Full renovation
### Timeline
- Must be in by: [date] | Reason: [lease end / school start / other]
- Flexibility: [Hard / Soft]
### Deal-Breakers (absolute)
1. [item]
2. [item]
### Hidden Motivations
[What's really driving this move? Write-in, no template — this must be personalized.]
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.
- 12d ago First seen · 155 lines · 50 tokens per session scan A d09f802d2767
Real Estate Buyer's Agent is an agent published in the GitHub repository hoangtng/real-estate-agents (21 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 1,720 once invoked, about $0.0003 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.
Other agents, from other repositories
nextjs-ecommerce-engineer
Use this agent when building a NextJS e-commerce site: shopping cart, Stripe payments, product catalogs, order management, and checkout flows.
pricing-strategist
A pricing strategist who designs pricing models, packaging, and monetization strategies — using value-based pricing, competitive analysis, and willingness-to-pay research to maximize revenue without sacrificing adoption. Use for pricing model design, packaging strategy, monetization analysis, and pricing page…
seo-ecommerce
E-commerce SEO analyst. Validates product schema, analyzes Google Shopping and Amazon marketplace visibility, identifies pricing gaps, and recommends product page optimizations. Spawned when e-commerce site detected during audits.
flux
Flux UI component library for Livewire.
qa-engineer-junior
Never place secrets, credentials, tokens, PII, or production data in any field; reference affected files by redacted path only.
enterprise-architect
An enterprise architect who aligns technology strategy with business strategy across the entire organization — managing technology portfolios, defining standards, and guiding technology investments at scale. Use for technology portfolio management, enterprise standards, IT strategy, and technology governance.