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 TheProsperityAgent/prosperity-real-estate-skills --skill quick-start-3-winsgit clone --depth 1 https://github.com/TheProsperityAgent/prosperity-real-estate-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/theprosperityagent/prosperity-real-estate-skills/quick-start-3-wins)<a href="https://agentmods.dev/skills/theprosperityagent/prosperity-real-estate-skills/quick-start-3-wins"><img src="https://agentmods.dev/badge/skills/theprosperityagent/prosperity-real-estate-skills/quick-start-3-wins/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/theprosperityagent/prosperity-real-estate-skills/quick-start-3-wins"><img src="https://agentmods.dev/badge/skills/theprosperityagent/prosperity-real-estate-skills/quick-start-3-wins.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 | $0.00052 | $0.00855 |
| Opus 5 | $0.00026 | $0.00428 |
| Sonnet 5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
quick-start-3-wins 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Start — 3 Wins for Realtors
When to use this skill
You just installed Claude. You want three workflows running today, not next week. You don't want to read a tutorial — you want copy-paste-go.
What it does
Three prompts. One paragraph each. Compliant from the first character: no school references, no scarcity language, no fair-housing violations, always positive.
Prompt 1 — Listing Description
You're writing a [CITY] [STATE] listing description for me, an agent.
Tone: warm, specific. NEVER use "must-see" or "won't last" or any cliché.
145 words max. The home is at [ADDRESS], [BEDS] bed [BATHS] bath, [SQFT]
sqft, on [LOT] acres, built [YEAR]. Standout features: [3 BULLETS]. End
with a line about [CITY] life that doesn't mention schools.
Why these constraints:
- Banned clichés ("must-see", "won't last") signal low-quality content to search engines.
- The school exclusion is a fair-housing rule — we never sort buyers by school perception.
- 145-word cap matches the optimal MLS field length.
Prompt 2 — Counter-Offer Reply
I'm a real estate agent. My buyer offered $[X] on a list price of $[Y].
The seller countered at $[Z] with [TERMS]. Write a reply email to the
listing agent that holds my position on price but signals flexibility on
close date / inspections / appliances. Tone: collegial, no pressure,
respect their professionalism.
Why this works:
- The reply email is half the negotiation. Most agents under-write it.
- "Collegial, no pressure" matters in small markets where you'll see the same listing agents every week.
- Hold price, flex on close-date / appliances — that's how a 20-year agent writes.
Prompt 3 — Three Social Posts From Today's MLS Pull
I'm a real estate agent in [CITY] [STATE]. Here are today's [N] new
listings under $[BAND]: [PASTE]. Write 3 social posts:
- Post 1: Instagram caption ≤2200 chars, hook + 5 hashtags, no links
- Post 2: Facebook ≤700 chars, conversational, ask a question
- Post 3: TikTok caption ≤300 chars, punchy, 5 hashtags
Frame: positive, never knock anywhere or anyone. No school rankings.
No "won't last."
What ships with it
3 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.
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 · 78 lines · 52 tokens per session scan A fde32733b7b0
quick-start-3-wins is a skill published in the GitHub repository TheProsperityAgent/prosperity-real-estate-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 855 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 2026-08-31.
Other skills, from other repositories
ad-creative-studio
Use when the user wants to CREATE ad creative — design new Facebook/Instagram/Google ads (static OR video), generate ad images, write ad copy, or turn competitor intel into their own ads. Triggers include "make me some ads", "create ad creative", "design an ad", "build this in Canva", "make me a video ad", "new…
competitor-ad-teardown
Use when the user wants to see, analyze, or learn from competitors' ads — Facebook/Instagram or Google. Triggers include "what are my competitors running", "show me competitor ads", "what's working for [firm]", "analyze their creative", "what ads should I steal/beat", "teardown", or any competitor creative research.…
ranql-recon
Use at the START of any Ranql task — before pulling competitor ads, SEO, reviews, social, or building a marketing plan. Teaches how to query the Ranql MCP correctly (which tool for which question, composites vs raw endpoints), how to read Ranql's response envelope (score/grade/signal/benchmarks/history/nextsteps), how…
growth-engine
Use for the big, open-ended marketing asks — "grow my firm", "get me more leads", "do my marketing", "run a full competitor analysis and make me ads", "what should I be doing", or any request that spans research → analysis → creative → launch. Orchestrates the whole Ranql skill suite end to end. Start here when the…
ranql-onboarding
Use when the user wants to SAVE their firm details to Ranql so they don't re-enter them — "set up my profile", "onboard me", "get me set up", "remember my firm/competitors". This is OPTIONAL and never a prerequisite — the other skills (teardown, creative, etc.) run fine on info collected in the chat. Onboarding just…
brand-kit-extractor
Use before generating any creative for a firm — extracts their brand identity (colors, fonts, logo, imagery style, tone of voice) from their website so new ads and content look on-brand. Triggers include "what are my brand colors", "extract my brand", "build a brand kit", "make it match my site", or any request to…