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 listing-descriptiongit 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/listing-description)<a href="https://agentmods.dev/skills/theprosperityagent/prosperity-real-estate-skills/listing-description"><img src="https://agentmods.dev/badge/skills/theprosperityagent/prosperity-real-estate-skills/listing-description/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/listing-description"><img src="https://agentmods.dev/badge/skills/theprosperityagent/prosperity-real-estate-skills/listing-description.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 | $0.00043 | $0.00803 |
| Opus 5.5 | $0.00017 | $0.00321 |
| Sonnet 5.5 | $0.00009 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
listing-description 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 2mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Listing Description
Writes a 145-word listing description in under two minutes. Compliant by default. References fair-housing-overlay for the underlying rule set.
When to use this skill
You just took a new listing. You have the address, beds/baths, square footage, lot, year built, and three standout features. You need a description that:
- Hits the MLS field cap exactly
- Avoids the dead-cliché filter (won't get downranked by Realtor.com / Zillow)
- Stays inside Fair Housing
- Localizes the close without referencing schools
This skill replaces 20 minutes of writing-and-rewriting with 90 seconds.
Prompt
You're writing a [CITY] [STATE] listing description for me, an agent.
REQUIRED COMPLIANCE (load fair-housing-overlay if available):
- NO clichés: never use "must-see", "won't last", "rare opportunity",
"hidden gem", "priced to sell", "act now"
- NO school references
- NO demographic targeting or steering language
- NO "safe", "quiet" (replace with "low-traffic street")
- ALWAYS positive
REQUIRED OUTPUT:
- 145 words exactly (MLS field cap)
- Tone: warm, specific, factual
- Open with the strongest objective feature
- Middle: floor plan, indoor flow, key spaces
- End: ONE line about [CITY] life that doesn't mention schools
(use commute time to a major employer, or a public park, or a downtown
amenity, or a commute-to-coast time — all objective, all FH-clean)
PROPERTY DATA:
- Address: [ADDRESS]
- Beds/Baths: [BEDS] / [BATHS]
- Square footage: [SQFT]
- Lot size: [LOT] acres
- Year built: [YEAR]
- Standout features (pick 3):
- [FEATURE 1]
- [FEATURE 2]
- [FEATURE 3]
- Major nearby employer / park / amenity for the close: [ANCHOR]
Write the description.
What good output looks like
See examples/ for two anonymized real-world outputs:
- A $300-400K Springfield home (suburban, screened porch)
- A $200K-under rural-county home (acreage, workshop)
Both are 145 words exactly. Both pass MLS feed filters. Both have FH-compliant local-life closing lines.
What ships with it
2 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.
- 2mo ago First seen · 89 lines · 43 tokens per session scan A 038f3e8f35e3
listing-description is a skill published in the GitHub repository TheProsperityAgent/prosperity-real-estate-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 803 once invoked, about $0.0002 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 2026-08-31.
listing-description compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| listing-descriptionTheProsperityAgent/prosperity-real-estate-skills | Skill | 11 | 3mo ago | MIT | A | 43 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | yesterday | MIT | A | 76 | Claude Code |
| playbook-social-engineerings0ld13rr/pentestcode | Skill | 930 | 2d ago | MIT | A | 37 | Claude Code, Codex |
| agb-begriff-vorformuliert-305Klotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 68 | Claude Code |
| aenderungsvorbehalt-308Klotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 41 | Claude Code |
| agb-pruefung-kaltstartKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 41 | Claude Code |
| agb-rechtswahl-schweizer-recht-rom-iKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |