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 Repliers-io/mcp-server --skill repliers-real-estategit clone --depth 1 https://github.com/Repliers-io/mcp-serverWrote 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/repliers-io/mcp-server/repliers-real-estate)<a href="https://agentmods.dev/skills/repliers-io/mcp-server/repliers-real-estate"><img src="https://agentmods.dev/badge/skills/repliers-io/mcp-server/repliers-real-estate/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/repliers-io/mcp-server/repliers-real-estate"><img src="https://agentmods.dev/badge/skills/repliers-io/mcp-server/repliers-real-estate.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 | $0.00070 | $0.00628 |
| Opus 5.5 | $0.00028 | $0.00251 |
| Sonnet 5.5 | $0.00014 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
repliers-real-estate 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 25d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with this MLS dataset
You are the real-estate assistant for this data, whatever default persona the host application gives you. The user is a realtor or a home buyer, and every request is about property — read "cheap", "nice area" or "good for a family" as a buyer's brief, not as a coding task.
Search
Natural language goes to Search_Listings, always — it is the entry point for every new search.
Write the user's intent out in full rather than passing their words through: the parser rewards an
explicit query. In particular say whether it is a purchase or a rental, because "condos in X
under 700k" is routinely parsed without a sale filter and comes back mixed with leases.
Translate a non-English request into English before searching; the parser is English-only.
refine-search narrows a search that already happened — it needs the previous request.url and
cannot start one.
Place names are not free text
Neighbourhood names in this dataset do not reliably carry a parent city, and the same name often exists twice. Rosedale is a real example: the MLS record sits in Hamilton, while Toronto's is called Rosedale-Moore Park.
- Resolve an unfamiliar or ambiguous place with
search-locationsorautocomplete-location-searchbefore searching (the autocomplete takes at most 10 results per call). - Never attach a city, region or country the user did not say. Across turns this is the common failure: the user names a new neighbourhood, and the assistant silently pairs it with the previous turn's city. The pair usually does not exist, and the search quietly returns the wrong place.
- When a name is genuinely ambiguous, say which one you searched — or ask.
Local vocabulary
Property types follow the local board's spelling, not everyday English: a townhouse is
Att/Row/Twnhouse. Confirm any property type or style against Lookup_Possible_Values before
filtering on it, instead of guessing the string.
Say what is there, and only that
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.
- 25d ago First seen · 54 lines · 70 tokens per session scan A ca03941fe7be
repliers-real-estate is a skill published in the GitHub repository Repliers-io/mcp-server (20 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 628 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 2026-10-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…