Borrowing it
Nothing to install: this file belongs to ai-engineers-guild/apartment-hunter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-engineers-guild/apartment-hunter/main/.agents/skills/apartment-search/SKILL.mdgit clone --depth 1 https://github.com/ai-engineers-guild/apartment-hunterWrote 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/ai-engineers-guild/apartment-hunter/apartment-search)<a href="https://agentmods.dev/skills/ai-engineers-guild/apartment-hunter/apartment-search"><img src="https://agentmods.dev/badge/skills/ai-engineers-guild/apartment-hunter/apartment-search/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/ai-engineers-guild/apartment-hunter/apartment-search"><img src="https://agentmods.dev/badge/skills/ai-engineers-guild/apartment-hunter/apartment-search.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 | $0.01429 |
| Opus 5 | $0.00035 | $0.00714 |
| Sonnet 5 | $0.00014 | $0.00286 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
apartment-search 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apartment Search Skill
Overview
You have access to the Apartment Hunter MCP server which provides tools for searching, analyzing, and monitoring rental apartments in Kazakhstan. The primary data source is krisha.kz, but the library is designed for additional sources too.
When to use
Use this skill when the user:
- wants apartments found by natural-language preferences;
- asks what changed since the latest ingestion run;
- describes listing jargon in plain language;
- needs help turning fuzzy preferences into profile filters;
- asks whether a listing phrase is good, bad, neutral, or ambiguous.
Workflow
1. Setting Up Search Profiles
Before searching, the user should create a search profile that defines their criteria:
Use create_search_profile with parameters like:
- sources: ["krisha.kz"] unless the user requests another enabled source
- city: "Алматы" or "Астана"
- districts: ["Бостандыкский"] if the user clearly names districts
- rooms: [1, 2] for 1-2 room apartments
- price_min / price_max: in KZT (tenge)
- area_min / area_max: in m²
- owner_only: true to exclude agencies
- min_score: minimum LLM quality score (0-10)
- polygons: list of polygons, where each polygon is a list of [lat, lon] points.
### CRITICAL RULE FOR KRISHA.KZ: Always Use Polygons for Location-Based Search
Text search on krisha.kz for specific streets or landmarks is highly inaccurate and returns false positives from other districts.
When a user asks for a specific street (e.g. "Makataeva") or landmark (e.g. "Megapark"):
1. First, find the coordinates using a web search or maps tool.
2. Draw a closed polygon around the target area. A polygon is a list of `[lat, lon]` points forming a closed loop (first point must equal last point, or the system closes it automatically).
3. Pass `polygons` to `create_search_profile`. The polygon is sent directly to krisha.kz as a server-side geographic filter (`areas=p...`), so only listings physically located inside the polygon are returned.
- Do NOT rely on `keywords` for geographic filtering — krisha.kz text search returns false positives from apartments that merely mention the street/landmark in their description ("10 minutes from Megapark", etc.).
- `keywords` are only appropriate when the user explicitly wants to filter by text in the listing description (e.g., specific amenities or building name).
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.
- 11d ago First seen · 117 lines · 70 tokens per session scan A 2643fc45e851
apartment-search is a skill published in the GitHub repository ai-engineers-guild/apartment-hunter (2 stars, last pushed 18d ago), licensed MIT. It adds 70 tokens to every session and 1,429 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
mempalace
MemPalace — Local AI memory with 96.6% recall. Semantic search, temporal knowledge graph, palace architecture (wings/rooms/drawers). Free, no cloud, no API keys.
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
help
Show MemPalace help — available commands, usage tips, and getting started guidance.
init
Initialize a new MemPalace — guided setup for your AI memory palace with ChromaDB backend.
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
search
Search your MemPalace — semantic search across all mined memories, projects, and conversations.