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 syleedlabs/deal-locator-mcp --skill deal-cardgit clone --depth 1 https://github.com/syleedlabs/deal-locator-mcpWrote 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/syleedlabs/deal-locator-mcp/deal-card)<a href="https://agentmods.dev/skills/syleedlabs/deal-locator-mcp/deal-card"><img src="https://agentmods.dev/badge/skills/syleedlabs/deal-locator-mcp/deal-card/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/syleedlabs/deal-locator-mcp/deal-card"><img src="https://agentmods.dev/badge/skills/syleedlabs/deal-locator-mcp/deal-card.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00098 | $0.01017 |
| Opus 5 | $0.00049 | $0.00508 |
| Sonnet 5 | $0.00020 | $0.00203 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
deal-card 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.
What it actually says
지번 실거래 조회 (/deal-card)
$ARGUMENTS 를 해석해 deal-locator MCP 의 deal_card_search 를 호출하고,
결과를 중개 실무 규칙에 맞게 정리해 답한다.
1) 인자 해석
- 주소 =
address.구 동 번지(예:구로구 구로동 1128-1)가 가장 정확하다. 구가 없으면(구로동 1128-1) 엔진이 역추적하니 그대로 넘기고, 결과의 구를 확인해 사용자에게 알린다. N개월=months. 없으면 기본 12개월.- 주소가 모호하거나 파싱이 실패하면
/resolve-address로 먼저 확인한다.
2) 답변 규칙 (반드시 지킬 것)
-
status가OK일 때만latest에 실측값이 있다. 그 외에는 사유를 그대로 전하고 수치를 추측·보간하지 않는다.NOT_FOUND는 "데이터가 없다"는 뜻이지 "거래가 없었다"는 확정이 아니다 — 기간을 늘려 재조회할 수 있음을 안내한다. -
매칭 신뢰도를 반드시 함께 말한다. 이 도구의 핵심은 마스킹된 지번을 표제부로 역추적한 것이라, 신뢰도가 곧 답의 품질이다.
확정·정확매칭— 그대로 전한다.추정매칭— **"동일 스펙의 인접 건물일 가능성이 있다"**를 반드시 붙인다. 사용자가 고객에게 제시할 상황이면/match-explain으로 근거를 확인시킨다.인접후보— 질의한 지번이 아니라 같은 본번의 다른 건물이다. 이 사실을 먼저 말한다.
-
금액은 반올림해 적는다(절사 금지). 평단가는 도구가 준
만원/평을 그대로 쓰고, 1억원/평을 넘으면1억 5,067만원/평처럼 억 단위를 앞에 붙인다. -
통건물만 취급한다. 이 MCP 는 집합(구분상가)을 제외한다. 상가 한 칸을 물으면 범위 밖임을 밝히고 답을 지어내지 않는다.
-
계산·인용은
structuredContent로 한다. 텍스트를 파싱해 숫자를 만들지 않는다. -
첫 조회는 수십 초 걸릴 수 있다(표제부·실거래 API). 오래 걸려도 재시도하지 말고 기다린다. 같은 구를 다시 보면 캐시로 즉시 응답한다.
3) 출력 형태
○○구 ○○동 123-4 [정확매칭]
매매가 115억원 (2026-06-12)
대지 평단가 1억 3,707만원/평 · 연면적 평단가 X,XXX만원/평
토지/연면적 52.9평 / 106.2평
용도지역 제2종일반주거 · 준공 2002년
매도/매수 개인 → 법인
도로명 서울특별시 ○○구 ○○로 12
- 신뢰도가
추정매칭이하면 표 바로 아래에 한 줄 경고를 붙인다. - 마지막에 도구가 준
source한 줄을 유지한다. - 사용자가 고객 제시용이라고 하면 **"이 결과는 참고자료이지 중개대상물 확인·설명서가 아니다 — 원문(실거래가 공개시스템·건축물대장)을 직접 확인하라"**를 덧붙인다.
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 · 65 lines · 98 tokens per session scan A 8c964a6c58f0
deal-card is a skill published in the GitHub repository syleedlabs/deal-locator-mcp (27 stars, last pushed 7d ago), licensed MIT. It adds 98 tokens to every session and 1,017 once invoked, about $0.0005 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 skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.