match-explain

match-explain is a skill for Claude Code from syleedlabs/deal-locator-mcp. It costs 102 tokens per session (930 once invoked), scanned A, original, MIT.

A command for showing why a masked real-estate transaction was matched to a particular building.

In plain words
What is it for?
It compares areas and construction year, reports the matching stage and differences, lists related parcel numbers, and flags weak matches for review.
Why use it?
It exposes the matching evidence and confidence level instead of asking users to trust an unexplained estimate.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the deal-locator plugin — 7 skills, 1 MCP server shipped together

Good fit It compares areas and construction year, reports the matching stage and differences, lists related parcel numbers, and flags weak matches for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/syleedlabs/deal-locator-mcp/match-explain
Install

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.

Any agent
npx skills add syleedlabs/deal-locator-mcp --skill match-explain
Clone the repo
git clone --depth 1 https://github.com/syleedlabs/deal-locator-mcp

Made for: Claude Code.

Or install deal-locator, the plugin that ships this one along with the rest of its 7 skills, 1 MCP server.

Wrote 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.

agentmods badge for match-explain

README.md
[![agentmods](https://agentmods.dev/badge/skills/syleedlabs/deal-locator-mcp/match-explain/github.svg)](https://agentmods.dev/skills/syleedlabs/deal-locator-mcp/match-explain)
Your own site
<a href="https://agentmods.dev/skills/syleedlabs/deal-locator-mcp/match-explain"><img src="https://agentmods.dev/badge/skills/syleedlabs/deal-locator-mcp/match-explain/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.

agentmods 80×15 button for match-explain

Your own site · 80×15
<a href="https://agentmods.dev/skills/syleedlabs/deal-locator-mcp/match-explain"><img src="https://agentmods.dev/badge/skills/syleedlabs/deal-locator-mcp/match-explain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 930 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.00930
Opus 5 $0.00051 $0.00465
Sonnet 5 $0.00020 $0.00186
Haiku 4.5 $0.00010 $0.00093

Measured 11d ago against content hash 12e359951102, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

match-explain 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.

skills/match-explain/SKILL.md · 64 lines

What it actually says

매칭 근거 확인 (/match-explain)

$ARGUMENTS 를 해석해 deal-locator MCP 의 match_explain 을 호출하고, 표제부 앵커값과 거래행값의 대조를 사용자가 스스로 판단할 수 있게 펼쳐 보인다.

이 스킬의 목적은 설득이 아니라 검증이다. 매칭이 약하면 약하다고 말하는 게 성공이다.

1) 인자 해석

  • 주소 = address (구 동 번지).
  • N개월 = months. 없으면 12개월.

2) 답변 규칙 (반드시 지킬 것)

  1. comparison 을 그대로 펼친다. 표제부 앵커(건축물대장) 대 거래행(실거래)의 항목별 대조 — 연면적·대지면적·건축년도 — 를 delta·equal 과 함께 보인다. 요약만 하고 숫자를 감추지 마라. 사용자가 직접 보고 판단할 수 있어야 한다.

  2. 발화 단계(stage)를 그대로 설명한다. 어떤 단계로 매칭됐는지가 신뢰도의 근거다.

    • 지번매칭(비마스킹) — 지번이 애초에 가려지지 않았다. 가장 강하다.
    • 1단계: 정확매칭 — 연면적·대지·건축년도가 모두 일치.
    • 2단계: 건축년도+연면적 — 대지 정보 없이 두 값만 일치.
    • 3단계: 오차범위 ±10% — 근사 일치. 가장 약하다.
  3. 약한 매칭을 변호하지 마라. 3단계나 추정매칭이면 **"같은 스펙의 인접 건물일 수 있다"**를 분명히 말한다. 사용자가 "확실하냐"고 물어 이 스킬을 부른 것이니, 확실하지 않으면 확실하지 않다고 답하는 게 정답이다.

  4. 필지세트(_필지세트)가 여럿이면 합필 건물이다. 대표지번 외 부속지번이 있으면 나열한다 — 왜 이 지번으로 잡혔는지 이해하는 데 필요하다.

  5. 고객 제시용이면 원문 확인을 안내한다. 이 결과는 참고자료이지 중개대상물 확인·설명서가 아니다. 실거래가 공개시스템·건축물대장 원문을 직접 확인하도록 반드시 안내한다.

  6. statusOK 가 아니면 사유를 그대로 전하고 추측하지 않는다.

3) 출력 형태

○○구 ○○동 123-4 — 2026-06-12 거래 매칭 근거
판정: 정확매칭 (1단계)

항목       표제부(앵커)    거래행(실거래)   차이
연면적       351.0㎡         351.0㎡        0     ✅
대지면적     175.0㎡         175.0㎡        0     ✅
건축년도       2002            2002         0     ✅

필지구성: 단일 필지
  • 판정이 추정매칭 이하면 표 아래 한 줄 경고를 붙인다.
  • 마지막에 도구가 준 source 한 줄을 유지한다.
Changes

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.

  1. 11d ago First seen · 64 lines · 102 tokens per session scan A 12e359951102

Subscribe to this mod's changes

match-explain is a skill published in the GitHub repository syleedlabs/deal-locator-mcp (27 stars, last pushed 6d ago), licensed MIT. It adds 102 tokens to every session and 930 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens