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 2016judea/small-business-intelligence-mcp --skill twin-cities-property-recordgit clone --depth 1 https://github.com/2016judea/small-business-intelligence-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/2016judea/small-business-intelligence-mcp/twin-cities-property-record)<a href="https://agentmods.dev/skills/2016judea/small-business-intelligence-mcp/twin-cities-property-record"><img src="https://agentmods.dev/badge/skills/2016judea/small-business-intelligence-mcp/twin-cities-property-record/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/2016judea/small-business-intelligence-mcp/twin-cities-property-record"><img src="https://agentmods.dev/badge/skills/2016judea/small-business-intelligence-mcp/twin-cities-property-record.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 | $0.00071 | $0.00975 |
| Opus 5 | $0.00036 | $0.00487 |
| Sonnet 5 | $0.00014 | $0.00195 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
twin-cities-property-record 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twin Cities property record
The two data tools query 25 joined public-records files for the seven-county Minneapolis–St. Paul metro. Everything below exists because guessing at this data produces answers that look right and are wrong.
Quick start
- Call
twin_cities_datasetsfirst. It returns the real dataset ids, row counts, column names, scopes and per-dataset county coverage. Do not guess a dataset id —sales,owners,adjacency,parcels,contamination,corridors,licences,businesses,flood,sba-loansand the rest are returned by that call, and the list changes as datasets ship. - Call
twin_cities_recordswith thedatasetyou picked. Addaddressto answer about one property and its surroundings; omit it to ask about the whole market cut. - Report
matching_rowsas the answer. Show rows fromsampleas examples. Hand the userdownload_urlfor the complete file.
The four rules that stop a wrong answer
sample is at most six rows; matching_rows is the truth. Presenting six
rows as the whole result is the single most common way to be confidently wrong
here. Say "399 sales, here are the five closest" — never "here are the sales".
Coverage is per dataset, never metro-wide. It runs from one city to all
seven counties and each result states its own. emergency-calls, incidents,
landlords and vacancies are Minneapolis or Minneapolis + Saint Paul only;
contamination and building-stock are Hennepin + Ramsey; owners is five
counties; sales and parcels are all seven. Never carry one dataset's
counties over to another, and never report "no records" when the real answer is
"that county is not in this file."
An ambiguous address is answered, not failed. Several of these cities have a Grand Ave. The tool returns the candidate cities; ask which one and call again with the city after a comma. The whole string after the comma is read as the city.
owner and taxpayer are the county's tax-billing name. That is an entity
on a tax roll, not a verified beneficial owner and not a person you have
contact details for. Say "the parcel is billed to X", not "X owns it".
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 · 79 lines · 71 tokens per session scan A 4b65cf95b4e7
twin-cities-property-record is a skill published in the GitHub repository 2016judea/small-business-intelligence-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 71 tokens to every session and 975 once invoked, about $0.0004 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
add-provider
Add a new storage or service provider to the core package. Use when implementing a new backend for StorageService (e.g., a new database) or a new service provider (e.g., a new LLM backend).
add-export
Add a new subpath export to the @cyanheads/mcp-ts-core package. Use when creating a new public API surface that consumers import from a dedicated subpath (e.g., @cyanheads/mcp-ts-core/newutil).
owd-albatross
Connect, initialize, resume, or coordinate MDevolved Projects from Albatross using its agent.config.json stdio MCP surface, a pinned OAuth bridge, qualified tool names, workspace prompt continuity, path forks, resets, and independently attributable participant identities. Use when a repository runs Albatross, contains…
owd-eve
Connect, initialize, resume, or coordinate MDevolved Projects from an Eve agent using Eve's standard remote MCP connection, user-scoped Vercel Connect OAuth, qualified tool names, durable Project continuity, and independently attributable agent identities. Use when an Eve repository has agent/connections, when adding…
owd-obsidian-mind
Connect, initialize, resume, or coordinate an Obsidian Mind vault with MDevolved while preserving its local qmd/om MCP runtime, native note layout, scoped memories, private-note rules, and multi-agent writer safety. Use when a vault-manifest.json identifies template obsidian-mind, when adding MDevolved beside Obsidian…
mdevolved-albatross
Connect or resume an Albatross workspace with MDevolved through its stdio MCP bridge, preserving runtime-local execution and owner-approved Project authority.