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 cyanheads/socrata-mcp-server --skill socrata-guidegit clone --depth 1 https://github.com/cyanheads/socrata-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/cyanheads/socrata-mcp-server/socrata-guide)<a href="https://agentmods.dev/skills/cyanheads/socrata-mcp-server/socrata-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/socrata-mcp-server/socrata-guide/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/cyanheads/socrata-mcp-server/socrata-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/socrata-mcp-server/socrata-guide.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 | $0.00051 | $0.00869 |
| Opus 5.5 | $0.00020 | $0.00348 |
| Sonnet 5.5 | $0.00010 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
socrata-guide 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Use Socrata for public government datasets served through SODA 2.1. Discovery also lists maps, files, and stories; find a dataset-type asset for row analysis. The tools do not edit portal data.
Identifiers
Keep the portal and dataset identity from a discovery result together through analysis. Metadata supplies the typed API field names; a staged query supplies a separate canvas token and table name. Use the returned identifiers rather than deriving a local table name from a dataset ID.
Gates
- Before concluding that a jurisdiction has no data, search datasets beyond the curated portal list. An empty portal-name search establishes only that no entry in that list matched. Broaden restrictive category and tag filters before treating an empty dataset search as evidence of absence.
- Before filtering a category, inspect its actual values with a grouped count. A neighborhood, status, or agency name in the question need not match the dataset's vocabulary.
- Before reporting a population total, distinguish approximate cached metadata counts, matching source rows, returned groups, and staged rows. A filled page can have more matches; an absent total does not establish completeness. Grouped queries do not report a source-row total.
- Before treating a canvas statistic as a whole-dataset statistic, establish that the staged copy covers the intended population. It starts at the query's offset and stops at 50,000 matching result rows. Prefer upstream SoQL aggregation when the population exceeds the copy or its coverage is unknown.
- Before joining datasets, establish each table's record granularity, shared key meaning, time window, and units from metadata and observed values. Matching column names alone do not establish a valid join.
- Before staging another query into an existing canvas, account for replacement: another spill of the same dataset replaces its existing table, including when the filter or offset changes. The table name also omits the portal, so the same dataset ID from another portal collides. Use separate canvases for those extracts; these tools cannot join across canvases.
What ships with it
1 file 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.
- 2d ago First seen · 50 lines · 51 tokens per session scan A ff6daa1a7794
socrata-guide is a skill published in the GitHub repository cyanheads/socrata-mcp-server (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 869 once invoked, about $0.0002 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 2026-10-28.
Other skills, from other repositories
treasury-fiscaldata-guide
Use treasury tools for multi-step Treasury fiscal analysis: establish comparable reporting periods, retrieve complete datasets, and analyze staged tables without double-counting fiscal totals.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.clientCapabilities, ctx.enrich, ctx.content), and when to use each.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.