agentmods.dev

find-reference-data

find-reference-data is a skill for Claude Code from ChrisGVE/localdata-mcp. It costs 32 tokens per session (637 once invoked), scanned A, original, Apache-2.0.

A workflow for finding public datasets that add context to an existing database, such as population, economic, geographic, health, or industry data.

In plain words
What is it for?
Use it to locate, download, prepare, and connect reference datasets for analysis.
Why use it?
It helps when your own data lacks background information needed for comparison or interpretation. It also helps match outside data to fields such as location codes, dates, industries, or entity IDs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the localdata-mcp plugin — 18 skills, 11 agents, 1 MCP server shipped together

not rated 4repo +1 24d ago A scan 32 tokens original Apache-2.0

Good fit Use it to locate, download, prepare, and connect reference datasets for analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrisgve/localdata-mcp/find-reference-data
View source ↗ ChrisGVE/localdata-mcp
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 ChrisGVE/localdata-mcp --skill find-reference-data
Clone the repo
git clone --depth 1 https://github.com/ChrisGVE/localdata-mcp

Made for: Claude Code.

Or install localdata-mcp, the plugin that ships this one along with the rest of its 18 skills, 11 agents, 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 find-reference-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisgve/localdata-mcp/find-reference-data.svg)](https://agentmods.dev/skills/chrisgve/localdata-mcp/find-reference-data)
Your own site
<a href="https://agentmods.dev/skills/chrisgve/localdata-mcp/find-reference-data"><img src="https://agentmods.dev/badge/skills/chrisgve/localdata-mcp/find-reference-data.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 637 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.
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 $0.00032 $0.00637
Opus 5 $0.00016 $0.00318
Sonnet 5 $0.00006 $0.00127
Haiku 4.5 $0.00003 $0.00064

Measured 8d ago against content hash 844c165ead6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

find-reference-data 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 8d 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/exploration/find-reference-data/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find Reference Data

Locate, download, and prepare public reference datasets to provide context for analysis.

Steps

  1. Understand the enrichment need. From $ARGUMENTS, identify the user's database and what external context is needed (demographics, benchmarks, economic indicators, geographic boundaries, etc.). If unclear, describe what types of reference data would be most useful given the data at hand.

  2. Assess the user's data. Call describe_database with the user's database name. Identify the join keys available: geographic codes (ZIP, FIPS, country), time periods (years, months), industry codes (SIC, NAICS), or entity identifiers.

  3. Identify candidate sources. Based on the need and available join keys, determine the best public data sources:

    • Population/demographics: Census Bureau, Eurostat, UN Population Division
    • Economic indicators: FRED, World Bank, OECD, BLS
    • Geographic boundaries: Census TIGER/Line, Natural Earth
    • Industry benchmarks: BLS industry data, SEC EDGAR
    • Health/scientific: WHO, CDC, public research repositories
    • General-purpose: data.gov, Kaggle Datasets, UCI ML Repository

  4. Download and connect. Locate a direct download URL for the most suitable dataset (prefer CSV or Parquet). Download it and call connect_database to load it. If the primary source is unavailable, try mirror sites or alternative sources.

  5. Validate the reference data. Call describe_database and get_data_quality_report on the loaded reference data. Verify:

    • Expected columns and types are present
    • Value ranges are reasonable
    • Time period and geographic coverage overlap with the user's data
    • Join key format matches the user's data

  6. Test the join. Call execute_query to check how many records from the user's data would match the reference data on the proposed join key. Report the match rate. If low, investigate key format mismatches or coverage gaps.

  7. Document provenance. For each dataset, record: source name, URL, access date, data vintage/release date, license or terms, and any transformations applied.

Read the full file on GitHub · 44 lines

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. 8d ago First seen · 44 lines · 32 tokens per session scan A 844c165ead6b

Subscribe to this mod's changes

find-reference-data is a skill published in the GitHub repository ChrisGVE/localdata-mcp (4 stars, last pushed 24d ago), licensed Apache-2.0. It adds 32 tokens to every session and 637 once invoked, about $0.0002 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.

Analytics and metricsClaude CodeResearchai-toolsclaude-desktopdata-analyticsfastmcpmcp
Related

Other skills, from other repositories

wingman-mcp

Add persistent, interactive task plan management to your agent. Wingman tracks plans and tasks across a long conversation — Claude creates plans, ticks tasks after completing work, and a live panel renders inline in the chat. Install the MCP server first, then use these tools to manage plans and tasks throughout any…

adeoluwaadesina/wingman-mcp · 68 tokens

liveagent-code-review

Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation. Use when the user asks for code review, invokes the Code Review action from Git Review, or explicitly mentions this skill.

Stack-Cairn/LiveAgent · 54 tokens

skills-creator

Create or update LiveAgent runtime skills. Use when you need to summarize a workflow into a skill, write it into the fixed user skills root, validate it, package it, or refine a skill's references for LiveAgent's SkillsManager flow.

Stack-Cairn/LiveAgent · 53 tokens

skills-installer

Install, list enabled, validate, or package LiveAgent skills. Use when you need to inspect the skills enabled in the current conversation, import a local skill directory or package, search/install from ClawHub, install from a GitHub repo/tree URL, or reconcile conflicts during an upgrade.

Stack-Cairn/LiveAgent · 62 tokens

triaging-incidents

Creating, triaging, updating, and analyzing ServiceNow incidents. Assess severity, check affected CIs, find related incidents, and recommend assignments. Use when the user mentions incidents, INC numbers, outages, service disruptions, ticket creation, triage, priority, severity, ITSM operations, SLA breaches…

jschuller/mcp-server-servicenow · 82 tokens

reviewing-update-sets

Reviewing, analyzing, and comparing ServiceNow update sets before promotion. Shows changes, risks, dependencies, and conflicts. Use when the user mentions update sets, customizations, promotion, code review, change tracking, pre-deployment review, sysupdatexml, customer updates, "what changed in this update set," or…

jschuller/mcp-server-servicenow · 77 tokens