stock-data-setup

stock-data-setup is a skill for Claude Code, Codex from jamespud/yahoo-stock-mcp. It costs 87 tokens per session (1,335 once invoked), scanned A, original, MIT.

A setup and diagnosis workflow for the local stock-data database used by the other stock research tools. It initializes or updates the MySQL database, downloads stock or sector data, checks freshness, and reports sync problems.

In plain words
What is it for?
Use it to sync one stock or the sector set, backfill history, fetch intraday data, verify stored dates and prices, and investigate provider or database failures.
Why use it?
It addresses empty, missing, stale, or partly updated data before research begins. Verification steps show what actually arrived instead of assuming a sync succeeded.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to sync one stock or the sector set, backfill history, fetch intraday data, verify stored dates and prices, and investigate provider or database failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamespud/yahoo-stock-mcp/stock-data-setup
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 jamespud/yahoo-stock-mcp --skill stock-data-setup
Clone the repo
git clone --depth 1 https://github.com/jamespud/yahoo-stock-mcp

Made for: Claude Code, Codex.

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 stock-data-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamespud/yahoo-stock-mcp/stock-data-setup/github.svg)](https://agentmods.dev/skills/jamespud/yahoo-stock-mcp/stock-data-setup)
Your own site
<a href="https://agentmods.dev/skills/jamespud/yahoo-stock-mcp/stock-data-setup"><img src="https://agentmods.dev/badge/skills/jamespud/yahoo-stock-mcp/stock-data-setup/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 stock-data-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamespud/yahoo-stock-mcp/stock-data-setup"><img src="https://agentmods.dev/badge/skills/jamespud/yahoo-stock-mcp/stock-data-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,335 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 $0.00087 $0.01335
Opus 5.5 $0.00035 $0.00534
Sonnet 5.5 $0.00017 $0.00267
Haiku 4.5 $0.00009 $0.00134

Measured 5d ago against content hash ecd6fd738a52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stock-data-setup 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 5d 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.

plugins/yahoo-stock-mcp/skills/stock-data-setup/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data setup and diagnosis

Get the local snapshot into a usable state, then prove it. Every other skill assumes the database already holds the rows it reads, so this is the skill that runs when a tool answers instrument not found in DB, no sector data synced yet, or returns an empty list.

Read references/data-policy.md first - in particular the sections on partial syncs and on provider access denial, which govern how failures are reported.

MCP tools used

  • sync_stock - sync one symbol; mode: "full" backfills complete history, mode: "incremental" fetches only new data; intraday optionally pulls minute bars
  • sync_sectors - sync the 11 GICS sector ETFs plus SPY benchmark and their top-holding constituents
  • search_symbol - check whether a symbol is already stored before syncing
  • get_quote - verify what landed: latestBar.trade_date, currency, syncedAt
  • get_sector_performance - verify sector data landed (asOf, ranked rows)

CLI surface

The same operations exist as CLI commands for setting up a host that has no MCP client yet. Run these where the agent has shell access; the package requires Node.js 20 or newer. Use npx yahoo-stock-mcp <command> if the binary is not installed globally.

Command Purpose
yahoo-stock-mcp db:init create the database if missing, then install the bootstrap schema and all migrations
yahoo-stock-mcp db:migrate apply pending migrations to an existing database
yahoo-stock-mcp sync --symbol NVDA --full full history for one symbol
yahoo-stock-mcp sync --symbol NVDA --intraday 15m also pull minute bars
yahoo-stock-mcp sync --all --full every symbol already stored
yahoo-stock-mcp sync --sectors sector ETFs and constituents (--no-members skips constituents)
yahoo-stock-mcp server start the MCP server over stdio

Configuration is read from YAHOO_STOCK_MCP_DATABASE_URL, or from the discrete YAHOO_STOCK_MCP_DB_HOST / _PORT / _USER / _PASSWORD / _NAME variables when the URL is not set. Provider behaviour is controlled by YAHOO_STOCK_MCP_PRIMARY_PROVIDER (yahoo by default), YAHOO_STOCK_MCP_BARS_START_DATE, and YAHOO_STOCK_MCP_PROXY_URL. db:init needs CREATE DATABASE privileges only when the database does not exist yet.

Read the full file on GitHub · 82 lines

Files

What ships with it

2 files 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.

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. 5d ago Changed · -2 tokens per session ecd6fd738a52
  2. 13d ago Changed a3ad76e636f6
  3. 17d ago First seen · 82 lines · 89 tokens per session scan A 8a38fd921457

Subscribe to this mod's changes

stock-data-setup is a skill published in the GitHub repository jamespud/yahoo-stock-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 1,335 once invoked, about $0.0003 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 2026-09-28.

Related

Other skills, from other repositories