pykrx-mcp copilot-instructions.md

pykrx-mcp copilot-instructions.md is an instructions file for GitHub Copilot from sharebook-kr/pykrx-mcp. It costs 2,226 tokens per session, scanned A, original, MIT.

Development instructions for pykrx-mcp, an MCP server that lets AI agents query Korean KOSPI and KOSDAQ stock-market data through the pykrx library.

In plain words
What is it for?
Use them when developing, versioning, testing, documenting, or releasing the pykrx-mcp server and its stock-data tools.
Why use it?
They provide project-specific rules for architecture, versioning, logging, tool definitions, and automated releases, reducing inconsistent changes.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

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.

agentmods
npx agentmods add instructions/sharebook-kr/pykrx-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/sharebook-kr/pykrx-mcp

Made for: GitHub Copilot.

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 pykrx-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sharebook-kr/pykrx-mcp/copilot-instructions.svg)](https://agentmods.dev/instructions/sharebook-kr/pykrx-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/sharebook-kr/pykrx-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sharebook-kr/pykrx-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,226 This file is loaded in full into every session.
When invoked 2,226 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02226 $0.02226
Opus 5 $0.01113 $0.01113
Sonnet 5 $0.00445 $0.00445
Haiku 4.5 $0.00223 $0.00223

Measured 5d ago against content hash d8d47c802b45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pykrx-mcp copilot-instructions.md 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.

.github/copilot-instructions.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pykrx-mcp Development Guide

Project Overview

This is an MCP (Model Context Protocol) server that exposes the pykrx Korean stock market data library to AI agents like Claude Desktop. The server runs via stdio and provides tools for querying KOSPI/KOSDAQ stock data.

Architecture

Core Components:

  • src/pykrx_mcp/server.py: FastMCP server with tool definitions
  • src/pykrx_mcp/__about__.py: Single source of truth for version management
  • server.json: MCP official registry metadata (auto-synced with Python version)
  • .github/workflows/publish.yml: Fully automated dual-platform release workflow

MCP stdio Pattern:

  • All logging MUST go to sys.stderr (stdout is reserved for MCP protocol communication)
  • Tool functions are decorated with @mcp.tool() and use type hints for LLM schema generation
  • Resources are decorated with @mcp.resource() to provide static documentation and guides
  • Entry point: mcp.run() in main() function

Version Management

Single source of truth: src/pykrx_mcp/__about__.py

__version__ = "x.y.z"

Fully Automated Release Workflow

Two automated paths to release:

Path 1: Upstream pykrx Update (Fully Automated)

Trigger: repository_dispatch event from pykrx repository

What happens:

  1. CI upgrades pykrx dependency: uv lock --upgrade-package pykrx
  2. Bumps patch version in __about__.py (e.g., 0.1.00.1.1)
  3. Commits: uv.lock, __about__.py
  4. Creates git tag v0.1.1
  5. Pushes commit and tag to main branch
  6. Tag push triggers Path 2 (below)

Zero manual intervention required.

Path 2: Tag Push (Fully Automated)

Trigger: Git tag push matching v* pattern

What happens:

  1. Updates server.json version to match tag
  2. Builds Python package: uv build
  3. Publishes to PyPI via OIDC Trusted Publishing
  4. Creates GitHub Release with auto-generated notes
  5. MCP Registry can consume updated server.json metadata

Works for both:

  • Tags created by Path 1 (automated)
  • Tags created manually (see below)

Read the full file on GitHub · 249 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. 5d ago First seen · 249 lines · 2,226 tokens per session scan A d8d47c802b45

Subscribe to this mod's changes

pykrx-mcp copilot-instructions.md is an instructions file published in the GitHub repository sharebook-kr/pykrx-mcp (3 stars, last pushed 7mo ago), licensed MIT. It adds 2,226 tokens to every session, about $0.0111 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.

Related

Other instructions, from other repositories