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 agentmods add instructions/sharebook-kr/pykrx-mcp/copilot-instructionsgit clone --depth 1 https://github.com/sharebook-kr/pykrx-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/instructions/sharebook-kr/pykrx-mcp/copilot-instructions)<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>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 | $0.02226 | $0.02226 |
| Opus 5 | $0.01113 | $0.01113 |
| Sonnet 5 | $0.00445 | $0.00445 |
| Haiku 4.5 | $0.00223 | $0.00223 |
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.
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 definitionssrc/pykrx_mcp/__about__.py: Single source of truth for version managementserver.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()inmain()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:
- CI upgrades pykrx dependency:
uv lock --upgrade-package pykrx - Bumps patch version in
__about__.py(e.g.,0.1.0→0.1.1) - Commits:
uv.lock,__about__.py - Creates git tag
v0.1.1 - Pushes commit and tag to main branch
- 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:
- Updates
server.jsonversion to match tag - Builds Python package:
uv build - Publishes to PyPI via OIDC Trusted Publishing
- Creates GitHub Release with auto-generated notes
- MCP Registry can consume updated
server.jsonmetadata
Works for both:
- Tags created by Path 1 (automated)
- Tags created manually (see below)
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.
- 5d ago First seen · 249 lines · 2,226 tokens per session scan A d8d47c802b45
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.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.