TradingAgents-KR: Instructions file for Claude Code

CLAUDE.md

TradingAgents-KR CLAUDE.md is an instructions file for Claude Code from malda231125/TradingAgents-KR. It costs 1,553 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for TradingAgents Korea, a research tool that uses several AI agents to analyse Korean stocks and produce a Markdown report. It gathers Korean market data and news for KOSPI and KOSDAQ companies.

In plain words
What is it for?
Setting up the project in a virtual environment, running an analysis for a stock and date, using its command-line interface or Telegram bot, and finding the generated report.
Why use it?
It gives the coding agent the commands and setup needed to install and run the project. It also clarifies that the project is for research and education, not automated trading or investment advice.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is malda231125/TradingAgents-KR's own configuration. It tells Claude Code how to work on TradingAgents-KR itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TradingAgents-KR configures →

Reuse

Borrowing it

Nothing to install: this file belongs to malda231125/TradingAgents-KR. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/malda231125/TradingAgents-KR/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/malda231125/TradingAgents-KR

Made for: Claude Code.

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 TradingAgents-KR CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/malda231125/tradingagents-kr/claude-md/github.svg)](https://agentmods.dev/instructions/malda231125/tradingagents-kr/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/malda231125/tradingagents-kr/claude-md"><img src="https://agentmods.dev/badge/instructions/malda231125/tradingagents-kr/claude-md/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 TradingAgents-KR CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/malda231125/tradingagents-kr/claude-md"><img src="https://agentmods.dev/badge/instructions/malda231125/tradingagents-kr/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,553 This file is loaded in full into every session.
When invoked 1,553 The same file — it is already loaded in full.
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 $0.01553 $0.01553
Opus 5 $0.00776 $0.00776
Sonnet 5 $0.00311 $0.00311
Haiku 4.5 $0.00155 $0.00155

Measured 9d ago against content hash dc7c1186b153, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

TradingAgents-KR CLAUDE.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 9d 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.

CLAUDE.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

TradingAgents Korea is a Korea-market adaptation of TauricResearch/TradingAgents — a multi-agent LLM research workflow for KOSPI/KOSDAQ equities. It resolves Korean stock identifiers, prefetches data from Korean sources (KIS, DART, ECOS, Naver News) plus yfinance, builds compact feature packets, runs a LangGraph multi-agent debate, and emits a Markdown research report (Korean by default). It is a research/education project, not investment advice or an automated trading system.

Common commands

# Setup (editable install into a venv)
python3 -m venv .venv
.venv/bin/python -m pip install -e .
cp .env.example .env          # then fill in API keys

# Run a single analysis (defaults: ticker 005930, today KST)
.venv/bin/python main.py [TICKER] [YYYY-MM-DD]
# Report saved under ./results/<ticker>/<date>/complete_report.md

# Interactive Rich CLI
.venv/bin/python -m cli.main      # or `tradingagents` after install

# Telegram bot
.venv/bin/python -m cli.bot       # requires TELEGRAM_BOT_TOKEN

# Tests (bare unittest — no pytest config, no conftest)
.venv/bin/python -m unittest discover -s tests        # all tests
.venv/bin/python -m unittest tests.test_prefetch_cache # one module
.venv/bin/python -m unittest tests.test_cli_client.TestFactoryRouting  # one case

# OpenClaw → Notion publishing helper
python .openclaw/skills/tradingagents-korea-analysis/scripts/run_analysis_to_notion.py \
  --ticker 005930 --date YYYY-MM-DD --timeout 7200

Enable runtime timing traces with TRADINGAGENTS_TIMING_LOGS=1 (see tradingagents/runtime_trace.py).

Architecture

The pipeline: ticker resolution → data prefetch → feature packets → LangGraph agent workflow → Markdown/Notion report.

LLM execution — CLI-first, not API-first

The default provider is a local CLI backend, not a hosted API. tradingagents/llm_clients/factory.py routes llm_provider to a client; claude-cli and codex-cli both use CLIClient, which shells out to the claude or codex binary (see CLI_BACKEND_SPECS in cli_client.py) instead of sending an API key. anthropic/openai/google API clients also exist. Two model tiers are used everywhere: quick_think_llm and deep_think_llm. Provider/model defaults come from env vars (TRADINGAGENTS_LLM_PROVIDER, TRADINGAGENTS_QUICK_MODEL, TRADINGAGENTS_DEEP_MODEL) resolved in tradingagents/default_config.py.

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 1,553 tokens per session scan A dc7c1186b153

Subscribe to this mod's changes

TradingAgents-KR CLAUDE.md is an instructions file published in the GitHub repository malda231125/TradingAgents-KR (6 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,553 tokens to every session, about $0.0078 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens