TradingAgents-KR: Skill for Codex

.agents/skills/korean-stock-analysis/SKILL.md

korean-stock-analysis is a skill for Codex from malda231125/TradingAgents-KR. It costs 120 tokens per session (1,551 once invoked), scanned A, original, Apache-2.0.

An on-demand analysis workflow for shares listed on South Korea's KOSPI and KOSDAQ markets. It produces a summary with key events that could move the price and sends the result to Slack or Telegram.

In plain words
What is it for?
Use it to analyze individual Korean stocks or run analysis for a watchlist, including checks related to market hours and foreign-investor activity.
Why use it?
It gives you a repeatable way to review a named Korean stock or its six-digit market code without manually assembling the analysis and report.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; mentions Codex.

This is malda231125/TradingAgents-KR's own configuration. It tells Codex 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/.agents/skills/korean-stock-analysis/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/malda231125/TradingAgents-KR

Made for: 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 korean-stock-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/malda231125/tradingagents-kr/korean-stock-analysis/github.svg)](https://agentmods.dev/skills/malda231125/tradingagents-kr/korean-stock-analysis)
Your own site
<a href="https://agentmods.dev/skills/malda231125/tradingagents-kr/korean-stock-analysis"><img src="https://agentmods.dev/badge/skills/malda231125/tradingagents-kr/korean-stock-analysis/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 korean-stock-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/malda231125/tradingagents-kr/korean-stock-analysis"><img src="https://agentmods.dev/badge/skills/malda231125/tradingagents-kr/korean-stock-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,551 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 $0.00120 $0.01551
Opus 5 $0.00060 $0.00776
Sonnet 5 $0.00024 $0.00310
Haiku 4.5 $0.00012 $0.00155

Measured 12d ago against content hash 8e149dff9eeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

korean-stock-analysis 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 12d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/analyze_kr_stock.sh, scripts/analyze_kr_watchlist.sh, scripts/kr_foreign_flow.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/korean-stock-analysis/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Korean Stock Analysis (Codex Skill)

Invoke explicitly with $korean-stock-analysis, or Codex selects it implicitly when the task matches the description (agents/openai.yaml sets allow_implicit_invocation). Repo-level AGENTS.md should point Codex here for KRX requests. Report a short plan + ETA before executing.

Layout

Installed at .agents/skills/korean-stock-analysis/ (Codex scans $REPO_ROOT/.agents/skills). Codex exposes no skill-dir variable, so invoke bundled scripts by their repo-root-relative path SKILL_DIR=.agents/skills/korean-stock-analysis (set it once per run, then use "$SKILL_DIR/scripts/…").

  • scripts/analyze_kr_stock.sh <code> <date> (detached runner → main.py), analyze_kr_watchlist.sh <date> [codes…], kr_is_open.py, kr_preflight.py, kr_foreign_flow.py.
  • references/report-format.md — the 📐 Slack/Telegram report template (single source).
  • agents/openai.yaml — Codex presentation/policy metadata.

Fixed facts

  • Repo TradingAgents-KR; bundled shell scripts auto-detect the repo root from the project-level skill path, or honor an exported $TRADINGAGENTS_KOREA_REPO when the skill is copied elsewhere. The bundled scripts cd into it themselves. Runner writes results/<code>/<date>/complete_report.md. The data pre-flight is built into main.py (aborts with DATA_UNAVAILABLE on empty KIS data). Ledger: 국내주식.md. Full run ~20–40 min.

Language (기본 한국어 · language-driven)

Global project — all user-facing output follows TRADINGAGENTS_REPORT_LANGUAGE in the repo .env (default ko). Read it before reporting:

  • ko (default) → Slack/Telegram summary, checkpoint labels, 국내주식.md ledger entries, and verification wording in Korean.
  • en → English · ja → Japanese · zh → Chinese (Simplified). Use the matching label map + example in references/report-format.md. The chat summary and the report share this language.
  • Write natively, never literally. Compose the summary directly in the target language's own financial register — do not translate the Korean/English word-for-word. Localize idioms, sentence flow, politeness level, and market terminology so a native reader finds it natural (a stiff literal translation is a failure). The templates are style references, not fill-in-the-blank strings. main.py already localizes complete_report.md from the same var, so the attached report and your summary share one language. Never translate tickers / proper nouns.

Read the full file on GitHub · 49 lines

Files

What ships with it

7 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. 12d ago First seen · 49 lines · 120 tokens per session scan A 8e149dff9eeb

Subscribe to this mod's changes

korean-stock-analysis is a skill published in the GitHub repository malda231125/TradingAgents-KR (6 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 120 tokens to every session and 1,551 once invoked, about $0.0006 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 skills, from other repositories

company

A single-company research interface for South Korean DART filings and United States EDGAR filings. It provides one object through which users can request company records, analysis, credit, prices, quantitative data, market context, industry information, and reports.

eddmpython/dartlab · 0 tokens

credit

A credit-risk analysis engine for one non-financial company. It assesses repayment, capital structure, liquidity, cash flow, business stability, financial reliability, and disclosure risk, then produces a dCR rating from dCR-AA+ to dCR-D.

eddmpython/dartlab · 0 tokens

dataHub

A central catalogue and query layer for source data, cleaned data, cross-company data, and analysis products. It lets other programs discover and request these assets through a shared contract.

eddmpython/dartlab · 0 tokens

gather

An engine for collecting outside data used in financial analysis, such as prices, news, dividends, ownership, sector information, and economic indicators. It can gather data for Korean and US stocks and create snapshots of the source data.

eddmpython/dartlab · 0 tokens

panel

A data tool that turns government financial disclosures into a wide table, with financial items as rows and reporting periods as columns. DART is South Korea’s public company filing system, and XBRL is a standard format for labeling financial data.

eddmpython/dartlab · 0 tokens

quant

A quantitative analysis tool for prices, trading volume, market factors, risk, public filings, rankings, portfolios, and strategy tests. A backtest checks how a trading strategy would have performed on past data.

eddmpython/dartlab · 0 tokens