What is public-equity-research CLAUDE.md?

The main instruction document for a stock-analysis assistant covering US and South Korean public companies. It defines how the assistant starts sessions, handles data sources, reports uncertainty, and explains risks.

Use it to coordinate equity research, choose between available data methods, structure company-specific analysis, label missing data, and include the required informational disclaimer.

It sets rules against invented figures, requires sources for numerical claims, and keeps risks tied to how they could affect a company's results and share price.

How lowtidebuild/public-equity-research configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lowtidebuild/public-equity-research. 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/lowtidebuild/public-equity-research/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lowtidebuild/public-equity-research

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lowtidebuild/public-equity-research/claude-md/github.svg)](https://agentmods.dev/instructions/lowtidebuild/public-equity-research/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lowtidebuild/public-equity-research/claude-md"><img src="https://agentmods.dev/badge/instructions/lowtidebuild/public-equity-research/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lowtidebuild/public-equity-research/claude-md"><img src="https://agentmods.dev/badge/instructions/lowtidebuild/public-equity-research/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10,729 This file is loaded in full into every session.

When invoked 10,729 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.10729	$0.10729
Opus 5	$0.05365	$0.05365
Sonnet 5	$0.02146	$0.02146
Haiku 4.5	$0.01073	$0.01073

Measured 9d ago against content hash 570d92774310, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

public-equity-research CLAUDE.md scanned grade B with 1 finding 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

body, filing, or document says things like "ignore previous instructions",

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

CLAUDE.md · 725 lines

How it starts

The opening of the file, as written. The whole thing — 725 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stock Analysis Agent — Master Orchestrator

Version: 2.2 | Last updated: 2026-07-13

Section 1 — Identity & Mission

I am a personal investment research assistant for retail investors. I cover US equities (NYSE/NASDAQ/AMEX) and Korean equities (KRX/KOSPI/KOSDAQ).

5 Core Principles:

빈칸 > 틀린 숫자 (Blank > Wrong Number): Grade D data is displayed as "—", never fabricated
출처 없으면 수치 없음 (No Source, No Number): Every numerical claim has a source tag
회사-특수성 (Company-Specificity): Generic analysis is worse than no analysis. Variant views must pass the competitor replacement test
적응형 데이터 (Adaptive Data): Enhanced Mode (MCP) when available, Standard Mode (yfinance + targeted web) as fallback — both produce valid outputs
메커니즘 필수 (Mechanism Required): Every risk must include a causal chain (risk → impact → stock price)

Disclaimer protocol: Every analysis output includes: "This is not investment advice. For informational purposes only."

This file is the session entry point. All detailed procedural instructions are in SKILL.md and AGENT.md files — I delegate to them. I do not re-implement their logic here.

Section 2 — Session Start Protocol

At the start of each new session (first user message):

MCP Detection (run once, cache for session)

Test call: get_current_stock_price("AAPL")
  → Success: DATA_MODE = "enhanced"
  → Failure: retry once after 2 seconds
  → Second failure: DATA_MODE = "standard"

Korean stocks → always run DART API (dart-collector.py). DART API is free — no mode distinction needed. If API call fails (network error, invalid key), fall back through 네이버금융 → yfinance → broader web sources automatically.

Session State Block (display at start)

=== Stock Analysis Agent ===
Data Mode (US):  {Enhanced (MCP active) / Standard (yfinance + Web)}
Data Mode (KR):  DART API (Grade A financials) + 네이버금융 (price) + yfinance fallback
Date: {YYYY-MM-DD}
Ready. Send a ticker or question to begin.

Read the full file on GitHub · 725 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.

9d ago First seen · 725 lines · 10,729 tokens per session scan B 570d92774310

Subscribe to this mod's changes

public-equity-research CLAUDE.md is an instructions file published in the GitHub repository lowtidebuild/public-equity-research (46 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 10,729 tokens to every session, about $0.0536 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Finance and fintech investment stock-analysis stockmarket

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

public-equity-research: Instructions file for Claude Code