What is ashare-ai-analyst CLAUDE.md?

Project instructions for an experimental platform that uses language models to analyse and predict Chinese A-share stock markets. A-share means mainland Chinese company shares traded in Shanghai or Shenzhen.

Use it when developing or reviewing this Python and React application, including its data collection, signal analysis, language-model decision process, risk controls, simulated execution, and Docker setup.

It explains the technology stack and how market data, analysis signals, risk checks, and simulated trading fit together. It also states that the results are not investment advice.

ashare-ai-analyst CLAUDE.md — Instructions file for coding agents by Jcstack: Project instructions for an experimental platform that uses la

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/jcstack/ashare-ai-analyst/claude-md

Clone the repo

git clone --depth 1 https://github.com/Jcstack/ashare-ai-analyst

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/jcstack/ashare-ai-analyst/claude-md.svg)](https://agentmods.dev/instructions/jcstack/ashare-ai-analyst/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jcstack/ashare-ai-analyst/claude-md"><img src="https://agentmods.dev/badge/instructions/jcstack/ashare-ai-analyst/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 966 This file is loaded in full into every session.

When invoked 966 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.

Model	Per session	Once invoked
Fable 5	$0.00966	$0.00966
Opus 5	$0.00483	$0.00483
Sonnet 5	$0.00193	$0.00193
Haiku 4.5	$0.00097	$0.00097

Measured 3d ago against content hash 92f2e5a15a8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ashare-ai-analyst 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 3d 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code and other AI assistants working in this repository. For full detail, read docs/guides/development-guide.md.

Project

LLM-powered A-share (Chinese stock) market analysis & prediction platform. Personal learning / technical-exploration toy project — outputs are not investment advice (see the disclaimer in README.md).

Stack

Python 3.13 · FastAPI · React 19 + TypeScript · AKShare · Qlib (optional) · Celery + Redis · SQLite · Docker Compose. LLM layer: Claude (via the Claude Code bridge or the Anthropic API) + Google Gemini fallback — configured in config/llm.yaml.

Architecture

AI-first (v2): three signal sources → autonomous OODA agent loop → risk gates → (simulated) execution, over a Redis-Streams event bus.

src/data/ (multi-source data) → signals: src/intelligence/ + src/intelligence_hub/ (intel pipeline, knowledge graph), src/quant/ (HMM regime, alpha, signal library), src/recommendation/ (智能选股) → src/agent_loop/ (OODA: aggregate → Bayesian prescreen → debate → risk gates → Kelly sizing; InvestmentDirector, ThesisTracker, calibration) → src/risk/ + src/trading/ (circuit breaker, VaR, gates, A-share constraints — simulation only)

Event bus src/event_bus/ (Redis Streams) · classic analysis src/analysis/ → src/prediction/ → src/strategy/ + src/backtest/
Web API src/web/ (FastAPI) · Frontend frontend/ (React SPA)
LLM gateway src/llm/ (multi-provider router + Claude Code bridge) · legacy agents src/agents/
Market intelligence src/market_intelligence/, src/intelligence/
Automation openclaw/ (Celery beat + always-on daemon) · Config config/*.yaml
Research workstation research/ — a separate Claude Code project root with an analyst persona (cd research && claude; see research/CLAUDE.md)

Setup

python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env          # then fill in your API keys
cd frontend && npm install

Read the full file on GitHub · 82 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.

3d ago First seen · 82 lines · 966 tokens per session scan A 92f2e5a15a8e

Subscribe to this mod's changes

ashare-ai-analyst CLAUDE.md is an instructions file published in the GitHub repository Jcstack/ashare-ai-analyst (5 stars, last pushed 2mo ago), licensed MIT. It adds 966 tokens to every session, about $0.0048 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.

Analytics and metrics Finance and fintech LLM a-share ai-agent akshare backtesting fastapi

china-financial-services AGENTS.md

Instructions for cyijun/china-financial-services, covering agents.md, 项目边界, 目录、marketplace 与唯一数据源, 数据、安全与研究证据 and 修改原则.

cyijun/china-financial-services · 1,503 tokens

aifolimizer CLAUDE.md

Instructions for tusharagg1/aifolimizer, covering aifolimizer - project context, session startup (read every new session), what this is, architecture and how to start.

tusharagg1/aifolimizer · 3,156 tokens

all-weather-portfolio CLAUDE.md

Claude Code instructions for IdealAuror/all-weather-portfolio, covering claude.md, 策略优化闭环, 前置原则, 第 0 层：哲学基座 and sperandeo 三层结构.

IdealAuror/all-weather-portfolio · 3,434 tokens

china-financial-services CLAUDE.md

Instructions for cyijun/china-financial-services, a project described as: AI agent plugins & managed-agent templates for China A-share market research and financial modeling, powered by Tushare. Research workflows and valuation tools for professional analyst review—not investment advice. | 面向中国 A 股市场的 AI…

cyijun/china-financial-services · 3 tokens

aktools-pro AGENTS.md

AGENTS.md instructions for tchivs/aktools-pro, covering agents.md - cross-agent development guide, 🤖 multi-agent compatibility protocol, 🎯 role & mission, 🏗 project architecture and 🛠 standard operating procedures (sops).

tchivs/aktools-pro · 1,619 tokens

TradingAgents-astock CLAUDE.md

Claude Code instructions for simonlin1212/TradingAgents-astock, covering tradingagents-astock, 项目概述, 架构, 数据层（v0.2.5 全部直连 http，零第三方数据库依赖） and agent 角色（7 个）.

simonlin1212/TradingAgents-astock · 3,359 tokens