What is quantcli CLAUDE.md?

A project instruction file for QuantCLI, a command-line tool for selecting stocks using several measurable factors. It explains the project's structure, design rules, data handling, and multi-stage filtering process.

Use it when working on QuantCLI's data sources, formula parser, core engine, JSON output, or stock-selection pipeline.

It gives a coding agent the repository context and rules it needs to make consistent changes. This reduces guesswork about where code belongs and how the tool should behave.

quantcli CLAUDE.md — Instructions file by wumu2013

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/wumu2013/quantcli/claude-md

Clone the repo

git clone --depth 1 https://github.com/wumu2013/quantcli

Per session 2,660 This file is loaded in full into every session.

When invoked 2,660 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	$0.02660	$0.02660
Opus 5	$0.01330	$0.01330
Sonnet 5	$0.00532	$0.00532
Haiku 4.5	$0.00266	$0.00266

Measured 2d ago against content hash 7849d882a50e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quantcli 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 2d 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 · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 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.

Project Overview

QuantCLI - A multi-factor stock selection CLI tool for quantitative research.

AI Agent Friendly: Designed for AI Agent integration with:

JSON output mode (--json) for structured data
Claude Code Skill support (/skill multi-factor-strategy)
Idempotent APIs for safe retries
Alpha101 factor library examples

Target Users: Individual quant researchers, students, part-time investors, AI Agents

Core Design Principles

Let it Crash: Fail fast, fail loud. No tolerance for silent errors. Force correctness.
YAGNI: You Aren't Gonna Need It. Resist over-engineering. Solve today's problems.
80/20 Rule: 80% of use cases covered by 20% of features.
DataFrame First: All APIs return/accept pd.DataFrame, not List[Dict].

Architecture

quantcli/
├── datasources/      # 数据源适配器 (akshare, baostock, mixed, mysql)
├── parser/           # 公式表达式解析器 (40+ 内置函数)
│   ├── formula.py    # 核心解析器
│   └── constants.py  # BUILTIN_FUNCTIONS, COLUMN_ALIASES
├── core/             # 核心引擎
│   ├── data.py       # DataManager: 缓存、清洗
│   ├── factor.py     # FactorEngine, Factor, FactorRegistry
│   └── backtest.py   # BacktestEngine, YAMLBacktestEngine
├── factors/          # 因子配置 (推荐使用新 API)
│   ├── base.py       # 数据类 (FactorDefinition, StrategyConfig, BacktestConfig)
│   ├── loader.py     # load_strategy(), load_factor(), load_all_factors()
│   ├── screening.py  # ScreeningEvaluator
│   ├── compute.py    # FactorComputer (返回 DataFrame)
│   ├── ranking.py    # FactorRanker, ScoringEngine
│   └── pipeline.py   # FactorPipeline: 多阶段编排
├── cli.py            # CLI 入口点
└── utils/            # 工具函数

Multi-Stage Filter Pipeline Flow

Stage 1: fundamental_data → fundamental_conditions → candidates
Stage 2: price_data → daily_conditions → filtered candidates
Stage 3: factors → weight fusion + conditions + bonuses → ranked results

Read the full file on GitHub · 312 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.

2d ago First seen · 312 lines · 2,660 tokens per session scan A 7849d882a50e

Subscribe to this mod's changes

quantcli CLAUDE.md is an instructions file published in the GitHub repository wumu2013/quantcli (5 stars, last pushed 7mo ago), licensed MIT. It adds 2,660 tokens to every session, about $0.0133 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.

Planning

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 · 5,182 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

quantcli CLAUDE.md