QuantRL-Lab CLAUDE.md

QuantRL-Lab CLAUDE.md is an instructions file for Claude Code from whanyu1212/QuantRL-Lab. It costs 2,870 tokens per session, scanned A, original, MIT.

A repository guide for a Python research project using uv for dependencies, pytest for tests, and pre-commit for code checks.

In plain words
What is it for?
Setting up the environment, installing optional machine-learning or notebook tools, running selected tests, measuring coverage, and checking code quality.
Why use it?
It shows developers which dependency groups and test commands to use, including the difference between local unit tests and integration tests that need API keys.

Instructions file for Claude Code

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

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/whanyu1212/quantrl-lab/claude-md
Clone the repo
git clone --depth 1 https://github.com/whanyu1212/QuantRL-Lab

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 QuantRL-Lab CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/whanyu1212/quantrl-lab/claude-md.svg)](https://agentmods.dev/instructions/whanyu1212/quantrl-lab/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/whanyu1212/quantrl-lab/claude-md"><img src="https://agentmods.dev/badge/instructions/whanyu1212/quantrl-lab/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,870 This file is loaded in full into every session.
When invoked 2,870 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02870 $0.02870
Opus 5 $0.01435 $0.01435
Sonnet 5 $0.00574 $0.00574
Haiku 4.5 $0.00287 $0.00287

Measured 6d ago against content hash fce87a7f5817, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

QuantRL-Lab 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 6d 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 · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 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.

Essential Commands

Package Management

This project uses uv (not Poetry). The lock file is uv.lock.

uv sync                                    # Core deps only
uv sync --extra dev --extra notebooks      # With dev/notebook extras
uv sync --all-extras                       # All optional features
source .venv/bin/activate

Optional dependency groups: dev, notebooks, ml (torch/transformers/litellm), tuning, viz, storage, full.

Testing

uv run pytest -m "not integration"         # Unit tests only (CI/CD - no API keys needed)
uv run pytest -m integration               # Integration tests (requires .env with API keys)
uv run pytest tests/data/test_indicators.py  # Specific test file
uv run pytest -k "test_portfolio"          # Tests matching pattern
uv run pytest --cov=quantrl_lab            # With coverage

Code Quality

Pre-commit hooks run automatically on git commit. Run manually with:

pre-commit install                         # One-time setup
pre-commit run --all-files
pre-commit run --files path/to/file.py    # Before committing changes

Hook configuration (.pre-commit-config.yaml):

  • Black: --line-length=120 --skip-string-normalization
  • isort: --profile black
  • flake8: --max-line-length=120
  • docformatter: Google-style, --wrap-summaries=72

Always run pre-commit run --files <changed_files> after significant changes. Common failures: unused imports (flake8), line length violations, missing/malformed docstrings.

Documentation

uv run mkdocs serve    # Local preview
uv run mkdocs build    # Build (always run before committing API changes)

When renaming modules or changing public APIs, update docs/api-reference/ to match actual module paths and run mkdocs build to verify.

Standalone guide tabs (top-level nav, each a self-contained reference):

  • docs/DATA_SOURCES.md — data loaders, capability matrix, usage per source
  • docs/data-processing.mdDataProcessor and DataPipeline with all 7 pipeline steps
  • docs/environments.md — action/observation/reward spaces, all reward strategies, full env example
  • docs/experiments.mdBacktestRunner, ExperimentJob, JobGenerator, AgentExplainer, OptunaRunner

Read the full file on GitHub · 263 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. 6d ago First seen · 263 lines · 2,870 tokens per session scan A fce87a7f5817

Subscribe to this mod's changes

QuantRL-Lab CLAUDE.md is an instructions file published in the GitHub repository whanyu1212/QuantRL-Lab (53 stars, last pushed 4mo ago), licensed MIT. It adds 2,870 tokens to every session, about $0.0144 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 2026-08-30.