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.
npx agentmods add instructions/whanyu1212/quantrl-lab/claude-mdgit clone --depth 1 https://github.com/whanyu1212/QuantRL-LabWrote 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.
[](https://agentmods.dev/instructions/whanyu1212/quantrl-lab/claude-md)<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>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 | $0.02870 | $0.02870 |
| Opus 5 | $0.01435 | $0.01435 |
| Sonnet 5 | $0.00574 | $0.00574 |
| Haiku 4.5 | $0.00287 | $0.00287 |
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.
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 sourcedocs/data-processing.md—DataProcessorandDataPipelinewith all 7 pipeline stepsdocs/environments.md— action/observation/reward spaces, all reward strategies, full env exampledocs/experiments.md—BacktestRunner,ExperimentJob,JobGenerator,AgentExplainer,OptunaRunner
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.
- 6d ago First seen · 263 lines · 2,870 tokens per session scan A fce87a7f5817
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.
Other instructions, from other repositories
PINA AGENTS.md
AGENTS.md instructions for PINA-org/PINA, covering pina — physics-informed neural architectures, quick reference, workflow: problem → model → solver → trainer, problem types and condition types.
tensorcircuit-ng AGENTS.md
AGENTS.md instructions for tensorcircuit/tensorcircuit-ng, covering tensorcircuit-ng repository guide for ai agents, mission, non-negotiable rules, environment rules and where to look first.
PINA CLAUDE.md
Claude Code instructions for PINA-org/PINA, a project described as: Physics-Informed Neural networks for Advanced modeling.
kite-mcp-server CLAUDE.md
Claude Code instructions for Sundeepg98/kite-mcp-server, covering claude.md - kite mcp server, what it is, branch / repo, commands and deploy the hosted app (manual).
clawock AGENTS.md
AGENTS.md instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.
bio-gene-to-reference-tree copilot-instructions.md
Copilot instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.