What is open-xquant CLAUDE.md?

Project instructions for open-xquant, an agent-based quantitative research system. They describe the project layout and how bugs should be fixed using TDD, or test-driven development.

Use them when navigating open-xquant, fixing bugs, keeping related files in sync, or running its test suite.

They give an agent consistent rules for understanding the repository, writing tests before fixes, and checking that changes do not cause regressions.

How xingwudao/open-xquant configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to xingwudao/open-xquant. 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/xingwudao/open-xquant/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/xingwudao/open-xquant

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/xingwudao/open-xquant/claude-md.svg)](https://agentmods.dev/instructions/xingwudao/open-xquant/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/xingwudao/open-xquant/claude-md"><img src="https://agentmods.dev/badge/instructions/xingwudao/open-xquant/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 706 This file is loaded in full into every session.

When invoked 706 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00706	$0.00706
Opus 5	$0.00353	$0.00353
Sonnet 5	$0.00141	$0.00141
Haiku 4.5	$0.00071	$0.00071

Measured 8d ago against content hash ff9b98bd2c03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

open-xquant 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 8d 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

open-xquant is an Agentic Quant Research Kernel. See README.md for motivation and docs/architecture.md for full design.

Project Structure

src/oxq/ — main Python package (pip install open-xquant)
agent/ — Agent layer (skills, bootstrap configs, OpenCode integration)
- agent/skills/ — Agent skill definitions (markdown workflows)
- agent/openclaw/bootstrap/ — Agent startup files (OpenClaw etc.)
- agent/opencode/ — OpenCode integration (agents, commands, skills)
examples/ — example strategies, research cases, module demos
tests/ — mirrors src/oxq/ structure
docs/ — documentation

Bug Fixing

Follow this strict TDD protocol for every bug fix:

Write a failing test first — describe the expected behavior with hand-calculated values, not values copied from buggy code.
Run the test, confirm it fails for the right reason — if it passes, your understanding of the bug is wrong.
Implement the smallest possible fix — no refactoring, no drive-by improvements.
Run the new test — confirm it passes.
Run the full test suite (uv run pytest) — confirm no regressions.
Grep for the same pattern across the entire codebase — fix ALL instances before declaring done. E.g., if prices = {symbol: price} is wrong in risk.py, check entry.py, rebalance.py, etc.

Never guess root causes — provide concrete evidence (specific line numbers, variable values) before proposing a fix.

Cross-File Sync

When fixing a bug or updating logic in one module, always check and update all related modules that share the same pattern. Use grep to find all affected locations before editing any of them.

Conventions

Code and comments in English
User-facing docs may be in Chinese
Follow ruff defaults (E, F, I, N, W, UP rules)
Prefer Protocol over ABC for interfaces
Keep Indicator/Signal compute functions pure (no side effects)
Do not add new top-level directories — this is an open-source project; keep the root structure stable. New apps, demos, and examples go under examples/.

Read the full file on GitHub · 57 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.

8d ago First seen · 57 lines · 706 tokens per session scan A ff9b98bd2c03

Subscribe to this mod's changes

open-xquant CLAUDE.md is an instructions file published in the GitHub repository xingwudao/open-xquant (126 stars, last pushed 5d ago), licensed MIT. It adds 706 tokens to every session, about $0.0035 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.

Building agents Scientific

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

open-xquant: Instructions file for Claude Code