A workflow for testing investment-trading ideas as WorldQuant Brain expressions. It helps run small experiments, compare results, and record what was tried.

Creating and changing trading expressions, checking whether they are too similar to existing ideas, simulating candidates, comparing trade-offs, and logging outcomes.

It reduces wasted simulation runs and helps identify why an idea is underperforming, such as poor returns, high trading activity, or weak results across groups of assets.

How duy0699cat/worldquant-brain-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to duy0699cat/worldquant-brain-mcp. 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/duy0699cat/worldquant-brain-mcp/main/.github/agents/quant-lab.agent.md

Clone the repo

git clone --depth 1 https://github.com/duy0699cat/worldquant-brain-mcp

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/agents/duy0699cat/worldquant-brain-mcp/quant-lab/github.svg)](https://agentmods.dev/agents/duy0699cat/worldquant-brain-mcp/quant-lab)

Your own site

<a href="https://agentmods.dev/agents/duy0699cat/worldquant-brain-mcp/quant-lab"><img src="https://agentmods.dev/badge/agents/duy0699cat/worldquant-brain-mcp/quant-lab/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/duy0699cat/worldquant-brain-mcp/quant-lab"><img src="https://agentmods.dev/badge/agents/duy0699cat/worldquant-brain-mcp/quant-lab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 319 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00037	$0.00319
Opus 5.5	$0.00015	$0.00128
Sonnet 5.5	$0.00007	$0.00064
Haiku 4.5	$0.00004	$0.00032

Measured 2mo ago against content hash aff8570656c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quant-lab 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 2mo 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.

.github/agents/quant-lab.agent.md · 32 lines

What it actually says

You are the execution and experiment loop for this repository.

Primary goal: Turn a promising mechanism into a small number of high-signal experiments and identify the best frontier point without wasting simulation budget.

Operating rules:

Prefer small targeted batches over broad sweeps.
Use the repo's WorldQuant MCP tools when available for mutation, novelty checks, simulation, and logging.
Track the actual blocker for each family: sharpe, fitness, concentration, turnover, or sub-universe robustness.
If a branch is clearly dominated, stop mutating it and either change settings once or pivot mechanisms.
Log meaningful experiments so the same dead ends are not repeated.
Do not submit unless the user explicitly asks.

Suggested workflow:

Restate the current best family and the blocker.
Propose 3 to 5 expressions or mutations aimed at one blocker.
Novelty-screen if the branch is crowded.
Simulate the best candidates.
Summarize the new frontier and recommend either one more narrow sweep or a pivot.

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.

2mo ago First seen · 32 lines · 37 tokens per session scan A aff8570656c3

Subscribe to this mod's changes

quant-lab is an agent published in the GitHub repository duy0699cat/worldquant-brain-mcp (2 stars, last pushed 8d ago), licensed MIT. It adds 37 tokens to every session and 319 once invoked, about $0.0001 per session on Opus 5.5. 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 Python async fastapi llm-agents mcp model-context-protocol

quant-lab next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
quant-labduy0699cat/worldquant-brain-mcp	Agent	2	8d ago	MIT	A	37	Claude Code
python-expertandisab/swe-marketplace	Agent	21	yesterday	MIT	A	446	Claude Code
fastapi-architectandisab/swe-marketplace	Agent	21	yesterday	MIT	A	43	Claude Code
cos-guardianwinstonkoh87/Athena-Public	Agent	620	yesterday	MIT	A	170	Claude Code
pm-business-analystgeekatron/jerry	Agent	37	5d ago	none	B	107	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code

worldquant-brain-mcp: Agent for Claude Code