cursorrules

Cursor rules for connecting to OpenQuant, a local service that analyzes stocks, portfolios, trading strategies, and paper trades.

In plain words
What is it for?
Use them to request stock analysis, insider-activity scans, risk assessments, strategy signals, backtests, portfolio status, paper trades, and trade history.
Why use it?
They document how to start the service and which analysis or trading operation to use for each task.

Cursor rule for Cursor

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 rules/mitchellbernstein/openquant/cursorrules
Clone the repo
git clone --depth 1 https://github.com/mitchellbernstein/openquant

Made for: Cursor.

Per session 631 This file is loaded in full into every session.
When invoked 631 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 $0.00631 $0.00631
Opus 5 $0.00316 $0.00316
Sonnet 5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured yesterday against content hash 27020585169c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenQuant — Cursor AI Rules

MCP Connection

Start: pip install openquant[mcp] && openquant-mcp Default URL: http://localhost:8000/sse (SSE transport) Alternative: openquant-mcp as stdio command

Tool Quick Reference

Tool Purpose Key Args
openquant_analyze Full stock analysis (prices + insider + risk) ticker, days=90
openquant_insider_scan Insider buying/selling scan ticker, days=90
openquant_risk_assessment VaR, drawdown, Kelly, risk level tickers (csv), days=252
openquant_strategy_list List 4 built-in strategies
openquant_strategy_run Generate trade signal strategy_name, ticker
openquant_backtest Historical strategy validation strategy_name, ticker, days=252
openquant_portfolio_status Positions, balance, P&L
openquant_trade_execute Paper trade execution action, ticker, shares, price
openquant_trade_history Recent trades log limit=20
openquant_game_status Game mode stats

Workflow

  1. openquant_analyze → get the picture
  2. openquant_insider_scan + openquant_strategy_run → dig deeper
  3. openquant_risk_assessment → MANDATORY before any trade
  4. Confirm confidence >= 40 → openquant_trade_execute

Risk Rules

  • 0.25x Kelly for position sizing (built into tools, do not override)
  • Max 10% of portfolio per single position (system-enforced hard limit)
  • Confidence < 40 = HOLD (monitor only, do not trade)
  • Always show risk assessment before executing any trade
  • Never execute live trades without explicit user confirmation

Signal Scale

  • Agent signals: -1.0 (strong sell) to +1.0 (strong buy)
    • +0.3 to +1.0 = BULLISH
    • -0.3 to +0.3 = NEUTRAL
    • -1.0 to -0.3 = BEARISH
  • Strategy confidence: 0–100 (act only if >= 40)
  • Insider score: -100 to +100 (>= 60 = STRONG BUY, <= -60 = STRONG SELL)

Data Units (QuantFetch)

  • Earnings: in cents (250 = $2.50)
  • Revenue: in thousands (50000 = $50M)

Read the full file on GitHub · 56 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. yesterday First seen · 56 lines · 631 tokens per session scan A 27020585169c

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository mitchellbernstein/openquant (2 stars, last pushed 4mo ago), licensed MIT. It adds 631 tokens to every session, about $0.0032 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.