openquant-trading

A stock-analysis and paper-trading toolkit that uses the OpenQuant service to examine companies, trading signals, risk, and simulated trades. Paper trading means placing practice trades without using real money.

In plain words
What is it for?
Analyzing stock tickers, reviewing insider activity and risk measures, generating signals, backtesting strategies, checking portfolios, and executing paper trades.
Why use it?
It brings stock research and risk checks into one workflow while keeping the described trading mode simulated.

Skill for Claude CodeCodex

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 skills/mitchellbernstein/openquant/openquant-trading
Any agent
npx skills add mitchellbernstein/openquant --skill openquant-trading
Clone the repo
git clone --depth 1 https://github.com/mitchellbernstein/openquant

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,128 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00025 $0.02128
Opus 5 $0.00013 $0.01064
Sonnet 5 $0.00005 $0.00426
Haiku 4.5 $0.00003 $0.00213

Measured yesterday against content hash 711a3351ece1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openquant-trading 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.

SKILLS/openquant-trading/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenQuant Trading Skill

When This Skill Activates

Activate this skill when the user:

  • Asks about a stock or ticker (e.g., "What do you think of AAPL?")
  • Wants trading signals or strategy recommendations
  • Mentions insider trading, risk, VaR, or position sizing
  • Wants to check their portfolio or execute a trade
  • Asks about backtesting or strategy validation
  • Uses terms like "analyze", "signal", "backtest", "Kelly", "insider buy"

Prerequisites

The OpenQuant MCP server must be running. Start it:

pip install openquant-cli[mcp]
openquant-mcp

MCP endpoint: http://localhost:8000/sse (SSE transport) Server name: openquant

Common Workflows

Workflow 1: Analyze a Stock

Use when: User asks about a ticker or wants a stock opinion.

  1. Call openquant_analyze(ticker="SYMBOL", days=90)
  2. Review the result: current_price, insider score/label, risk level, VaR, max drawdown
  3. If insider score is interesting (|score| > 25), call openquant_insider_scan(ticker="SYMBOL") for detail
  4. Summarize for the user: price, insider sentiment, risk level, and whether it's worth deeper investigation
  5. Do NOT execute any trades — this is research mode

Workflow 2: Get a Trading Signal

Use when: User wants a buy/sell recommendation for a ticker.

  1. Call openquant_strategy_list() if user doesn't specify a strategy
  2. Call openquant_strategy_run(strategy_name="STRATEGY", ticker="SYMBOL")
  3. Review: action (BUY/SELL/HOLD), confidence (0-100), entry_price, stop_loss, take_profit, position_size_pct, reasoning
  4. If confidence < 40: tell the user the signal is weak, suggest monitoring
  5. If confidence >= 40: present the signal with all details but do NOT execute without confirmation

Workflow 3: Validate a Strategy

Use when: User wants to know if a strategy works before using it.

  1. Call openquant_backtest(strategy_name="STRATEGY", ticker="SYMBOL", days=252)
  2. Review: total_trades, win_rate, total_return, max_drawdown, sharpe_ratio, avg_holding_days
  3. Flag concerns: win_rate < 50%, max_drawdown > 20%, sharpe < 0.5
  4. Present the backtest results with interpretation

Read the full file on GitHub · 171 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 · 171 lines · 25 tokens per session scan A 711a3351ece1

Subscribe to this mod's changes

openquant-trading is a skill published in the GitHub repository mitchellbernstein/openquant (2 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 2,128 once invoked, about $0.0001 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.