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/mitchellbernstein/openquant/agents-mdgit clone --depth 1 https://github.com/mitchellbernstein/openquantWhat 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 | $0.01649 | $0.01649 |
| Opus 5 | $0.00825 | $0.00825 |
| Sonnet 5 | $0.00330 | $0.00330 |
| Haiku 4.5 | $0.00165 | $0.00165 |
Grade A, and why
openquant AGENTS.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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- openquant CLAUDE.md — 92% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenQuant — Codex / OpenCode Agent Instructions
This file teaches Codex and OpenCode agents how to use OpenQuant's trading tools via the MCP server.
MCP Server Connection
OpenQuant exposes an MCP server with SSE transport. Start it with:
pip install openquant-cli[mcp]
openquant-mcp
The server runs at http://localhost:8000/sse by default.
MCP Client Configuration
For Codex/OpenCode, configure the MCP server in your agent settings:
SSE transport (remote):
{
"mcpServers": {
"openquant": {
"url": "http://localhost:8000/sse",
"transport": "sse"
}
}
}
Stdio transport (local process):
{
"mcpServers": {
"openquant": {
"command": "openquant-mcp",
"transport": "stdio"
}
}
}
Available MCP Tools
Research & Analysis
| Tool | When to Use | Key Params |
|---|---|---|
openquant_analyze |
First stop for any ticker — full analysis combining prices, insider, risk | ticker, days (default 90) |
openquant_insider_scan |
Deep dive on insider buying/selling activity | ticker, days (default 90) |
openquant_risk_assessment |
Before any trade — volatility, VaR, drawdown, Kelly fraction | tickers (comma-separated), days (default 252) |
Strategy & Signals
| Tool | When to Use | Key Params |
|---|---|---|
openquant_strategy_list |
Discover available strategies | none |
openquant_strategy_run |
Generate a trade signal for a specific strategy + ticker | strategy_name, ticker |
openquant_backtest |
Validate a strategy on historical data | strategy_name, ticker, days (default 252) |
Portfolio & Execution
| Tool | When to Use | Key Params |
|---|---|---|
openquant_portfolio_status |
Check current positions, balance, P&L | none |
openquant_trade_execute |
Execute a paper trade (game mode) | action, ticker, shares, price |
openquant_trade_history |
Review recent trades | limit (default 20) |
openquant_game_status |
Game mode leaderboard and achievements | none |
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.
- yesterday First seen · 166 lines · 1,649 tokens per session scan A 80f397af5acc
openquant AGENTS.md is an instructions file published in the GitHub repository mitchellbernstein/openquant (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,649 tokens to every session, about $0.0082 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.
Other instructions, from other repositories
awesome-quant AGENTS.md
AGENTS.md instructions for wilsonfreitas/awesome-quant, covering agents.md, project overview, architecture, commands and install deps (requires python 3.11+).
kalshi-trading-bot-cli CLAUDE.md
Instructions for OctagonAI/kalshi-trading-bot-cli, covering claude.md and workflow.
tradingview-mcp-server CLAUDE.md
Instructions for fiale-plus/tradingview-mcp-server, covering claude.md, project overview, build and development commands, running a single test file and development workflow.
eodhd-claude-skills CLAUDE.md
Instructions for EodHistoricalData/eodhd-claude-skills, covering eodhd claude skills, file structure, key components, development setup and testing.
secedgar-mcp-server AGENTS.md
Instructions for cyanheads/secedgar-mcp-server, covering agent protocol, core rules, what's next?, mcp surface and tools.
tiingo-mcp AGENTS.md
Instructions for major7apps/tiingo-mcp, covering agents.md, project map, public contract, operating rules and commands.