Q-agent AGENTS.md

A set of working rules for AI agents in a QuantConnect workspace. QuantConnect is a platform for developing and testing trading algorithms, and the document explains the workspace layout and boundaries.

In plain words
What is it for?
Guide work on algorithm projects, locate project documentation, follow workspace assumptions, and keep the LEAN engine and other out-of-scope areas untouched.
Why use it?
It gives agents shared project context and identifies which files and parts of the workspace they should or should not change.

Instructions file for CodexOpenCode

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 instructions/wolfpackofone/q-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/WolfpackOfOne/Q-agent

Made for: Codex, OpenCode.

Per session 5,903 This file is loaded in full into every session.
When invoked 5,903 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 $0.05903 $0.05903
Opus 5 $0.02951 $0.02951
Sonnet 5 $0.01181 $0.01181
Haiku 4.5 $0.00590 $0.00590

Measured 2d ago against content hash 975dd2865d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Q-agent 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 2d 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.

AGENTS.md · 601 lines

How it starts

The opening of the file, as written. The whole thing — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - AI Agent Guidelines for QuantConnect Workspace

Purpose

This document provides guardrails and expectations for AI agents working in this QuantConnect workspace. It is project-agnostic and applies to any algorithm developed here.

For project-specific rules, check for AGENTS.md or claude.md files within individual project directories.


Workspace Structure

Q-agent/
├── venv/                    # Shared Python virtual environment
├── Lean/                    # LEAN engine checkout (OUT OF SCOPE - do not edit)
├── AGENTS.md                # This file (workspace-level guidelines)
├── claude.md                # Workspace setup and CLI reference
├── Dockerfile               # Workspace runtime image (LEAN CLI + pipelines + marimo)
├── .dockerignore            # Build-context exclusions; mirrors .gitignore
├── .github/workflows/       # CI: tests, docs, secret-scan, docker (GHCR publish)
├── .claude/
│   ├── agents/              # Agent prompts (new-strategy-coder, new-pipeline-coder, ...)
│   └── skills/              # Project-scoped skills (/docker-workflow, /marimo-pair, ...)
├── infrastructure/          # Data pipelines & tooling (NOT algorithm code)
│   └── pipelines/
│       ├── crypto/              # CCXT crypto OHLCV pipeline
│       ├── edgar/               # SEC EDGAR fundamentals (edgartools)
│       ├── openbb/              # OpenBB Platform notes (interactive use)
│       ├── polymarket/          # Polymarket metadata and prices pipeline
│       ├── wrds/                # WRDS/CRSP pipeline
│       ├── yfinance/            # Yahoo Finance OHLCV pipeline
│       └── treasury_gov_rates/  # Treasury.gov daily par yield curve
├── References/              # Reference notes, papers, and repo index
└── MyProjects/              # Active strategy code lives here (each project is typically its own Git repo)
    ├── lean.json            # LEAN CLI configuration (shared, gitignored)
    ├── data/                # Local sample market data (gitignored; populate via `lean init`)
    ├── storage/             # ObjectStore artifacts (gitignored)
    ├── .claude/agents/      # Agent-specific guides (lean-cli.md, github-sync.md)
    ├── shared/              # Reusable signal atoms (never pushed to any project)
    │   └── signals/         # Pure Python signal files — symlinked into projects that need them
    └── <ProjectName>/       # Individual project repo
        ├── main.py          # Composition root (QCAlgorithm entry point)
        ├── config.json      # Cloud/local IDs (NOT committed)
        ├── AGENTS.md        # Project-specific agent rules (optional)
        ├── claude.md        # Project-specific documentation (optional)
        ├── docs/            # Detailed documentation (optional)
        └── ...              # Project modules (atoms, molecules, organisms)

Read the full file on GitHub · 601 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. 2d ago First seen · 601 lines · 5,903 tokens per session scan A 975dd2865d07

Subscribe to this mod's changes

Q-agent AGENTS.md is an instructions file published in the GitHub repository WolfpackOfOne/Q-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 5,903 tokens to every session, about $0.0295 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.

Related

Other instructions, from other repositories

quant-mind AGENTS.md

Instructions for LLMQuant/quant-mind, covering quantmind — agent instructions, progressive context loading, what this is, positioning and module map.

LLMQuant/quant-mind · 2,189 tokens

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+).

wilsonfreitas/awesome-quant · 1,367 tokens

awesome-quant CLAUDE.md

Claude Code instructions for wilsonfreitas/awesome-quant, covering claude.md, project overview, architecture, commands and install dependencies (uses uv, requires python 3.11+).

wilsonfreitas/awesome-quant · 1,118 tokens

martex-quant CLAUDE.md

Instructions for martex-dev/martex-quant, covering session start — read these first, project instructions, ai trading bot project - master instructions, role and project objective.

martex-dev/martex-quant · 6,161 tokens

NexusTrader CLAUDE.md

Instructions for Quantweb3-com/NexusTrader, covering claude.md, project overview, development commands, dependencies and setup and install with uv (package manager used in this project).

Quantweb3-com/NexusTrader · 1,552 tokens

quant-mind CLAUDE.md

Instructions for LLMQuant/quant-mind: CLAUDE.md imports AGENTS.md as the single source of repository instructions for coding agents. Do not duplicate rules here — edit AGENTS.md. Add Claude Code- specific guidance (if any) below the import. This block-level HTML comment is stripped from Claude's context at load, so it…

LLMQuant/quant-mind · 75 tokens