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/wolfpackofone/q-agent/agents-mdgit clone --depth 1 https://github.com/WolfpackOfOne/Q-agentWhat 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 | $0.05903 | $0.05903 |
| Opus 5 | $0.02951 | $0.02951 |
| Sonnet 5 | $0.01181 | $0.01181 |
| Haiku 4.5 | $0.00590 | $0.00590 |
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.
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)
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.
- 2d ago First seen · 601 lines · 5,903 tokens per session scan A 975dd2865d07
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.
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.
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+).
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+).
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.
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).
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…