Machine Learning for Trading is a code repository and companion resource for developing machine-learning trading strategies, covering data collection, feature and model development, backtesting, risk, deployment, and monitoring. It is used by readers and practitioners following the book’s workflow from research ideas to live market execution.
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/stefan-jansen/machine-learning-for-trading/copilot-instructionsgit clone --depth 1 https://github.com/stefan-jansen/machine-learning-for-tradingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/stefan-jansen/machine-learning-for-trading/copilot-instructions)<a href="https://agentmods.dev/instructions/stefan-jansen/machine-learning-for-trading/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/stefan-jansen/machine-learning-for-trading/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00592 | $0.00592 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
machine-learning-for-trading copilot-instructions.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 6d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository conventions for code review
This is the companion code repository for Machine Learning for Trading, 3rd Edition. The conventions below are deliberate and repository-wide. Please do not flag adherence to them as defects, and do apply them when reviewing.
Prose and comment style
- No em dashes. The repository standardizes on the ASCII hyphen (
-) in all prose, markdown, docstrings, figure titles, and printed output. Em dashes (—) are being removed repository-wide; a file that uses a hyphen where a sibling still has an em dash is ahead of the sweep, not a regression. Do not suggest reintroducing em dashes for "consistency" with files that have not been cleaned yet.
Notebooks
- Every notebook is a paired
.py+.ipynbmanaged by jupytext. The.pyis the source of truth; the.ipynbis generated. Edit the.pyand runjupytext --sync; never hand-edit the.ipynb. - A committed
.ipynbis a production re-execution of its paired.py, stamped inmetadata.ml4t_provenance. Cell outputs are real, not illustrative. - Notebook output must carry no machine-specific paths (no
/tmp/..., no home directory, no absolute checkout path). Print repo-root-relative paths instead, e.g.output_path.relative_to(get_case_study_dir("etfs").parents[1]).
Data schema
- The canonical schema is
symbol(entity identifier) +timestamp(all frequencies, daily and intraday). Thecme_futuresdataset usesproductinstead ofsymbol. These are intentional; do not suggest renaming toasset,date,ticker, orpair.
Results and DataFrames
- The sole source of truth for model/backtest/strategy results is
run_log/registry.dbin each case study.results/*.jsonfiles are a deprecated legacy format and must not be treated as ground truth. - Polars-first. DataFrame operations use Polars; pandas appears only at visualization boundaries. Do not suggest converting Polars code to pandas.
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.
- 6d ago First seen · 47 lines · 592 tokens per session scan A b14b85e41bd4
machine-learning-for-trading copilot-instructions.md is an instructions file published in the GitHub repository stefan-jansen/machine-learning-for-trading (20,779 stars, last pushed today), licensed MIT. It adds 592 tokens to every session, about $0.0030 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 2026-08-30.
Other instructions, from other repositories
zenml CLAUDE.md
Claude Code instructions for zenml-io/zenml, covering zenml claude code guidelines, project structure, use zenml docs via mcp, code style & quality standards and commenting policy — explain why, not what.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
polymarket-alpha-bot CLAUDE.md
Instructions for chainstacklabs/polymarket-alpha-bot, covering claude.md, commands, development, pipeline and seed data.
PortfolioOptimisers.jl copilot-instructions.md
Copilot instructions for dcelisgarza/PortfolioOptimisers.jl, covering copilot instructions for portfoliooptimisers.jl, project overview, architecture & key patterns, developer workflows and required before each commit.
scomp_link AGENTS.md
AGENTS.md instructions for GiacomoSaccaggi/scomp_link, covering agents.md — instructions for ai coding agents, what is scomp-link?, when to use scomp-link, cli quick reference (26 commands) and data understanding.