What is 0dte-strategies CLAUDE.md?

A project guide for working with a research repository about same-day S&P 500 options trading. It explains what the repository contains, how it is organized, and which commands reproduce and test its results.

It helps install dependencies, check the environment, reproduce the research outputs, run individual analyses, and execute the project’s tests.

It reduces the time needed to understand the project and prevents agents from guessing how to set up, run, or verify the code.

How vilkovgr/0dte-strategies configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vilkovgr/0dte-strategies. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/vilkovgr/0dte-strategies/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vilkovgr/0dte-strategies

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vilkovgr/0dte-strategies/claude-md.svg)](https://agentmods.dev/instructions/vilkovgr/0dte-strategies/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vilkovgr/0dte-strategies/claude-md"><img src="https://agentmods.dev/badge/instructions/vilkovgr/0dte-strategies/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,201 This file is loaded in full into every session.

When invoked 1,201 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01201	$0.01201
Opus 5	$0.00600	$0.00600
Sonnet 5	$0.00240	$0.00240
Haiku 4.5	$0.00120	$0.00120

Measured 8d ago against content hash 314387fa3abf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

0dte-strategies CLAUDE.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 8d 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.

CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude Project Context

What Is This Repository?

Public replication package for "0DTE Trading Rules: Tail Risk, Implementation, and Tactical Timing" (Vilkov, 2026). Contains analysis code, derived data panels, and AI-optimized documentation for reproducing every exhibit in the paper.

Quick Orientation

Paper topic: Realized payoffs of S&P 500 zero-days-to-expiration (0DTE) options and multi-leg strategies. Tests whether 0DTE offers repeatable carry or is better used as a tactical overlay.
Sample: SPXW options, Sep 2016 – Jan 2026, focusing on 10:00 ET entry held to 16:00 ET close.
Main finding: Unconditional 0DTE is weak after costs and tail risk; conditional OOS rules on selected strategies and baskets achieve SR 1.0–1.3.

How to Run

pip install -r requirements.txt
python tools/doctor.py           # verify setup
python code/run_replication.py   # reproduce all tables + figures
python tests/test_replication.py # verify parity with reference

Key Commands

Task	Command
Reproduce everything	`python code/run_replication.py`
Single table family	`python code/analysis/<script>.py`
Check environment	`python tools/doctor.py`
Run parity tests	`python tests/test_replication.py`
Run tooling tests	`python tests/test_tools.py`
Convert LaTeX to annotated MD	`python tools/latex2md.py paper.tex -o out.md`

Code Structure

All analysis scripts live in code/analysis/ and follow a uniform pattern:

Parse args (optional --project-root, --data-dir)
Load data from data/ via _paths.py helpers
Compute statistics
Write LaTeX tables to output/tables/ or PDF figures to output/figures/

Central config: code/config.py (RepoConfig dataclass with path properties).

Data Files

All in data/ directory (Git LFS tracked):

data_opt.parquet — interpolated option panel (mid, spread, Greeks, payoff, PNL)
data_structures.parquet — strategy-level panel (7 types, flow/liquidity features)
vix.parquet — VIX and intraday implied/realized moments
slopes.parquet — Volatility surface slopes (point-in-time)
future_moments_SPX.parquet — forward realized moments for SPX (PIT intraday)
future_moments_VIX.parquet — forward realized moments for VIX (PIT intraday)
ALL_eod.csv — end-of-day reference prices

Read the full file on GitHub · 99 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.

8d ago First seen · 99 lines · 1,201 tokens per session scan A 314387fa3abf

Subscribe to this mod's changes

0dte-strategies CLAUDE.md is an instructions file published in the GitHub repository vilkovgr/0dte-strategies (54 stars, last pushed 12d ago), licensed MIT. It adds 1,201 tokens to every session, about $0.0060 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.

Finance and fintech

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

0dte-strategies: Instructions file for Claude Code