Autoresearch_MRsequence: Instructions file for Codex

AGENTS.md

Autoresearch_MRsequence AGENTS.md is an instructions file for Codex, OpenCode from zjgao-spin/Autoresearch_MRsequence. It costs 2,279 tokens per session, scanned A, original, MIT.

Instructions for an autonomous agent that optimizes a two-dimensional Turbo Spin Echo MRI pulse sequence using physics simulation.

In plain words
What is it for?
The agent edits experiment parameters in optimize.py, runs the MRI simulation, reads error scores and result files, and decides which parameter settings to keep.
Why use it?
They constrain the experiment to a fixed optimization workflow, making results comparable while preventing changes to unrelated files or the evaluation process.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is zjgao-spin/Autoresearch_MRsequence's own configuration. It tells Codex and OpenCode how to work on Autoresearch_MRsequence itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Autoresearch_MRsequence configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zjgao-spin/Autoresearch_MRsequence. 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/zjgao-spin/Autoresearch_MRsequence/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/zjgao-spin/Autoresearch_MRsequence

Made for: Codex, OpenCode.

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.

agentmods badge for Autoresearch_MRsequence AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zjgao-spin/autoresearch_mrsequence/agents-md.svg)](https://agentmods.dev/instructions/zjgao-spin/autoresearch_mrsequence/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zjgao-spin/autoresearch_mrsequence/agents-md"><img src="https://agentmods.dev/badge/instructions/zjgao-spin/autoresearch_mrsequence/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,279 This file is loaded in full into every session.
When invoked 2,279 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02279 $0.02279
Opus 5 $0.01140 $0.01140
Sonnet 5 $0.00456 $0.00456
Haiku 4.5 $0.00228 $0.00228

Measured 7d ago against content hash c17ed53f50d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Autoresearch_MRsequence 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 7d 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 · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — MRI Sequence Optimization Agent

You are an autonomous MRI pulse sequence designer. Your task is to optimize a 2D Turbo Spin Echo (TSE) sequence given a single natural-language instruction.

Background

This project transplants the karpathy/autoresearch autonomous LLM-agent paradigm from neural network training to MR physics simulation. You replace train.py with a PyPulseq sequence builder and prepare.py with MRzero Bloch-equation GPU simulation.

Built on: karpathy/autoresearch, MRzero-Core, PyPulseq 1.4.2, Agent4MR (arXiv:2604.13282) (Zaiss et al., 2026)

What You Will Do

You edit ONE file: autoresearch_mrsequence/optimize.py. This is equivalent to karpathy's train.py — it is the only file you modify. You never create new .py files.

Your workflow:

  1. Read autoresearch_mrsequence/optimize.py — it contains a loop that calls the fixed evaluate() oracle
  2. Edit the EXPERIMENTS section: fill in parameter choices for each experiment
  3. Run python -m autoresearch_mrsequence.optimize
  4. Read the output (MAE, scores, KEEP events)
  5. Analyze results: check output/results.tsv and output/live_panel.png
    • Which parameter directions lowered MAE or SAR the most?
    • Does centric encoding consistently outperform linear?
    • Which turbo factor gives the best tradeoff?
  6. Immediately plan a refinement batch of ~5 experiments: perturb the best-found parameters by small amounts
  7. Edit the experiments list, re-run — do NOT ask the user whether to continue
  8. If a batch produces zero KEEP events, you have converged — stop and report the final result

You are fully autonomous. Do not wait for permission. After each batch, analyze → plan → edit → run → repeat. Only stop and summarize when convergence is reached.

State is persistent. output/state.json remembers your best params and experiment count across runs. Each new batch continues from where the last one left off — no need to re-run the baseline.

Read the full file on GitHub · 179 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. 7d ago First seen · 179 lines · 2,279 tokens per session scan A c17ed53f50d9

Subscribe to this mod's changes

Autoresearch_MRsequence AGENTS.md is an instructions file published in the GitHub repository zjgao-spin/Autoresearch_MRsequence (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,279 tokens to every session, about $0.0114 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

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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens