nexustrade-ts: Instructions file for Codex

AGENTS.md

nexustrade-ts AGENTS.md is an instructions file for Codex, OpenCode from austin-starks/nexustrade-ts. It costs 4,066 tokens per session, scanned A, original, MIT.

Instructions for using the NexusTrade TypeScript SDK to write trading strategies. The SDK provides a typed client and generated building blocks for assembling portfolios, submitting jobs, and reading results.

In plain words
What is it for?
Use it when creating NexusTrade strategies, assets, orders, or indicator-based portfolios in Node.js. It also covers submitting strategy jobs, waiting for completion, and reading their results.
Why use it?
It helps agents produce strategy requests in the structure expected by the NexusTrade engine. It also explains how to use API keys safely through environment variables rather than putting them in source files.

Instructions file for CodexOpenCode

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

This is austin-starks/nexustrade-ts's own configuration. It tells Codex and OpenCode how to work on nexustrade-ts 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 nexustrade-ts configures →

Reuse

Borrowing it

Nothing to install: this file belongs to austin-starks/nexustrade-ts. 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/austin-starks/nexustrade-ts/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/austin-starks/nexustrade-ts

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 nexustrade-ts AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/austin-starks/nexustrade-ts/agents-md/github.svg)](https://agentmods.dev/instructions/austin-starks/nexustrade-ts/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/austin-starks/nexustrade-ts/agents-md"><img src="https://agentmods.dev/badge/instructions/austin-starks/nexustrade-ts/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nexustrade-ts AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/austin-starks/nexustrade-ts/agents-md"><img src="https://agentmods.dev/badge/instructions/austin-starks/nexustrade-ts/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,066 This file is loaded in full into every session.
When invoked 4,066 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 $0.04066 $0.04066
Opus 5.5 $0.01626 $0.01626
Sonnet 5.5 $0.00813 $0.00813
Haiku 4.5 $0.00407 $0.00407

Measured 26d ago against content hash 3c3ab90d71fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nexustrade-ts 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 26d 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 · 423 lines

How it starts

The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — NexusTrade TypeScript SDK

Instructions for coding agents (Claude Code, Cursor, Codex, and friends) writing NexusTrade strategies with this package. Humans: README.md is the friendlier read.

What this package is

A typed client plus ~170 generated builders for authoring trading strategies. The builders are generated from the engine's indicator specification. They describe draft payloads; the API still validates complete portfolios and their conditions. A builder's existence does not guarantee support for every trading method. Read the option selection and execution limits before claiming exact option timing, expiration selection, or rolling behavior.

author a portfolio  →  submit a job  →  poll until terminal  →  read result

Setup

npm install nexustrade
export NEXUSTRADE_API_KEY=sk-...
export NEXUSTRADE_API_BASE_URL=https://nexustrade.io/api/v1
import { NexusTradeClient } from "nexustrade";
const client = new NexusTradeClient();   // reads the environment

Keys come from https://nexustrade.io/developers. Never hardcode one into a file you write; read it from the environment. Node 18+.

Rules that matter

1. Use the builders. Never hand-write the JSON.

// Right — validated shape, correct wire names
nt.buy(nt.stockAsset("SPY"), 100);

// Wrong — silently diverges from the engine's schema
{ type: "Buy", targetAsset: { symbol: "SPY" }, amount: 100 };

The client accepts both a builder result and a plain object, so a wrong literal will typecheck. Prefer the builder.

2. Comparisons are functions, not operators.

TypeScript cannot overload >, so indicator comparisons go through helpers. This is the single most common mistake in this SDK.

// Right
nt.filter(nt.gt(nt.Price(nt.CANDIDATE), nt.SMA(nt.CANDIDATE, 200)));

// Wrong — compares object references, always nonsense
nt.filter(nt.Price(nt.CANDIDATE) > nt.SMA(nt.CANDIDATE, 200));

Read the full file on GitHub · 423 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. 26d ago Changed · +2 lines · +41 tokens per session 3c3ab90d71fa
  2. 1mo ago Changed · +2 lines · +79 tokens per session f14215995694
  3. 1mo ago Changed · +4 tokens per session 491e242a04b0
  4. 1mo ago Changed · +66 lines · +637 tokens per session a92f87c24c3d
  5. 2mo ago First seen · 353 lines · 3,305 tokens per session scan A 5938df555ea4

Subscribe to this mod's changes

nexustrade-ts AGENTS.md is an instructions file published in the GitHub repository austin-starks/nexustrade-ts (10 stars, last pushed 7d ago), licensed MIT. It adds 4,066 tokens to every session, about $0.0163 per session on Opus 5.5. 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

nexustrade-ts AGENTS.md compared with instructions from other repositories

nexustrade-ts AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nexustrade-ts AGENTS.mdaustin-starks/nexustrade-tsInstructions file107d agoMITA4,066Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode