What is LLM_trader AGENTS.md?

A repository instruction file that gives coding agents the rules, architecture, and working procedures for an experimental, paper-trading bot. The bot uses market data, news, chart images, and language models to produce buy, sell, or hold decisions.

Following the project's coding standards, testing rules, lifecycle, and governance while working on its multi-agent trading system.

It gives agents one authoritative source of guidance, reducing conflicting instructions and uncertainty about how the project should be changed or run.

How qrak/LLM_trader configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to qrak/LLM_trader. 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/qrak/LLM_trader/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/qrak/LLM_trader

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/qrak/llm_trader/agents-md/github.svg)](https://agentmods.dev/instructions/qrak/llm_trader/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/qrak/llm_trader/agents-md"><img src="https://agentmods.dev/badge/instructions/qrak/llm_trader/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/qrak/llm_trader/agents-md"><img src="https://agentmods.dev/badge/instructions/qrak/llm_trader/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9,206 This file is loaded in full into every session.

When invoked 9,206 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.09206	$0.09206
Opus 5.5	$0.03682	$0.03682
Sonnet 5.5	$0.01841	$0.01841
Haiku 4.5	$0.00921	$0.00921

Measured 4d ago against content hash 840e6b592178, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LLM_trader AGENTS.md scanned grade A with 1 finding 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 4d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Any `eval` / `exec` / `subprocess(shell=True)` / `os.system` / `pickle.loads` / `yaml.load` hit in `src/` is CRITICAL until proven otherwise.

AGENTS.md · 442 lines

How it starts

The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Trader — Master Architecture Blueprint

Repository: https://github.com/qrak/LLM_trader.git Python: 3.13, .venv/, python start.py Execution: with [executor_api] enabled = true decisions are forwarded to a separate executor service (not in this repository); with enabled = false the book is simulated Live Dashboard: https://semanticsignal.qrak.org

0. Instruction Authority

Root AGENTS.md is the single instruction source of truth in this repository across all IDEs, agents, and harnesses.

Root AGENTS.md is canonical for system-wide rules, architecture, coding standards, testing, terminal behavior, and governance.
IDE-specific instruction files are non-authoritative and should not contain policy that is missing from AGENTS.md.
.github/workflows/* defines CI execution behavior, not instruction authority.

1. System Overview

Asyncio-first trading bot: market data, news (RAG) and chart images become structured BUY / SELL / HOLD decisions from an LLM. A central trading loop coordinates data ingestion, technical analysis (Numba indicator kernels), RAG retrieval, risk validation, an outcome-aware brain (vector memory + reflection), and an order-governance chain. Filled orders are executed by a separate service; the bot keeps the decision loop and books what the venue actually did.

DataFetcher ─▶ AnalysisEngine ─▶ ProviderOrchestrator ─▶ UnifiedParser
   (CCXT)       TechCalc+Pattern+Chart+RAG+Brain        (fallback chain)
                                                              │
   BrainContextProvider ◀── vector memory ◀── closed trade     ▼
        (confidence + rules into next prompt)          GuardPipeline ─▶ RiskManager
                                                              │            (SL/TP, size)
                                                              ▼                │
                                                     TradingStrategy ◀─────────┘
                                                     (R:R gate, OrderLifecycle, ExitMonitor)
                                                              │
                                                        executor_api ─▶ venue, verdict journal ─▶ booking

Read the full file on GitHub · 442 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.

4d ago Changed · +46 tokens per session 840e6b592178
6d ago Changed · +1 lines · +37 tokens per session 6d6a093c5d27
8d ago Changed · +15 lines · +910 tokens per session 34737663a04b
10d ago Changed · +38 lines · +1,171 tokens per session 41c2501ea491
11d ago Changed · +7 lines · +463 tokens per session 08e756139e2d
12d ago Changed · +19 lines · +283 tokens per session 012695eb3df1
13d ago Changed · +10 lines · +308 tokens per session a9f48714c2d3
15d ago Changed · +1 lines · +40 tokens per session 6b98f6e58f38
18d ago Changed · -132 lines · -1,167 tokens per session 87ed24d77230
23d ago First seen · 483 lines · 7,115 tokens per session scan A 289f406daadc

Subscribe to this mod's changes

LLM_trader AGENTS.md is an instructions file published in the GitHub repository qrak/LLM_trader (141 stars, last pushed 4d ago), licensed MIT. It adds 9,206 tokens to every session, about $0.0368 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Finance and fintech LLM cryptocurrency market-analysis openrouter sentiment-analysis technical-analysis

LLM_trader AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
LLM_trader AGENTS.mdqrak/LLM_trader	Instructions file	141	4d ago	MIT	A	9,206	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

LLM_trader: Instructions file for Codex