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/armandcismaru/deeptraderx/agents-mdgit clone --depth 1 https://github.com/armandcismaru/DeepTraderXWrote 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/armandcismaru/deeptraderx/agents-md)<a href="https://agentmods.dev/instructions/armandcismaru/deeptraderx/agents-md"><img src="https://agentmods.dev/badge/instructions/armandcismaru/deeptraderx/agents-md.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 | $0.03147 | $0.03147 |
| Opus 5 | $0.01573 | $0.01573 |
| Sonnet 5 | $0.00629 | $0.00629 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
DeepTraderX 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.
2. **`os.system()` with f-string interpolation.** How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guidance for AI agents working on DeepTraderX
This file orients coding agents (and humans) working in this repository. It
covers what the project is, how to run and verify it, the conventions to follow,
and a catalogue of known bugs, latent defects, and security concerns found
by scanning the codebase. Detailed end-user/architecture documentation lives in
docs/.
⚠️
docs/is published publicly via GitHub Pages (.github/workflows/pages.yml). Keep security findings and internal notes in this file andCLAUDE.md(repo root, not published) — never indocs/.
1. What this project is
DeepTraderX (DTX, trader code DTR) is an LSTM-based automated trading agent
that competes inside TBSE — the Threaded Bristol Stock Exchange, a Python
multi-threaded simulation of a continuous-double-auction limit-order-book
market. It is academic research code (an MEng dissertation + ICAART 2024 paper),
not a production trading system. There is no live money, no broker, no network
listener; it is a self-contained Monte-Carlo market simulator.
The codebase is largely a faithful fork of Dave Cliff's BSE / Michael Rollins's
TBSE, with the DeepTrader agent and an offline ML training pipeline added.
2. How to run & verify
# from repo root
python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cd deep_trader_tbse # IMPORTANT: run from here
python3 tbse.py # config-driven run
python3 tbse.py 0 0 0 5 0 0 5 # 5 AA + 5 DTR per side
python3 tbse.py markets.csv # batch run (prints "Done Now" when finished)
- Always run from
deep_trader_tbse/. Imports (import src.config) and the model path (./src/deep_trader/Models/...) are CWD-relative. - The CSV mode prints
Done Nowon success — that string is whatsimulation-check.ymlgreps for. Don't remove it. - Lint/format before committing:
pylint(config.pylintrc, max line 120) andblack../checks.shruns both over every*.py.
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 First seen · 220 lines · 3,147 tokens per session scan A 05d5cfd2ec71
DeepTraderX AGENTS.md is an instructions file published in the GitHub repository armandcismaru/DeepTraderX (21 stars, last pushed 17d ago), licensed MIT. It adds 3,147 tokens to every session, about $0.0157 per session on Opus 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.
Other instructions, from other repositories
albucore AGENTS.md
Instructions for albumentations-team/albucore, covering codex ai development guidelines for albucore, project overview, core documentation, repo-local codex skills and development principles.
zero-to-ai snyk_rules.instructions.md
Snyk Security At Inception.
DeepSpeed AGENTS.md
AGENTS.md instructions for deepspeedai/DeepSpeed, covering deepspeed project rules, commit & ci requirements, code change discipline, tool caveats and edit tool auto-formatter.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
ai CLAUDE.md
Claude Code instructions for vercel/ai, a project described as: The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents.
Prompt-Engineering-Guide CLAUDE.md
Instructions for dair-ai/Prompt-Engineering-Guide, covering prompt engineering guide, project overview, project learnings, notes & content and git workflow.