Borrowing it
Nothing to install: this file belongs to deonmenezes/opentradex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/deonmenezes/opentradex/main/AGENTS.mdgit clone --depth 1 https://github.com/deonmenezes/opentradexWrote 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/deonmenezes/opentradex/agents-md)<a href="https://agentmods.dev/instructions/deonmenezes/opentradex/agents-md"><img src="https://agentmods.dev/badge/instructions/deonmenezes/opentradex/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.
<a href="https://agentmods.dev/instructions/deonmenezes/opentradex/agents-md"><img src="https://agentmods.dev/badge/instructions/deonmenezes/opentradex/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00930 | $0.00930 |
| Opus 5.5 | $0.00372 | $0.00372 |
| Sonnet 5.5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
opentradex 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenTradex
An open-source AI trading cockpit that connects to prediction markets, equities, and crypto through a single harness. Paper-first by default (live trading is gated behind a 24h lock). Ships as an npm CLI, web dashboard, Electron desktop app, and mobile (iOS SwiftUI + Expo).
Tech Stack
- Language: TypeScript (compiled to
dist/) - Runtime: Node.js >= 18
- AI: Anthropic SDK (
@anthropic-ai/sdk) - Bundler/build: TypeScript compiler (
tsc) - Workspaces: npm workspaces (
packages/dashboard,packages/desktop,packages/ios,packages/mobile) - Web dashboard: React + Tailwind (in
packages/dashboard) - Desktop: Electron 31 (in
packages/desktop) - Testing: Node.js built-in test runner (
tsx --test)
Setup
npm install
# Build the TypeScript source
npm run build
# (Optional) Build all packages including dashboard
npm run build:all
Build / Run / Test
# Build core TypeScript
npm run build
# Build everything (core + dashboard)
npm run build:all
# Build desktop app (current platform)
npm run build:desktop
# Watch mode (TypeScript only)
npm run dev
# Start web dashboard (build first, then serve)
npm run ui
# Start desktop app (dev mode)
npm run desktop
# Start dashboard in dev mode
npm run dev:dashboard
# Run CLI gateway
npm start
# or: npm run gateway
# Onboarding wizard
npm run onboard
# Run tests
npm test
# Live/integration tests (requires real exchange credentials)
npm run test:live
# Clean all build artifacts
npm run clean
Project Structure
src/
index.ts # Library entry point
bin/cli.js # CLI entry point (opentradex command)
gateway/ # Gateway core logic + tests
agent/ # AI agent strategies
markets/ # Market connector implementations
scraper/ # Exchange scrapers (incl. live tests)
ai/ # AI/LLM integration
mcp/ # MCP tool definitions
config.ts # Configuration loading
risk.ts # Risk management
onboard.ts # Onboarding wizard
types.ts # Shared TypeScript types
x402/ # x402 payment protocol integration
packages/
dashboard/ # React web dashboard
desktop/ # Electron desktop app
ios/ # iOS SwiftUI app
mobile/ # Expo mobile app
landing/ # Marketing landing page
claude-plugin/ # Claude Code plugin
ralph/ # Ralph agent config
tasks/ # Task definitions
docs/ # Documentation and dashboard preview
tsconfig.json # TypeScript config
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.
- 2mo ago First seen · 119 lines · 930 tokens per session scan A 9c84dd30776a
opentradex AGENTS.md is an instructions file published in the GitHub repository deonmenezes/opentradex (57 stars, last pushed 4mo ago), licensed MIT. It adds 930 tokens to every session, about $0.0037 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 2026-08-30.
opentradex AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| opentradex AGENTS.mddeonmenezes/opentradex | Instructions file | 57 | 4mo ago | MIT | A | 930 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |