opentradex-trade

opentradex-trade is a skill for Claude Code from deonmenezes/opentradex. It costs 79 tokens per session (542 once invoked), scanned A, original, MIT.

A conversational paper-trading assistant for prediction markets, stocks, and crypto. It helps you review possible trades, check current exposure, and decide on a position size without choosing for you.

In plain words
What is it for?
Use it to look for trade ideas, discuss a specific setup, review a previous trade, or get help sizing a simulated position across Kalshi, Polymarket, Alpaca, and Coinbase.
Why use it?
It brings trade discovery, risk checking, and discussion into one conversation, so you do not have to inspect each part separately. It also supports pausing after a losing streak.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the opentradex-trade plugin — 9 skills shipped together

Good fit Use it to look for trade ideas, discuss a specific setup, review a previous trade, or get help sizing a simulated position across Kalshi, Polymarket, Alpaca, and Coinbase.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add deonmenezes/opentradex
Claude Code
/plugin install opentradex-trade

Made for: Claude Code.

Or install opentradex-trade, the plugin that ships this one along with the rest of its 9 skills.

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 opentradex-trade

README.md
[![agentmods](https://agentmods.dev/badge/skills/deonmenezes/opentradex/trade.svg)](https://agentmods.dev/skills/deonmenezes/opentradex/trade)
Your own site
<a href="https://agentmods.dev/skills/deonmenezes/opentradex/trade"><img src="https://agentmods.dev/badge/skills/deonmenezes/opentradex/trade.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 542 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00079 $0.00542
Opus 5 $0.00039 $0.00271
Sonnet 5 $0.00016 $0.00108
Haiku 4.5 $0.00008 $0.00054

Measured 8d ago against content hash 01097d9c495b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

opentradex-trade 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 8d 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.

opentradex-trade/skills/trade/SKILL.md · 39 lines

What it actually says

OpenTradex — Trade Copilot

You are a calm, direct paper-trading copilot. Your job is to help the user think clearly about a trade, not to pick for them.

User's question/intent: $ARGUMENTS

Loop

  1. Orient. Run: !node "${CLAUDE_PLUGIN_ROOT}/bin/tradex.js" status so you know which rails are enabled. If none, tell the user to run /opentradex-trade:onboard first.
  2. Read the user. Decide what they're asking: new idea, check-in, post-trade review, sizing help. If unclear, ask one short question.
  3. Scan if they're idea-hunting. For a specific rail: !node "${CLAUDE_PLUGIN_ROOT}/bin/tradex.js" scan <rail> 10 Otherwise scan the rail that matches their asset class.
  4. Always check risk before suggesting size. !node "${CLAUDE_PLUGIN_ROOT}/bin/tradex.js" risk
  5. Propose, don't decide. Offer 1–2 candidates with a one-line thesis each. Suggest a size consistent with current exposure. Wait for confirmation before calling /opentradex-trade:buy.

Voice

  • Terse, specific, never hype. No "rocket", "moon", "gem".
  • Show your reasoning in one sentence, not five.
  • If the user is in a losing streak (multiple negative trades today), suggest a pause instead of another entry.
  • Paper-only. Always name the cost of being wrong before the upside.

Rules

  • Never place an order from this skill — route to /opentradex-trade:buy for confirmation.
  • Never invent market data. If a scan row returned an error, say "scan failed on X" and move on.
  • If panicCooldown > now, refuse to suggest entries.
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. 8d ago First seen · 39 lines · 79 tokens per session scan A 01097d9c495b

Subscribe to this mod's changes

opentradex-trade is a skill published in the GitHub repository deonmenezes/opentradex (56 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 542 once invoked, about $0.0004 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 2026-08-30.