trade

trade is a skill for Claude Code, Codex from Degenapetrader/EVClaw. It costs 47 tokens per session (794 once invoked), scanned A, original, MIT.

A manual trading-plan workflow for requested cryptocurrency symbols. It produces long or short plans with two possible entry methods and leaves the decision to execute the trade to the user.

In plain words
What is it for?
Creating and saving plans for one or more symbols, including fast entries and resting limit orders that can be cancelled automatically after a set time.
Why use it?
It turns a trading request into a structured plan before any order is placed, making the proposed entry, stop-loss, and take-profit levels explicit.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/degenapetrader/evclaw/trade
Any agent
npx skills add Degenapetrader/EVClaw --skill trade
Clone the repo
git clone --depth 1 https://github.com/Degenapetrader/EVClaw

Made for: Claude Code, Codex.

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 trade

README.md
[![agentmods](https://agentmods.dev/badge/skills/degenapetrader/evclaw/trade.svg)](https://agentmods.dev/skills/degenapetrader/evclaw/trade)
Your own site
<a href="https://agentmods.dev/skills/degenapetrader/evclaw/trade"><img src="https://agentmods.dev/badge/skills/degenapetrader/evclaw/trade.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.00794
Opus 5 $0.00023 $0.00397
Sonnet 5 $0.00009 $0.00159
Haiku 4.5 $0.00005 $0.00079

Measured 5d ago against content hash ec044c8bd7e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/allocate_context.py, scripts/execute_plan.py, scripts/finalize_plan.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

openclaw_skills/trade/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/trade (advisor-mode)

Goal: when the user types /trade ETH, generate a compact but informative trade plan immediately (direction + confidence + sizing + SL/TP + key context) and always present two execution options:

  • FAST = chase_limit entry
  • RESTING = SR-anchored resting limit (pending SR limit) with auto-cancel (default 60m)

This command is manual/advisor: the user decides whether to execute.

Workflow (must follow)

This uses an LLM gate (same idea as EVClaw entry gate) but restricted to the symbol(s) the user requested.

  1. Generate + store plan(s) via the trade gate:
EVCLAW_ROOT="${EVCLAW_ROOT:-$HOME/.openclaw/skills/EVClaw}" \
python3 "$EVCLAW_ROOT/openclaw_skills/trade/scripts/generate_plans.py" <SYMBOL...> [--direction long|short] [--size-usd 5000]

Examples:

  • Single symbol: EVCLAW_ROOT="${EVCLAW_ROOT:-$HOME/.openclaw/skills/EVClaw}" python3 "$EVCLAW_ROOT/openclaw_skills/trade/scripts/generate_plans.py" ETH
  • Multi-symbol: EVCLAW_ROOT="${EVCLAW_ROOT:-$HOME/.openclaw/skills/EVClaw}" python3 "$EVCLAW_ROOT/openclaw_skills/trade/scripts/generate_plans.py" ETH BTC

This script will:

  • allocate monotonic ids (e.g. ETH-06)
  • load latest evclaw_candidates_*.json
  • filter candidates to requested symbols
  • call the OpenClaw manual trade gate agent (default id: default)
  • write /tmp/manual_trade_plan_<ID>.json
  • store plan_json into manual_trade_plans (status=READY)
  1. Reply to the user with a short plan summary for each symbol and the execute commands (ONE-CLICK COPY):
  • Put the exact command on its own line (prefer a code block), e.g. /execute chase
  • And /execute limit

Output rules:

  • Confidence displayed as percent (0–100) mapped from our conviction model.
  • RESTING must include the explicit cancel timing string ("Auto-cancels ~60m after placing (around ... UTC)").
  • Do NOT display raw pipeline score (misleading).
  • Do NOT display funding rate or 24h price change.
  • Direction MUST respect the dossier: if dossier vetoes a direction (e.g. "hard-veto longs"), flip direction or reject the trade with explanation.

Read the full file on GitHub · 59 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 59 lines · 47 tokens per session scan A ec044c8bd7e2

Subscribe to this mod's changes

trade is a skill published in the GitHub repository Degenapetrader/EVClaw (40 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 794 once invoked, about $0.0002 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.