Borrowing it
Nothing to install: this file belongs to vincentwongso/mt5-trading-mcp. 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/vincentwongso/mt5-trading-mcp/main/.claude/skills/mt5-trading/SKILL.mdgit clone --depth 1 https://github.com/vincentwongso/mt5-trading-mcpWrote 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/skills/vincentwongso/mt5-trading-mcp/mt5-trading)<a href="https://agentmods.dev/skills/vincentwongso/mt5-trading-mcp/mt5-trading"><img src="https://agentmods.dev/badge/skills/vincentwongso/mt5-trading-mcp/mt5-trading/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/skills/vincentwongso/mt5-trading-mcp/mt5-trading"><img src="https://agentmods.dev/badge/skills/vincentwongso/mt5-trading-mcp/mt5-trading.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 | $0.00152 | $0.02757 |
| Opus 5 | $0.00076 | $0.01378 |
| Sonnet 5 | $0.00030 | $0.00551 |
| Haiku 4.5 | $0.00015 | $0.00276 |
Grade A, and why
mt5-trading 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 11d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trading on MetaTrader 5 - mutating tools
This skill covers the four mutating tools the mt5-mcp server exposes. Every successful call here is a real broker action. Even on a demo account, the trade reaches the broker's MT5 server and is irreversible from the agent's side - the only way to undo a wrong order is another order. Treat the consent flow described below as the line that separates "I told the user what I'm about to do" from "I just did something the user didn't sign off on".
Tool catalogue
place_order(symbol, side, type, volume, price?, stop_limit_price?, sl?, tp?, deviation=10, comment?, idempotency_key?, approval_confirmed=false, approval_request_id?) - open a new market or pending order. side is "buy" or "sell". type is "market", "limit", "stop", or "stop_limit". volume is in lots, as a string (e.g. "0.10").
modify_order(ticket, sl?, tp?, price?, expiration?, idempotency_key?, approval_confirmed=false, approval_request_id?) - adjust a position's SL/TP (positions only), or a pending order's price / expiration / SL / TP. When the consent gate is armed (auto_approve_notional > 0), widening or removing an existing SL/TP on a position requires approval and tightening auto-approves; with the gate off (the default) every modify auto-executes. Pass expiration only for pending orders, as ISO 8601 UTC.
cancel_order(ticket, idempotency_key?) - remove a pending order. Never gates for approval (cancelling reduces exposure).
close_position(ticket, volume?, idempotency_key?, approval_confirmed=false, approval_request_id?) - close a position in full (omit volume) or part (pass a smaller string volume).
All mutating tools return a result envelope on success: {retcode, deal, order, volume, price, comment, request_id?, request_echo}. Surface deal and price to the user - that's the executed fill.
The two-call approval flow
For place_order, modify_order (when widening), and close_position, the policy engine compares the trade's notional value against policy.auto_approve_notional. This gate is opt-in and OFF by default: it defaults to 0, so out of the box every mutating call auto-executes with no approval step. The operator arms it by setting auto_approve_notional > 0. When the gate is armed, an order whose notional is at or above the threshold returns an ApprovalPreview envelope on the first call instead of executing:
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.
- 11d ago First seen · 120 lines · 152 tokens per session scan A c8258d796056
mt5-trading is a skill published in the GitHub repository vincentwongso/mt5-trading-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 2,757 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
vc-industry-research
Generate professional primary market / venture capital industry research reports, including sector deep-dives, investment memos, and market analysis. Produces detailed PDF reports covering TMT, consumer, healthcare, and industrials. Triggered by requests to analyze an industry, create a market report, write a sector…
trade-memory
Compliance-grade decision audit trail for AI trading agents. Records every trading decision with full context (conditions, filters, indicators, risk state), SHA-256 tamper detection, and structured export for MiFID II / EU AI Act readiness. Works alongside Binance Spot, Futures, and Web3 skills — they execute trades…
tradememory-bridge
Bridge between Binance trading events and TradeMemory Protocol. Automatically journals trades, recalls similar past setups, detects behavioral biases, and provides outcome-weighted recall for AI trading agents. Use this skill after executing Binance spot trades to build persistent memory.
evolution-engine
Domain knowledge for the Evolution Engine — LLM-powered autonomous strategy discovery from raw OHLCV data. Covers the generate-backtest-select-evolve loop, vectorized backtesting, out-of-sample validation, and strategy graduation. Use when discovering trading patterns, running backtests, evolving strategies, or…
risk-management
Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on "risk", "drawdown", "tilt"…
trading-memory
Domain knowledge for AI trading memory — Outcome-Weighted Memory (OWM) architecture, 5 memory types, recall scoring, and behavioral analysis. Use when recording trades, recalling similar contexts, analyzing performance, or checking behavioral drift. Triggers on "record trade", "remember trade", "recall", "similar…