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 skills add mahmoud20138/Tradecraft --skill forex-tradinggit clone --depth 1 https://github.com/mahmoud20138/TradecraftWrote 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/mahmoud20138/tradecraft/forex-trading)<a href="https://agentmods.dev/skills/mahmoud20138/tradecraft/forex-trading"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/forex-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/mahmoud20138/tradecraft/forex-trading"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/forex-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 | $0.00094 | $0.01138 |
| Opus 5 | $0.00047 | $0.00569 |
| Sonnet 5 | $0.00019 | $0.00228 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
forex-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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Forex Trading | Domain: trading | Category: asset-class | Level: beginner Tags:
trading,asset-class,forex,pairs,pips,session-hours
Forex Trading — Asset Class Reference
Major Pairs & Characteristics
| Pair | Nickname | Spread (avg) | Best Session | Volatility |
|---|---|---|---|---|
| EURUSD | Fiber | 0.1–0.6 pips | London/NY overlap | Medium |
| GBPUSD | Cable | 0.3–1.0 pips | London open | High |
| USDJPY | Ninja | 0.2–0.7 pips | Tokyo/London | Medium |
| AUDUSD | Aussie | 0.2–0.8 pips | Sydney/London | Medium |
| USDCAD | Loonie | 0.3–1.0 pips | NY session | Medium |
| USDCHF | Swissie | 0.3–1.0 pips | London/NY | Medium |
Pip Value Calculator
def pip_value(pair: str, lot_size: float, account_currency: str = "USD") -> float:
"""Standard pip values for 1 standard lot (100,000 units)."""
pip_sizes = {
"EURUSD": 0.0001, "GBPUSD": 0.0001, "AUDUSD": 0.0001,
"USDCAD": 0.0001, "USDCHF": 0.0001, "USDJPY": 0.01,
"XAUUSD": 0.01, "XAGUSD": 0.001,
}
pip = pip_sizes.get(pair.upper(), 0.0001)
# For USD-quoted pairs: pip_value = pip * lot_size * contract_size
return pip * lot_size * 100_000
Session Hours & Liquidity Windows
| Session | UTC Open | UTC Close | Key Pairs |
|---|---|---|---|
| Sydney | 22:00 | 07:00 | AUDUSD, NZDUSD |
| Tokyo | 00:00 | 09:00 | USDJPY, AUDJPY |
| London | 07:00 | 16:00 | GBPUSD, EURUSD |
| New York | 12:00 | 21:00 | All majors |
| London/NY Overlap | 12:00 | 16:00 | Highest volume — best for scalping |
Carry Trade Framework
def carry_trade_screen(pairs: list, rates: dict) -> list:
"""Find best carry pairs: borrow low-rate currency, invest high-rate."""
results = []
for pair in pairs:
base, quote = pair[:3], pair[3:]
carry = rates.get(base, 0) - rates.get(quote, 0)
results.append({"pair": pair, "carry_pct": round(carry, 2),
"direction": "LONG" if carry > 0 else "SHORT"})
return sorted(results, key=lambda x: abs(x["carry_pct"]), reverse=True)
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 · 101 lines · 94 tokens per session scan A 61dfc96772a2
forex-trading is a skill published in the GitHub repository mahmoud20138/Tradecraft (15 stars, last pushed 4mo ago), licensed MIT. It adds 94 tokens to every session and 1,138 once invoked, about $0.0005 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.
Other skills, from other repositories
etf-analysis
A framework for comparing exchange-traded funds (ETFs), which are funds bought and sold on a stock exchange and usually track an index, industry, asset, or strategy. It covers fees, how closely an ETF follows its target, trading activity, and portfolio use.
options-payoff
Option P&L analysis methodology: payoff diagrams, breakeven calculation, multi-leg strategy visualization, and Greeks-based scenario analysis.
asset-allocation
Asset allocation theory and optimizer usage — MPT / Black-Litterman / risk budgeting / all-weather strategy, including guides for 5 optimizers and rebalancing rules.
fund-analysis
A framework for comparing mutual funds, private funds, and exchange-traded funds using returns, risk, investment style, and manager performance. It also examines whether a fund's style changes over time.
hedging-strategy
Hedging strategy design (beta hedge / option protection / tail risk / cross-asset hedging), including hedge-ratio calculation and cost evaluation.
convertible-bond
An analysis framework for Chinese A-share convertible bonds, which are bonds that can usually be exchanged for shares of the issuing company. It values the bond repayment component, the conversion option, and the bond's trading terms.