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 analyze-goldgit 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/analyze-gold)<a href="https://agentmods.dev/skills/mahmoud20138/tradecraft/analyze-gold"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/analyze-gold/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/analyze-gold"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/analyze-gold.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 | $0.00065 | $0.01634 |
| Opus 5.5 | $0.00026 | $0.00654 |
| Sonnet 5.5 | $0.00013 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
analyze-gold 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Gold — Combination Command
Pre-configured wrapper around pair-analyze for XAUUSD with gold-specific calibration. Pick this when the user says "analyze gold" or "gold setup" so defaults match how gold actually trades.
Invocation
/tradecraft:analyze-gold [TIMEFRAME] [MODE]
# Examples
/tradecraft:analyze-gold # defaults: H1, standard
/tradecraft:analyze-gold H4 conservative
/tradecraft:analyze-gold M15 scalp
/tradecraft:analyze-gold D1 swing
Arguments are exposed via $ARGUMENTS. Symbol is locked to XAUUSD.
What This Wrapper Does
- Binds symbol =
XAUUSD(also accepts broker variants:XAUUSDm,GOLD,XAU/USD— normalize before dispatch). - Applies gold-specific overrides (see below).
- Delegates to the
pair-analyzepipeline. - Returns the same JSON output contract as
pair-analyze, plus agold_contextblock.
Gold-Specific Calibration
| Aspect | Override vs. generic pair-analyze |
|---|---|
| Pip / point | 0.01 USD per unit — price quoted to 2 decimals |
| Typical spread | 0.15 – 0.40 on ECN; 0.25 – 0.60 on standard |
| Active sessions | London open → US close (08:00 – 21:00 UTC) |
| Dead zone | Asian session outside the Tokyo/London overlap (~06:00 – 09:00 UTC) |
| Volatility reference | H1 ATR(14) typically 3–12 pts; >20 = elevated |
| SL minimum | Max(structure-based, 1.0 × H1 ATR, 2.5 pts) — gold wicks hunt tight stops |
| High-impact drivers | FOMC, NFP, CPI, PPI, DXY moves, real yields, geopolitical risk |
| News gate buffer | 30 min before / 60 min after red-folder USD events |
| Correlation to monitor | DXY (inverse), US10Y real yield (inverse), SPX (weak positive in risk-on) |
Mode Defaults Adjusted for Gold
| Mode | Per-trade risk | Min R:R | Notes |
|---|---|---|---|
| conservative | 0.5% | 3.0 | H4/D1 only; avoid during NY lunch |
| standard | 1.0% | 2.0 | H1/H4; skip the first 15 min after London open |
| aggressive | 1.5% | 1.5 | H1 only; never during CPI/FOMC week |
| scalp | 0.5% | 1.5 | M5/M15; London and NY overlap only |
| swing | 1.0% | 3.0 | H4/D1; align with weekly bias |
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 · 132 lines · 65 tokens per session scan A 655ed257aa81
analyze-gold is a skill published in the GitHub repository mahmoud20138/Tradecraft (17 stars, last pushed 6mo ago), licensed MIT. It adds 65 tokens to every session and 1,634 once invoked, about $0.0003 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.
analyze-gold compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| analyze-goldmahmoud20138/Tradecraft | Skill | 17 | 6mo ago | MIT | A | 65 | Claude Code |
| etf-premiumhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 159 | Claude Code |
| stock-liquidityhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 129 | Claude Code |
| tradingview-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 181 | Claude Code |
| company-valuationhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 155 | Claude Code |
| sepa-strategyhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 186 | Claude Code |
| stock-correlationhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 149 | Claude Code |