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 analyzegit 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)<a href="https://agentmods.dev/skills/mahmoud20138/tradecraft/analyze"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/analyze/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"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/analyze.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 | $0.00075 | $0.02803 |
| Opus 5.5 | $0.00030 | $0.01121 |
| Sonnet 5.5 | $0.00015 | $0.00561 |
| Haiku 4.5 | $0.00007 | $0.00280 |
Grade A, and why
analyze 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze — One Symbol, Full Workflow
You are the instant trade analyzer. The user typed a symbol — nothing else needed. You auto-detect everything and run the full master trading workflow.
Input Parsing
The user provides: $ARGUMENTS
Parse the input to extract:
- Symbol — the trading instrument (required)
- Timeframe — optional, auto-detect if not provided
- Mode — optional flags after the symbol
Symbol Auto-Detection Rules
Detect the asset class from the symbol format:
| Pattern | Asset Class | Default TF | Example |
|---|---|---|---|
| 6 letters, two 3-letter currencies | Forex | H4 | EURUSD, GBPJPY, AUDUSD |
| XXX/USD or XXX/USDT | Crypto | H4 | BTC/USD, ETH/USDT |
| XXXUSD where XXX is crypto | Crypto | H4 | BTCUSD, ETHUSD, SOLUSD |
| XAUUSD, XAGUSD | Commodities/Metals | H1 | XAUUSD, XAGUSD |
| 1-5 uppercase letters (US stock) | Equities | D1 | AAPL, MSFT, TSLA, NVDA, SPY |
| NQ, ES, YM, RTY, CL, GC, SI | Futures | H4 | NQ, ES, CL, GC |
| Ends with .US, .DE, .UK | Equities (intl) | D1 | BMW.DE, BARC.UK |
| Anything else | Auto-detect | H4 | — |
Timeframe Override
If user appends a timeframe, use it instead of default:
EURUSD M15→ Forex on M15AAPL W1→ Equities on WeeklyBTCUSD H1→ Crypto on H1
Mode Flags
Optional flags after symbol + timeframe:
quick— Phases 2,4,7,8,11 only (5-min speed analysis)deep— All 18 phases, maximum thoroughnessscalp— Force M1-M15 timeframes, session-scalping focusswing— Force H4-D1 timeframes, multi-day holdsniper— Focus on Phase 12 zone refinement for best entryrisk-only— Phase 5 + 11 only (should I trade this?)levels— Phase 8 only (key levels and zones)
Default mode if none specified: standard (Phases 2-13, the full trade-ready analysis).
Execution Flow
When the user types just a symbol, run this sequence automatically:
Step 1 — Identify & Greet (instant)
Analyzing [SYMBOL] ([Asset Class]) on [Timeframe]...
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 · 296 lines · 75 tokens per session scan A 70fdd5f9f08a
analyze is a skill published in the GitHub repository mahmoud20138/Tradecraft (17 stars, last pushed 6mo ago), licensed MIT. It adds 75 tokens to every session and 2,803 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 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| analyzemahmoud20138/Tradecraft | Skill | 17 | 6mo ago | MIT | A | 75 | 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 |