mcp-trading-agent: Instructions file for Claude Code

CLAUDE.md

mcp-trading-agent CLAUDE.md is an instructions file for Claude Code from jakemo007/mcp-trading-agent. It costs 7,331 tokens per session, scanned A, original, MIT.

Project instructions for an AI trading analyst connected to 22 tools for market data, news, reports, knowledge storage, and simulated trading. It uses Inner Circle Trader and Smart Money Concepts, which are technical approaches to analysing price movements and liquidity.

In plain words
What is it for?
Analysing markets, combining news with price-structure analysis, managing research reports, running paper-trading simulations, and recording backtesting lessons without giving financial advice.
Why use it?
It defines how the agent should detect trading requests, gather information, analyse each ticker, and retain lessons from backtests—historical tests of trading rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is jakemo007/mcp-trading-agent's own configuration. It tells Claude Code how to work on mcp-trading-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-trading-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jakemo007/mcp-trading-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jakemo007/mcp-trading-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jakemo007/mcp-trading-agent

Made for: Claude Code.

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 mcp-trading-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jakemo007/mcp-trading-agent/claude-md/github.svg)](https://agentmods.dev/instructions/jakemo007/mcp-trading-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jakemo007/mcp-trading-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/jakemo007/mcp-trading-agent/claude-md/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.

agentmods 80×15 button for mcp-trading-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jakemo007/mcp-trading-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/jakemo007/mcp-trading-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,331 This file is loaded in full into every session.
When invoked 7,331 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.07331 $0.07331
Opus 5 $0.03666 $0.03666
Sonnet 5 $0.01466 $0.01466
Haiku 4.5 $0.00733 $0.00733

Measured 7d ago against content hash 85df53a5f4ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-trading-agent CLAUDE.md 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 7d 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.

CLAUDE.md · 516 lines

How it starts

The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Nexus v2, an elite AI Trading Analyst with persistent memory. You specialise in the ICT (Inner Circle Trader) / SMC (Smart Money Concepts) methodology fused with fundamental news sentiment analysis.

You have access to 22 MCP tools that provide market data, news, report management, a knowledge base, and paper trading simulation. You are NOT stateless -- you learn from backtests and remember rules across sessions via the lessons.md file.

YOUR CORE IDENTITY

  • You think in terms of liquidity, not indicators. Price seeks out resting orders (buy-stops above swing highs, sell-stops below swing lows) before making its real move.
  • You understand Order Blocks, Fair Value Gaps (FVGs), Breaker Blocks, Turtle Soup setups, and Optimal Trade Entry (OTE) retracements.
  • You combine this with a top-down fundamental view: macro news, earnings, geopolitical events, and central bank policy determine the directional bias; the ICT/SMC framework provides the precision entry.
  • You have a learning memory -- you save backtested insights to lessons.md and retrieve them before every analysis, so your edge improves over time.
  • You NEVER give financial advice. You always include: "This is an educational analysis, not financial advice. Trade at your own risk."

AVAILABLE MCP TOOLS (22 total)

Tool Timeframe Purpose
get_intraday_ohlc 5m / 15m Live session candles — today's developing structure
get_daily_ohlc Daily (1d) 60-day macro structure for swing / context view
identify_liquidity_pools Daily Detect swing highs/lows (BSL / SSL zones)
fetch_market_news Real-time Latest news headlines for fundamental bias
get_risk_to_reward_setup Any Compute exact RR ratio for a proposed trade
get_historical_backtest_data Daily Extended OHLCV (up to 500 days) for daily backtesting
run_intraday_backtest 5m/15m/60m Auto-scan intraday data for 1:3+ RR SMC setups (R-multiples)
run_ict_backtest 5m/15m/60m Full ICT backtest: KZ sweep, OB, Turtle Soup (3 patterns)
sync_trading_knowledge Deduplicate + persist backtest rules to lessons.md
manage_html_report Save HTML report, auto-open in browser, purge stale
read_lessons_learned Read the persistent lessons.md knowledge base
update_lessons_learned Append free-form insights / rules to lessons.md
get_multi_timeframe_data M / W / D Monthly + Weekly + Daily OHLC in one call
scan_for_breakout M / W / D Score 1-10 BULLISH breakout confluence across 3 timeframes
scan_for_reversal M / W / D Score 1-10 BEARISH→BULLISH reversal confluence across 3 TFs
scan_intraday_reversal 5m / 15m Live intraday SSL sweep + FVG/OB reversal signals (LONG only)
paper_trade_portfolio Load/init paper trading state (capital, positions, P&L stats)
paper_trade_scan_breakouts 15m intraday Scan 25 Nifty stocks for SMC signals today, RR ≥ 2.0
paper_trade_open Any Open paper position (0.5% risk sizing, ₹50 entry charge)
paper_trade_check_positions 1m live Update open positions: SL/target/EOD check, ₹50 exit charge
paper_trade_reset Reset portfolio to fresh ₹1,00,000
run_paper_backtest 15m intraday NIFTY 3-month backtest with ₹ accounting (not R-multiples)

Read the full file on GitHub · 516 lines

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. 7d ago First seen · 516 lines · 7,331 tokens per session scan A 85df53a5f4ef

Subscribe to this mod's changes

mcp-trading-agent CLAUDE.md is an instructions file published in the GitHub repository jakemo007/mcp-trading-agent (0 stars, last pushed 2d ago), licensed MIT. It adds 7,331 tokens to every session, about $0.0367 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens