What is crypto-claude-desk CLAUDE.md?

A project instruction file for a cryptocurrency analysis system that coordinates several specialized agents, such as market, technical, news, risk, and portfolio analysts.

Setting up the project, running quick or full analyses for a cryptocurrency, viewing portfolio status, and closing trades through its documented commands.

It gives the coding agent a defined way to set up and operate the system, from quick market checks to longer multi-agent analyses. Cryptocurrency analysis means examining digital-asset markets and trading risks.

How hugoguerrap/crypto-claude-desk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hugoguerrap/crypto-claude-desk. 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/hugoguerrap/crypto-claude-desk/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hugoguerrap/crypto-claude-desk

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hugoguerrap/crypto-claude-desk/claude-md/github.svg)](https://agentmods.dev/instructions/hugoguerrap/crypto-claude-desk/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hugoguerrap/crypto-claude-desk/claude-md"><img src="https://agentmods.dev/badge/instructions/hugoguerrap/crypto-claude-desk/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hugoguerrap/crypto-claude-desk/claude-md"><img src="https://agentmods.dev/badge/instructions/hugoguerrap/crypto-claude-desk/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,639 This file is loaded in full into every session.

When invoked 3,639 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.

Model	Per session	Once invoked
Fable 5.1	$0.03639	$0.03639
Opus 5.5	$0.01456	$0.01456
Sonnet 5.5	$0.00728	$0.00728
Haiku 4.5	$0.00364	$0.00364

Measured 1mo ago against content hash 805fe29ab942, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crypto-claude-desk 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 1mo 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 · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crypto Trading Desk - Multi-Agent Intelligence System

A cryptocurrency analysis system built with Claude Code's native features: agents, MCP servers, and skills.

Architecture

User Query
    |
    v
[Claude Code - Coordinator]
    |  Reads this CLAUDE.md
    |  Routes by complexity:
    |
    +-- QUICK (1 subagent) ----------> market-monitor (haiku)
    |
    +-- STANDARD (2-3 parallel) -----> market-monitor + technical-analyst + news-sentiment
    |
    +-- FULL ANALYSIS (5 subagents) -> 3 phases with file-based coordination
         Phase 1 (parallel): market-monitor || technical-analyst || news-sentiment
         Phase 2 (sequential): risk-specialist (reads Phase 1 files)
         Phase 3 (sequential): portfolio-manager (reads all, decides)

How to Use

First-Time Setup

/setup - Run once after installing. Detects environment, installs uv + Python deps, verifies MCP servers work. Cross-platform (macOS, Linux, Windows).

Slash Commands

/quick BTC - Fast market snapshot (1 agent, ~15 sec)
/analyze BTC - Full 5-agent analysis with trading decision (~3-5 min)
/portfolio - View portfolio status and open trades
/close-trade trade_001 - Close trade with post-mortem
/validate-predictions - Review pending predictions against market data
/monitor - Autonomous loop: check SL/TP, close trades, evaluate predictions
/create - Extend the system with new components

Natural Language

Ask naturally and the coordinator routes by complexity:

"How's BTC?" → Quick (market-monitor only)
"RSI of ETH?" → Standard (technical-analyst only)
"Analyze SOL" → Standard (2-3 agents)
"Full analysis of BTC with recommendation" → Full (5 agents in phases)
"Check my portfolio" → portfolio-manager
"Post-mortem on trade_003" → learning-agent

Routing Rules

How Delegation Works

All agents are spawned via the Task tool with subagent_type: general-purpose and an explicit model parameter. This ensures every subagent inherits all MCP tools from the parent conversation. The agent .md files in agents/ contain the analysis framework — include "Read agents/{name}.md for your full analysis framework" in the prompt.

Read the full file on GitHub · 249 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.

1mo ago First seen · 249 lines · 3,639 tokens per session scan A 805fe29ab942

Subscribe to this mod's changes

crypto-claude-desk CLAUDE.md is an instructions file published in the GitHub repository hugoguerrap/crypto-claude-desk (64 stars, last pushed 2mo ago), licensed MIT. It adds 3,639 tokens to every session, about $0.0146 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.

Claude Code Finance and fintech Web3 and blockchain ai-agents anthropic claude-code-plugin crypto-trading cryptocurrency

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 · 9,715 tokens

crypto-claude-desk: Instructions file for Claude Code