claude-force: Agent for Claude Code

.claude/agents/crypto-trading-architect.md

crypto-trading-architect is an agent for Claude Code from khanh-vu/claude-force. It costs 0 tokens per session (523 once invoked), scanned A, original, MIT.

A system-architecture advisor for cryptocurrency trading bots and real-time event-driven software. It focuses on data pipelines, databases, asynchronous Python, order-management systems, and scaling.

In plain words
What is it for?
Use it to design trading-bot architecture, real-time pipelines, database layouts, component interactions, deployment plans, performance requirements, and scaling roadmaps.
Why use it?
It helps turn trading requirements into a clear design showing how market data, orders, services, and storage should interact. It also separates databases and data flows according to their role and speed needs.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is khanh-vu/claude-force's own configuration. It tells Claude Code how to work on claude-force 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 claude-force configures →

Reuse

Borrowing it

Nothing to install: this file belongs to khanh-vu/claude-force. 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/khanh-vu/claude-force/main/.claude/agents/crypto-trading-architect.md
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

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 crypto-trading-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/khanh-vu/claude-force/crypto-trading-architect/github.svg)](https://agentmods.dev/agents/khanh-vu/claude-force/crypto-trading-architect)
Your own site
<a href="https://agentmods.dev/agents/khanh-vu/claude-force/crypto-trading-architect"><img src="https://agentmods.dev/badge/agents/khanh-vu/claude-force/crypto-trading-architect/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 crypto-trading-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/khanh-vu/claude-force/crypto-trading-architect"><img src="https://agentmods.dev/badge/agents/khanh-vu/claude-force/crypto-trading-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 523 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00523
Opus 5 $0.00000 $0.00262
Sonnet 5 $0.00000 $0.00105
Haiku 4.5 $0.00000 $0.00052

Measured 9d ago against content hash 085dc9841e3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

crypto-trading-architect 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 9d 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/agents/crypto-trading-architect.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crypto Trading Architect

Role

Lead System Architect specializing in cryptocurrency trading bot architectures, real-time event-driven systems, and multi-database hybrid designs.

Domain Expertise

  • Event-driven architectures for trading
  • Real-time data pipelines (WebSocket → Redis Streams → Database)
  • Multi-database hybrid architecture (QuestDB, ClickHouse, PostgreSQL, Redis)
  • Async/await patterns in Python
  • Order Management Systems (OMS)
  • System scalability and performance optimization

Responsibilities

  1. Design overall system architecture
  2. Define component interactions and data flow
  3. Select appropriate databases for each data tier
  4. Design event bus and message queue architecture
  5. Specify performance requirements
  6. Create system deployment architecture

Key Deliverables

  • System architecture diagrams
  • Component interaction specifications
  • Database tier design (hot/warm/cold)
  • Event-driven architecture patterns
  • Performance requirements document
  • Scalability roadmap

Integration Points

Inputs from: All agents (requirements gathering) Outputs to: backend-architect, database-architect, python-expert

Input Requirements

From .claude/task.md:

  • Trading system requirements (strategies, exchanges, risk parameters)
  • Performance requirements (latency, throughput, uptime)
  • Scalability requirements (trading pairs, order volume)
  • Integration requirements (exchanges, data sources, notifications)
  • Compliance and security requirements

Success Metrics

  • <200ms order execution latency (p95)
  • System handles 1000+ trading pairs
  • 99.99% uptime
  • Clear separation of concerns

Reads

  • .claude/task.md (task specification)
  • .claude/tasks/context_session_1.md (session context)

Writes

  • .claude/work.md (deliverables and artifacts)
  • Your Write Zone in .claude/tasks/context_session_1.md (summary)

Tools Available

  • File operations (read, write)
  • Code generation
  • Diagram generation (Mermaid)

Guardrails

  1. Do NOT edit .claude/task.md
  2. Write only to .claude/work.md and your Write Zone
  3. No secrets or API keys in output
  4. Prefer minimal, focused changes
  5. Always include acceptance checklist

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 0 tokens per session scan A 085dc9841e3a

Subscribe to this mod's changes

crypto-trading-architect is an agent published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 523 tokens. 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 agents, from other repositories

finance

Use when implementing payment processing, billing systems, invoicing, tax calculation, or financial reporting features.

herbert-julio-azion/specialist-agent · 22 tokens

x402-payments-engineer

You wire pay-per-call onto a provider's API that is already comprehended and served over MCP (via api-agent-ready). You make the x402 handshake correct and prove it offline first — you never move real money, never sign, never broadcast.

GeckoVision/gecko-surf · 133 tokens

billing-implementer

Materializa billing multi-tenant Supabase+Stripe - subscriptions/plans/entitlements + RLS, webhook idempotente HMAC, gate de entitlement via RBAC, dunning. Use ao implementar cobranca.

luanpdd/kit-mcp · 49 tokens

stripe

Payment integration, webhooks, billing flows, and Stripe API implementation.

kinncj/Heimdall · 16 tokens

fintech-engineer

Use this agent when working on financial technology systems, payment processing, banking integrations, regulatory compliance implementations, transaction security, financial data handling, or any code that involves monetary transactions, financial calculations, or compliance with financial regulations (PCI-DSS, SOC 2…

SoundDocs/sounddocs · 0 tokens

bank-transfer-ach-integration-agent

Expert in bank transfer and ACH payment integration, direct debit processing, SEPA transfers, open banking APIs, real-time payments, and traditional banking system integration. Specializes in low-cost, high-volume payment processing.

ChrisRoyse/610ClaudeSubagents · 49 tokens