open-stocks-mcp: Instructions file for Claude Code

CLAUDE.md

open-stocks-mcp CLAUDE.md is an instructions file for Claude Code from Open-Agent-Tools/open-stocks-mcp. It costs 3,734 tokens per session, scanned A, original, Apache-2.0.

Developer instructions for Open Stocks MCP, a server that provides stock-market data and trading tools through Robinhood and Charles Schwab broker APIs.

In plain words
What is it for?
They are for developing and testing account, portfolio, holdings, market-data, and broker-integration features.
Why use it?
They explain the server’s architecture, authentication, sessions, transport, storage, and journey-based tests so contributors can change it consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; names the TodoWrite tool; mentions Claude Code.

This is Open-Agent-Tools/open-stocks-mcp's own configuration. It tells Claude Code how to work on open-stocks-mcp 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 open-stocks-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Open-Agent-Tools/open-stocks-mcp. 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/Open-Agent-Tools/open-stocks-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Open-Agent-Tools/open-stocks-mcp

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 open-stocks-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/open-agent-tools/open-stocks-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/open-agent-tools/open-stocks-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,734 This file is loaded in full into every session.
When invoked 3,734 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03734 $0.03734
Opus 5 $0.01867 $0.01867
Sonnet 5 $0.00747 $0.00747
Haiku 4.5 $0.00373 $0.00373

Measured 9d ago against content hash 2a1b8370dd1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

open-stocks-mcp CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:3001/health # Test health endpoint
CLAUDE.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project guidance for Claude Code when working with the Open Stocks MCP server.

Project Overview

Open Stocks MCP - Model Context Protocol server providing stock market data and trading tools through Robinhood and Charles Schwab broker APIs.

  • Current Version: v0.6.5 with multi-broker support, enhanced authentication, and session management
  • Framework: FastMCP for simplified MCP development
  • APIs: Robin Stocks for Robinhood plus schwab-py for Charles Schwab
  • Transport: HTTP with Server-Sent Events (SSE), configurable via --port (default 3000)
  • Docker: Production-ready with persistent session/log storage

Quick Reference

Development Setup

uv sync   # installs project + all dev dependencies

Testing

Journey-Based Testing - 11 user journey categories for focused testing:

# All tests (skips exception tests by default)
pytest                           

# Fast journey testing (<30s each)
pytest -m "journey_account"      # Account management (16 tests, ~1.8s)
pytest -m "journey_portfolio"    # Portfolio & holdings (3 tests, ~1.7s)  
pytest -m "journey_market_data"  # Stock quotes & market info (19 tests, ~3.8s)
pytest -m "journey_research"     # Earnings, ratings, news (23 tests, ~3.0s)
pytest -m "journey_watchlists"   # Watchlist management (20 tests, ~16.7s)
pytest -m "journey_options"      # Options analysis (13 tests, ~9.7s)
pytest -m "journey_notifications" # Alerts & notifications (15 tests, ~1.6s)
pytest -m "journey_system"       # Health & monitoring (11 tests, ~1.9s)
pytest -m "journey_trading"      # Trading operations (1 test, ~1.6s)

# Combined journeys
pytest -m "journey_account or journey_portfolio"          # User account flows
pytest -m "journey_market_data or journey_research"       # Market intelligence
pytest -m "journey_options or journey_trading"            # Trading related

# Development workflows
pytest -m "not slow and not exception_test"               # Fast tests (recommended)
pytest -m "unit and journey_account"                      # Quick unit feedback
pytest tests/unit/                                        # Unit tests (fast)
pytest tests/integration/ -m integration                  # Integration (needs auth)
pytest -m rate_limited                                    # Live rate-limited API tests
RUN_RATE_LIMITED=1 pytest                                 # Include rate-limited tests in full run
OPEN_STOCKS_RUN_LIVE_MARKET=1 RUN_RATE_LIMITED=1 ENABLED_BROKERS=schwab uv run pytest tests/integration/test_schwab_live_journeys.py -m "live_market and auth_required and rate_limited" --run-live-market -q

# READ ONLY journeys (perfect for ADK evaluations)
pytest -m "journey_account or journey_portfolio or journey_market_data or journey_research or journey_notifications or journey_system"

# Failure-mode regression tests (network/auth failures, no live credentials needed)
uv run pytest tests/unit/test_error_handling.py tests/unit/test_auth_coordinator.py -k 'retry or timeout or connection or auth_failed' -q

# Performance/load benchmarks (mocked, CI-safe, no credentials needed)
uv run pytest -m performance tests/performance -v
RUN_PERFORMANCE=1 uv run pytest      # Include performance tests in a full run

Read the full file on GitHub · 326 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 · 326 lines · 3,734 tokens per session scan A 2a1b8370dd1a

Subscribe to this mod's changes

open-stocks-mcp CLAUDE.md is an instructions file published in the GitHub repository Open-Agent-Tools/open-stocks-mcp (9 stars, last pushed 29d ago), licensed Apache-2.0. It adds 3,734 tokens to every session, about $0.0187 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens