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 agentmods add instructions/drasticstatic/robinhood-mcp/claude-mdgit clone --depth 1 https://github.com/drasticstatic/robinhood-mcpWrote 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/instructions/drasticstatic/robinhood-mcp/claude-md)<a href="https://agentmods.dev/instructions/drasticstatic/robinhood-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/drasticstatic/robinhood-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.01016 | $0.01016 |
| Opus 5 | $0.00508 | $0.00508 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
robinhood-mcp 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 5d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code when working with this repository.
Project Overview
robinhood-mcp is a read-only MCP server that wraps the robin_stocks Python library to provide research tools for Robinhood portfolio data. This is strictly a research/educational tool - no trading functionality is exposed.
Architecture
src/robinhood_mcp/
├── __init__.py # Package version
├── auth.py # Authentication with TOTP support
├── tools.py # 12 read-only tool implementations
└── server.py # FastMCP server with tool registration
Key Design Decisions
-
Read-Only Only: We explicitly do NOT expose any trading functions:
- No
order_buy_*,order_sell_* - No
cancel_*_order - No account modification functions
- No
-
FastMCP: Uses FastMCP for simpler decorator-based tool registration
-
Lazy Authentication: Login happens on first tool call, not server startup
-
Error Handling: All robin_stocks calls are wrapped with
_safe_call()for consistent error handling
Common Commands
# Install dependencies
pip install -e ".[dev]"
# Run linting
ruff check .
ruff format --check .
# Run tests
pytest -v
# Run with coverage
pytest --cov=src --cov-report=html
# Run the server
robinhood-mcp
Environment Variables
| Variable | Required | Description |
|---|---|---|
ROBINHOOD_USERNAME |
Yes | Robinhood account email |
ROBINHOOD_PASSWORD |
Yes | Robinhood account password |
ROBINHOOD_TOTP_SECRET |
No | Base32 TOTP secret for 2FA |
Testing
Tests use mocked robin_stocks responses. To run with real credentials (careful!):
# Set env vars first
pytest tests/ -v
Adding New Tools
- Add the implementation to
tools.pywith proper type hints - Register in
server.pywith@mcp.tool()decorator - Add tests in
tests/test_tools.py - Update
server.jsontool list - Update README.md tool table
Publishing
This project uses GitHub Actions for CI/CD:
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.
- 5d ago First seen · 116 lines · 1,016 tokens per session scan A 7a7576c397cc
robinhood-mcp CLAUDE.md is an instructions file published in the GitHub repository drasticstatic/robinhood-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,016 tokens to every session, about $0.0051 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.
Other instructions, from other repositories
longbridge-mcp CLAUDE.md
Claude Code instructions for longbridge/longbridge-mcp, covering code formatting, code style, generic bounds, imports and comments.
tradingview-mcp-jackson CLAUDE.md
Claude Code instructions for drasticstatic/tradingview-mcp-jackson, covering tradingview mcp — claude instructions, decision tree — which tool when, "what's on my chart right now?", "what levels/lines/labels are showing?" and "give me price data".
polymarket-alpha-bot CLAUDE.md
Instructions for chainstacklabs/polymarket-alpha-bot, covering claude.md, commands, development, pipeline and seed data.
luno-mcp copilot-instructions.md
Instructions for luno/luno-mcp, covering github copilot instructions, repository structure, coding standards, go standards and mcp server guidelines.
open-stocks-mcp CLAUDE.md
Instructions for Open-Agent-Tools/open-stocks-mcp, covering claude.md, project overview, quick reference, development setup and testing.
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.