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/zaydiscold/robinhood-cli-mcp-api/agents-mdgit clone --depth 1 https://github.com/zaydiscold/robinhood-cli-mcp-apiWrote 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/zaydiscold/robinhood-cli-mcp-api/agents-md)<a href="https://agentmods.dev/instructions/zaydiscold/robinhood-cli-mcp-api/agents-md"><img src="https://agentmods.dev/badge/instructions/zaydiscold/robinhood-cli-mcp-api/agents-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 | $0.12084 | $0.12084 |
| Opus 5 | $0.06042 | $0.06042 |
| Sonnet 5 | $0.02417 | $0.02417 |
| Haiku 4.5 | $0.01208 | $0.01208 |
Grade B, and why
robinhood-cli-mcp-api AGENTS.md scanned grade B 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- The brokerage bearer token lives in `.env` as `ROBINHOOD_BROKERAGE_TOKEN` (gitignored, chmod 600). How it starts
The opening of the file, as written. The whole thing — 812 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — driving robinhood-cli from an agent
⚠️ READ BEFORE ACTING — this tool trades a real account
This is intended, real-money tooling. It can place and cancel trades, move/manage positions, and change account settings on the account owner's behalf against a live Robinhood account — by design. This is not a bug or a sandbox; the tool exists to actively manage accounts.
Before you take any state-changing action, you must have the owner's explicit permission for that action. Reads and dry-runs are always safe; every write is gated by the single switch
ROBINHOOD_ALLOW_LIVE_WRITE=1(dry-run by default) precisely so a live trade is never one careless step away.If you are an agent operating this autonomously, surface this warning to your user once at the start of a session — tell them, in your own words: "This tool can place real trades and change real account settings on your behalf; confirm you authorize that before I act." Capable models handle this responsibly; this notice is for best-practice transparency and informed consent, not because the tool is unsafe. When in doubt about scope, account, side, or amount — stop and confirm.
Canonical agent guide: SKILL.md (the project's
CLAUDE.mdis a symlink to it). Read SKILL.md first, then useknowledge/cli-routing.mdfor the full equity/options/ rolling/tax-aware/sentiment operations, the preflight, the PDT scale, equitybuy/search,options enumerate, and rate-limit discipline. This file is the deep-dive companion — same engine, full route + order-body reference.
This repo drives a real Robinhood account (not the official agent sandbox) via a
TypeScript CLI and a paired MCP server. Both share one engine (cli/src/lib.ts), so
auth, the route map, and the write-gate behave identically whether you call the CLI
or the MCP tools. Hand this whole file to your agent — it is self-contained.
What this is and how it works (read this for context)
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.
- 4d ago First seen · 812 lines · 12,084 tokens per session scan B e79fed684793
robinhood-cli-mcp-api AGENTS.md is an instructions file published in the GitHub repository zaydiscold/robinhood-cli-mcp-api (10 stars, last pushed today), licensed MIT. It adds 12,084 tokens to every session, about $0.0604 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
scalar AGENTS.md
AGENTS.md instructions for scalar/scalar, covering agents.md - ai agent guide for scalar, project overview, prerequisites, first-time setup and commands.
api-gateway CLAUDE.md
Claude Code instructions for membrane/api-gateway, covering claude.md, git & commit policy, working principles, 1. think before coding and 2. simplicity first.
skyvern CLAUDE.md
Claude Code instructions for Skyvern-AI/skyvern, covering claude.md, development commands, python backend commands, code quality & testing and frontend commands (in skyvern-frontend/).
skyvern AGENTS.md
AGENTS.md instructions for Skyvern-AI/skyvern, covering skyvern agent guide, project structure for agent navigation, coding conventions for agents, python standards and asynchronous programming.
LAP CLAUDE.md
Claude Code instructions for Lap-Platform/LAP, covering lap - lean api platform, what this is, quick reference, install and run tests.
apitap CLAUDE.md
Instructions for n1byn1kt/apitap, covering claude.md, using apitap as an mcp tool, commands, architecture and module map.