setup-robinhood
Skill8 starsChanged 14 days agoMITView on GitHub
Connect Robinhood as Mangrove Agent's execution venue, inspect the connection and strategy routing, and explain setup or recovery. Use when the user asks to connect Robinhood, check Robinhood status, route a strategy to Robinhood, or recover a Robinhood authorization. Trigger with phrases such as "connect Robinhood", "check Robinhood status", or "route this strategy to Robinhood". Use the existing strategy workflow for research and signal selection.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-securitySkill
- check-alignmentSkill
- connect-krakenSkill
- setup-krakenSkill
- tool-specSkill
- trading-botSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Use agent_robinhood_status to inspect an existing connection.
- Very specific: line 29
No MCP tool currently reads a local strategy record on its own.
- Distinctive: line 45
Do not imply that the hosted engine runs the local scheduler or that connecting Robinhood itself starts trading.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Robinhood execution venue
Mangrove hosted services own signals, sizing, risk controls, exits and order
intents. The local agent owns scheduling, execution routing and reconciliation.
Robinhood executes orders. Read docs/robinhood-execution.md for the supported
scope, route schema, API equivalents and recovery behavior.
Connection and inspection
Use agent_robinhood_status to inspect an existing connection. If authorization
is missing or expired, run ./scripts/connect-robinhood.sh in the repository's
terminal. The user completes Robinhood's browser authorization for Mangrove
Agent. Never ask for passwords or tokens in chat, copy another assistant's OAuth
credentials, or alter Robinhood's approval setting. Verify status after connection.
agent_configure_execution_venue returns the venue mandate it saved, and
agent_configure_strategy_market returns the strategy record with execution_venue.
No MCP tool currently reads a local strategy record on its own.
market_context.market_data_venue is the price feed, not the execution broker.
A Robinhood route needs no local wallet. A live status does not prove any order
has filled: inspect evaluations, agent_list_venue_orders, and confirmed trades.
Prepare a route
Carry the user's chosen strategy, capital and limits through the existing create
and backtest workflow. Keep its execution config and explicit market context.
Configure the broker with agent_configure_execution_venue while the strategy is
fresh and inactive; this does not activate it or move money. Read back the saved
strategy and route. Do not invent a capital allocation or change a live mandate.
Activation is a separate existing lifecycle operation, described in the execution document. Observe the acting assistant's authorization and execution constraints. Once activated, the scheduler runs locally; the Mac must stay awake and online. Do not imply that the hosted engine runs the local scheduler or that connecting Robinhood itself starts trading.
Recovery
Inspect the journal before proposing a retry. Unknown submissions must be reconciled, never automatically resent. A cancellation acknowledgement does not prove absence of fills. Pausing prevents new submissions but does not cancel already submitted orders. Protective exits are evaluated on the strategy schedule, not installed as standing Robinhood bracket orders. Pending-order uncertainty can delay execution even though strategy evaluation continues.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

