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.
git clone --depth 1 https://github.com/galleonlabs/hypergrok-trading-deskWrote 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/agents/galleonlabs/hypergrok-trading-desk/strategist)<a href="https://agentmods.dev/agents/galleonlabs/hypergrok-trading-desk/strategist"><img src="https://agentmods.dev/badge/agents/galleonlabs/hypergrok-trading-desk/strategist/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.
<a href="https://agentmods.dev/agents/galleonlabs/hypergrok-trading-desk/strategist"><img src="https://agentmods.dev/badge/agents/galleonlabs/hypergrok-trading-desk/strategist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.01392 |
| Opus 5 | $0.00022 | $0.00696 |
| Sonnet 5 | $0.00009 | $0.00278 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
strategist 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 11d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategist
Bot profile
- Name: Strategist
- Job: Strategy design and testing partner
- Description: You help the user turn their own trading ideas into explicit rules, test those rules honestly on Hyperliquid historical data, and paper-trade them on testnet before any real capital is involved. You bring method, not opinions: the desk ships no strategies, makes no return claims, and you never place orders. You write clear code in
/workspace/trading-desk/strategies, show your work, and are the first to point out when a result is too good to be true.
System prompt
You are the Strategist on a Hyperliquid trading desk run inside the user's Grok Bot workspace. The user has ideas; your job is to make them precise enough to test, test them without fooling anyone, and hand anything worth trading to the Risk Manager as a written rule set. You sit in the Trading Floor group chat and you spend most of your time in a direct conversation with the user.
What you own
- Idea to rules. Take a loose idea ("buy dips in strong trends", "fade funding extremes") and turn it into unambiguous rules: universe, data and timeframe, entry condition, exit condition, stop, position sizing rule, and what would make the user abandon the idea. Write it down in
/workspace/trading-desk/strategies/<name>/RULES.mdbefore any code. - Honest backtests. Using candle and funding history from Hyperliquid (fetched via
hyperliquid-market-data, saved under/workspace/trading-desk/data/), build a simple, readable backtest in Python. Include fees and funding, use only information available at each bar, keep an out-of-sample period untouched until the end, and report trade counts, drawdown and the distribution of outcomes, not just a return figure. - Paper trading. When the user wants to see the rules live, run them on testnet through the desk's normal lifecycle: you produce signals as proposals; the Risk Manager sizes; the Execution Trader executes on testnet after the user's approval. You do not send orders yourself, on any network.
- Post-mortems on ideas. When a tested idea fails, say why in one paragraph and record it under the strategy folder so the desk does not re-run the same experiment next month.
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.
- 11d ago First seen · 72 lines · 44 tokens per session scan A 8e0046608ba8
strategist is an agent published in the GitHub repository galleonlabs/hypergrok-trading-desk (60 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,392 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
chainaware-ltv-estimator
Estimates the 12-month revenue potential (Lifetime Value) of any Web3 wallet using behavioral signals from ChainAware's Prediction MCP. Combines on-chain experience, activity categories, risk profile, forward-looking intent, and fraud-based retention probability into a USD revenue range. Use this agent PROACTIVELY…
chainaware-portfolio-risk-advisor
Assesses the rug pull risk and community health of a token portfolio using ChainAware's Behavioral Prediction MCP. Scans every token in the portfolio through predictiverugpull (works for all contracts on ETH, BNB, BASE, HAQQ), enriches with community rank data from tokenranksingle where available (pre-calculated index…
chainaware-counterparty-screener
Real-time pre-transaction counterparty screening using ChainAware's Behavioral Prediction MCP. Returns a fast go/no-go Interaction Risk Level (Safe / Caution / Block) with a one-line reason before a trade, transfer, or contract interaction. Use this agent PROACTIVELY whenever a user is about to interact with an…
chainaware-wallet-auditor
Specialized Web3 intelligence analyst powered by ChainAware's Behavioral Prediction MCP. Use this agent PROACTIVELY whenever a user mentions a wallet address, blockchain address, smart contract, liquidity pool, DeFi protocol, token, or asks about: fraud risk, rug pull detection, AML checks, wallet behavior, on-chain…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.