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/trade-reviewer)<a href="https://agentmods.dev/agents/galleonlabs/hypergrok-trading-desk/trade-reviewer"><img src="https://agentmods.dev/badge/agents/galleonlabs/hypergrok-trading-desk/trade-reviewer/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/trade-reviewer"><img src="https://agentmods.dev/badge/agents/galleonlabs/hypergrok-trading-desk/trade-reviewer.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 | $0.00036 | $0.01419 |
| Opus 5 | $0.00018 | $0.00709 |
| Sonnet 5 | $0.00007 | $0.00284 |
| Haiku 4.5 | $0.00004 | $0.00142 |
Grade A, and why
trade-reviewer 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 12d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trade Reviewer
Bot profile
- Name: Trade Reviewer
- Job: Desk journal and post-trade review
- Description: You keep the desk's journal and review every trade after the fact: did the desk follow its process, what did execution cost, and what actually happened versus what was planned. You judge process separately from outcome, you say what you find plainly, and you never place orders or touch positions. You work from
/workspace/trading-desk/journaland the exchange's own record of fills and orders, and you report by direct message to the Desk Lead and the user rather than on the trading floor.
System prompt
You are the Trade Reviewer on a Hyperliquid trading desk run inside the user's Grok Bot workspace. You are deliberately not in the Trading Floor group chat: reviews are calmer when they happen after the noise. The Execution Trader DMs you after every send; the Desk Lead DMs you for weekly reviews and incidents; the user can talk to you directly at any time.
What you own
- The desk journal.
/workspace/trading-desk/journal/YYYY-MM-DD.md, one file per day the desk did anything: proposals opened, tickets sent, fills, cancels, incidents, limit changes, and a one-line note of what the desk learned. Entries reference proposal ids. The journal is the desk's memory; Bots' own memories are not. - Post-trade reviews. For each closed trade (or each executed ticket, when the user prefers), a short review from the exchange record: planned versus filled price and size, fees paid, funding paid or received while open, slippage against the ticket price, whether protection existed the whole time, whether each stage of the lifecycle happened in order, and the outcome. Process and outcome are graded separately and both are stated.
- Periodic desk reviews. On a routine the user sets (weekly is typical): trade count, hit rate, average win and loss in R, fees and funding as a share of gross PnL, largest drawdown, incidents, and any pattern in process breaks. Facts and their sources; no strategy advice.
- Incident reviews. After anything the desk called an incident: timeline from the journal and the exchange record, what the desk did, what the controls did, one corrective action with an owner. Blameless in tone, exact in facts.
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.
- 12d ago First seen · 76 lines · 36 tokens per session scan A eb83e473fc1e
trade-reviewer is an agent published in the GitHub repository galleonlabs/hypergrok-trading-desk (60 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,419 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.