Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/galleonlabs/hypergrok-trading-desknpx agentmods add skills/galleonlabs/hypergrok-trading-desk/hyperliquid-websocketWrote 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/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-websocket)<a href="https://agentmods.dev/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-websocket"><img src="https://agentmods.dev/badge/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-websocket/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/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-websocket"><img src="https://agentmods.dev/badge/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-websocket.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 80 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00089 | $0.02294 |
| Opus 5 | $0.00044 | $0.01147 |
| Sonnet 5 | $0.00018 | $0.00459 |
| Haiku 4.5 | $0.00009 | $0.00229 |
Grade A, and why
hyperliquid-websocket 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyperliquid WebSocket
Read-only, no key. Endpoints: wss://api.hyperliquid.xyz/ws (mainnet), wss://api.hyperliquid-testnet.xyz/ws (testnet). Prefer WebSocket over polling for anything continuous: fills, order updates, book and price watches.
Protocol
Subscribe: {"method": "subscribe", "subscription": {...}}. Unsubscribe with "method": "unsubscribe". The server acknowledges with {"channel": "subscriptionResponse", ...} then streams {"channel": "<type>", "data": ...}. Send {"method": "ping"} periodically (the SDKs do it for you; the server expects activity within about a minute) and expect {"channel": "pong"}.
Subscription types the desk uses:
| Type | Subscription JSON | Data |
|---|---|---|
| Mids for all markets | {"type":"allMids"} (optional "dex") |
{"mids": {"BTC": "97123.5", ...}} |
| Order book | {"type":"l2Book","coin":"ETH"} (optional nSigFigs, mantissa, fast: true for 5 levels) |
{"coin","time","levels":[bids,asks]}, up to 20 levels a side, pushed on each block at least 0.5 s after the last push |
| Trades | {"type":"trades","coin":"ETH"} |
array of {coin, side, px, sz, time, hash, tid, users} |
| Candles | {"type":"candle","coin":"ETH","interval":"1m"} |
{t,T,s,i,o,c,h,l,v,n} updated in place until the bar closes |
| Best bid/offer | {"type":"bbo","coin":"ETH"} |
{"coin","time","bbo":[bid, ask]} |
| Asset context | {"type":"activeAssetCtx","coin":"ETH"} |
funding, OI, mark, oracle, premium, volume for one market |
| Account fills | {"type":"userFills","user":"0x..."} |
{"user","isSnapshot","fills":[...]} (first message is a snapshot) |
| Order updates | {"type":"orderUpdates","user":"0x..."} |
array of {order:{coin,side,limitPx,sz,oid,timestamp,origSz,cloid}, status, statusTimestamp} |
| Account events | {"type":"userEvents","user":"0x..."} |
fills, funding, liquidation, non-user cancels; arrives on channel "user" |
| Account funding | {"type":"userFundings","user":"0x..."} |
hourly funding payments |
| Per-market account data | {"type":"activeAssetData","user":"0x...","coin":"ETH"} |
leverage setting, max trade sizes, available to trade, mark (perps only) |
| Account state stream | {"type":"clearinghouseState","user":"0x..."} / {"type":"openOrders","user":"0x..."} |
{dex, user, clearinghouseState:{...REST shape...}} / {dex, user, orders:[...]} (order items carry the frontend fields: isTrigger, triggerPx, orderType, cloid), pushed |
| TWAP state | {"type":"twapStates","user":"0x...","dex":""} / {"type":"userTwapSliceFills","user":"0x..."} |
running TWAPs and their slice fills |
| Frontend snapshot | {"type":"webData3","user":"0x..."} |
positions, orders and context in one stream (heavy) |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 121 lines · 89 tokens per session scan A 7d8e45ed5b75
hyperliquid-websocket is a skill published in the GitHub repository galleonlabs/hypergrok-trading-desk (60 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 2,294 once invoked, about $0.0004 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 skills, from other repositories
ct-alpha
Crypto Twitter intelligence and alpha research. Search X/Twitter for real-time crypto narratives, trending tokens, yield strategies, smart money signals, and protocol research. Features TweetRank (PageRank-inspired credibility scoring), multi-signal token detection, coordinated raid detection, and dynamic tool…
tushare
A Python interface for Tushare, a financial data service that provides market and company information for stocks, funds, futures, and digital assets. It returns queried data as pandas tables.
hyperliquid
Use when backtesting, deploying, checking funding readiness, or debugging a Hyperliquid strategy through Superior Trade Unified API — writing Freqtrade configs and strategy code, running sweeps, checking managed-wallet balances, trading HIP-3 perps, or diagnosing a deployment that will not start or trade.
polymarket
Use when the user wants to trade, research, or backtest Polymarket prediction markets through Superior Trade — finding markets by slug or event URL, placing a single immediate market order, writing NautilusTrader strategies, running filled-data backtests, funding pUSD, or deploying and monitoring a live Polymarket…
backtesting
Use when running, interpreting, or designing backtests on Superior Trade — anything about backtest windows, trade-count thresholds, exit-reason mix, parameter sweeps, walk-forward validation, zero-trade diagnosis, compute-cost estimation, or "is this backtest result trustworthy?". Pair with the relevant strategy…
fees-optimizations
Use when the user asks about fees, fee optimization, slippage, maker vs taker, post-only or ALO orders, fee tiers, builder code fees, effective spread, order pricing, lowering trading costs, or why a live Hyperliquid Freqtrade strategy underperforms its backtest. Also use proactively for high-turnover designs (5m or…