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 skills add galleonlabs/hypergrok-trading-desk --skill hyperliquid-positionsgit 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/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-positions)<a href="https://agentmods.dev/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-positions"><img src="https://agentmods.dev/badge/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-positions/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-positions"><img src="https://agentmods.dev/badge/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-positions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 Data Exfiltration · line 31 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 43 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 109 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00085 | $0.02513 |
| Opus 5 | $0.00043 | $0.01256 |
| Sonnet 5 | $0.00017 | $0.00503 |
| Haiku 4.5 | $0.00009 | $0.00251 |
Grade B, and why
hyperliquid-positions scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -sS -X POST $BASE/info -H 'Content-Type: application/json' -d "{\"type\":\"clearinghouseState\",\"user\":\"$ADDR\"}" | jq '{ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST $BASE/info -H 'Content-Type: application/json' -d "{\"type\":\"clearinghouseState\",\"user\":\"$ADDR\"}" | jq '{ How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyperliquid positions and margin
Reads here are for everyone (Risk Manager first); the write actions (updateLeverage, updateIsolatedMargin, closes) are Execution Trader only, on a ticket. Order mechanics are in hyperliquid-orders.
Concepts
- Cross margin (default): all cross positions share the account's margin, and unrealised PnL counts as margin; liquidation is account-wide. Isolated margin: the position has its own margin; only that margin is at risk, and you can add to or remove from it (some markets are
strictIsolatedand refuse removal; HIP-3 markets may benoCross). - Leverage is set per market and per mode with
updateLeverage; it caps position size against margin, it is not "how much you win". Max leverage is per market and tiered by notional (see margin tiers). - Margin tiers: each perp has a margin table (
meta.marginTables, matched to the asset viamarginTableId) listing notional thresholds and the max leverage allowed above each. Bigger positions get less leverage. - Maintenance margin is half of the initial margin at the max leverage of the applicable tier (so between 1.25% for a 40x market and 16.7% for a 3x market); liquidation happens when account (cross) or position (isolated) equity falls below maintenance margin, on mark price. Large positions are liquidated partially first; the cross liquidation price does not depend on your leverage setting.
- Liquidation price is reported by the exchange per position (
liquidationPx); use that, do not recompute. - Funding is exchanged every hour between longs and shorts at the market's funding rate; it changes equity while a position is open.
- Closing is an order in the opposite direction with
reduceOnly. Full close at market: reduce-only IOC at a slippage-bounded price for the live position size.
Read positions and margin
ADDR=$HYPERLIQUID_ACCOUNT_ADDRESS
BASE=$([ "$HYPERLIQUID_NETWORK" = mainnet ] && echo https://api.hyperliquid.xyz || echo https://api.hyperliquid-testnet.xyz)
curl -sS -X POST $BASE/info -H 'Content-Type: application/json' -d "{\"type\":\"clearinghouseState\",\"user\":\"$ADDR\"}" | jq '{
accountValue: .marginSummary.accountValue, totalMarginUsed: .marginSummary.totalMarginUsed,
withdrawable, crossMaintenanceMarginUsed,
positions: [.assetPositions[].position | {coin, szi, entryPx, positionValue, unrealizedPnl, liquidationPx, marginUsed,
leverage: (.leverage.type + " " + (.leverage.value|tostring)), returnOnEquity, cumFunding: .cumFunding.sinceOpen}]}'
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.
- 11d ago First seen · 132 lines · 85 tokens per session scan B f73b6772f676
hyperliquid-positions is a skill published in the GitHub repository galleonlabs/hypergrok-trading-desk (60 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 2,513 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
aerodrome
Use when creating, validating, backtesting, deploying, sizing, or troubleshooting Aerodrome/Base spot trading strategies through the Superior Trade API, especially Freqtrade configs using exchange.name "aerodrome", AERO/USDC or CHECK/USDC pairs, AMM market swaps, wallet/gas balance checks, no-orderbook pricing, or…
basis-arb
Use when the user asks for spot-perp basis trade, basis arbitrage, cash-and-carry, perp discount, or any setup that reads the spot–perp basis as a positioning signal. Long-perp leg only — pure two-leg basis arb requires a paired spot short (or long) which Freqtrade can't run cleanly. The strategy below captures the…
funding-squeeze
Use when writing a strategy that captures short-squeeze setups on Hyperliquid perps — squeeze, short squeeze fuel, negative funding rally, fade the shorts, paid to long. Goes long when funding APR is deeply negative and price is already rising, then exits on funding normalisation or a time stop. Reads squeeze fuel…
bollinger-reverter-4h
Use when writing a symmetric Bollinger-band mean-reversion strategy on the 4h timeframe — BB reverter, range trader, chop strategy, ADX<25 mean reversion, band-fade with a minimalroi ladder. Long-or-short on 2-sigma band touches with RSI confirmation. Validated on BTC/ETH/SOL/DOGE; numbers and the exact ROI ladder are…
dca-weekly
Use when writing, validating, or troubleshooting a recurring scheduled buy strategy (DCA, dollar-cost averaging, weekly buys, daily buys, monthly accumulation, accumulator) on Superior Trade — especially anything that should "buy more of the same pair" on a calendar trigger rather than a price trigger.