hyperliquid-orders

hyperliquid-orders is a skill for Claude Code from galleonlabs/hypergrok-trading-desk. It costs 88 tokens per session (5,173 once invoked), scanned A, original, MIT.

A procedure for placing, cancelling, and changing orders on Hyperliquid, a cryptocurrency trading exchange. It covers regular limit orders, immediate-or-cancel orders, take-profit orders, and stop-loss orders.

In plain words
What is it for?
It helps prepare and send approved orders, round prices and sizes correctly, group protective orders, use client order IDs, handle reduce-only orders, and interpret responses.
Why use it?
It reduces errors caused by invalid prices or sizes, incorrect order types, missing protection, or misunderstood exchange responses.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hypergrok plugin — 17 skills, 7 agents shipped together

Good fit It helps prepare and send approved orders, round prices and sizes correctly, group protective orders, use client order IDs, handle reduce-only orders, and interpret responses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/galleonlabs/hypergrok-trading-desk/hyperliquid-orders
Install

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.

Any agent
npx skills add galleonlabs/hypergrok-trading-desk --skill hyperliquid-orders
Clone the repo
git clone --depth 1 https://github.com/galleonlabs/hypergrok-trading-desk

Made for: Claude Code.

Or install hypergrok, the plugin that ships this one along with the rest of its 17 skills, 7 agents.

Wrote 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.

agentmods badge for hyperliquid-orders

README.md
[![agentmods](https://agentmods.dev/badge/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-orders/github.svg)](https://agentmods.dev/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-orders)
Your own site
<a href="https://agentmods.dev/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-orders"><img src="https://agentmods.dev/badge/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-orders/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.

agentmods 80×15 button for hyperliquid-orders

Your own site · 80×15
<a href="https://agentmods.dev/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-orders"><img src="https://agentmods.dev/badge/skills/galleonlabs/hypergrok-trading-desk/hyperliquid-orders.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,173 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 3
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.05173
Opus 5 $0.00044 $0.02586
Sonnet 5 $0.00018 $0.01035
Haiku 4.5 $0.00009 $0.00517

Measured 11d ago against content hash e2f621c25407, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hyperliquid-orders 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.

skills/hyperliquid-orders/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hyperliquid orders

Everything here ends in a signed request to /exchange. On this desk only the Execution Trader runs it, only on a ticket with a Risk PASS and the user's approval by id, and only once per approval (desk-execution-protocol). Reads used for reconciliation are in hyperliquid-account.

Concepts you must get right

  • Asset index, not symbol. Perps use the index of the coin in meta.universe (BTC is 0 on mainnet, but never hardcode: read meta). Spot uses 10000 + index in spotMeta.universe. The Python SDK's Exchange accepts the coin name and resolves the index; the TS SDK wants the number.
  • Price rounding. At most 5 significant figures, and at most 6 - szDecimals decimal places for perps (8 - szDecimals for spot). Integer prices are always valid. Wrong precision is rejected by the exchange.
  • Size rounding. Round down to the market's szDecimals. Never round up.
  • Minimum order value is 10 USD notional.
  • Time in force: Gtc rests until filled or cancelled; Ioc fills what it can immediately and cancels the rest; Alo (add liquidity only) rests or is rejected if it would take.
  • There is no market order. A market-style order is an Ioc limit at a price bounded by your slippage tolerance (buy: above mid; sell: below mid).
  • reduceOnly orders can only reduce an existing position; use it for exits, stops and take-profits.
  • cloid (client order id) is 0x + 32 hex characters (16 bytes). Unique per order. It lets you query and cancel an order even if the response was lost.
  • Trigger orders (tp/sl): triggerPx is the mark price that arms the order; isMarket: true executes market-style once triggered, false places a limit at p. p is always required and acts as the worst-acceptable price after the trigger, so for market triggers set it beyond the trigger: a sell trigger's p below triggerPx, a buy trigger's p above it. A stop whose p equals its trigger can rest unfilled through a gap, so the desk defaults to a 5% bound for stop-losses (filling matters more than slippage) and 1% for take-profits; the app uses 10% for both. The ticket may override.
  • Grouping: na (independent orders); normalTpsl (entry plus TP/SL as one-cancels-other tied to that entry: children are sized to the entry, placed only when it fills, cancelled if it is cancelled, and when one child fills the sibling is cancelled); positionTpsl (TP/SL tied to the position rather than to an order, shown as the position's own TP/SL, isPositionTpsl: true). Every TP/SL with an explicit size is fixed-size once placed; it does not resize when the position changes. The app's "entire position" TP/SL is a reduce-only trigger sent with size 0 under positionTpsl grouping (such orders show up live in frontendOpenOrders as sz: "0.0", isPositionTpsl: true); rehearse it on testnet before the desk relies on it.
  • Responses: each order in an action gets a status: {"resting": {"oid": ...}}, {"filled": {"totalSz", "avgPx", "oid"}}, "waitingForTrigger", "waitingForFill", or {"error": "..."}. A top-level {"status": "err", "response": "..."} means the whole action was rejected.

Read the full file on GitHub · 271 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 271 lines · 88 tokens per session scan A e2f621c25407

Subscribe to this mod's changes

hyperliquid-orders is a skill published in the GitHub repository galleonlabs/hypergrok-trading-desk (60 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 5,173 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.

Related

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.

Superior-Trade/superior-skills · 64 tokens

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…

Superior-Trade/superior-skills · 83 tokens

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…

Superior-Trade/superior-skills · 87 tokens

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…

Superior-Trade/superior-skills · 77 tokens

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…

Superior-Trade/superior-skills · 91 tokens

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.

Superior-Trade/superior-skills · 63 tokens