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 gmx-io/gmx-ai --skill gmx-liquiditygit clone --depth 1 https://github.com/gmx-io/gmx-aiWrote 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/gmx-io/gmx-ai/gmx-liquidity)<a href="https://agentmods.dev/skills/gmx-io/gmx-ai/gmx-liquidity"><img src="https://agentmods.dev/badge/skills/gmx-io/gmx-ai/gmx-liquidity/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/gmx-io/gmx-ai/gmx-liquidity"><img src="https://agentmods.dev/badge/skills/gmx-io/gmx-ai/gmx-liquidity.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 | $0.00045 | $0.05669 |
| Opus 5 | $0.00023 | $0.02835 |
| Sonnet 5 | $0.00009 | $0.01134 |
| Haiku 4.5 | $0.00005 | $0.00567 |
Grade A, and why
gmx-liquidity 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 — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GMX Liquidity Skill
Overview
GMX V2 has two liquidity layers that back perpetual and spot trading:
- GM Pools — Single-market liquidity pools. Each GM pool backs one market (e.g., ETH/USD) and is composed of a long token and short token. Depositing mints GM tokens (LP tokens); withdrawing burns them.
- GLV Vaults (GMX Liquidity Vaults) — Multi-market vaults that hold multiple GM tokens and auto-rebalance across constituent pools. Depositing mints GLV tokens; withdrawing burns them.
Supported chains:
| Chain | Chain ID | Native Token | GLV Vaults |
|---|---|---|---|
| Arbitrum | 42161 | ETH | Yes |
| Avalanche | 43114 | AVAX | Yes |
| Botanix | 3637 | BTC | No (contracts deployed, no vaults configured) |
Execution model: All write operations use a two-step async pattern:
- User creates a request (deposit/withdrawal/shift) via
ExchangeRouterorGlvRoutermulticall - Keeper executes the request with oracle prices (typically 1–30 seconds later)
The user pays an execution fee (in native token) upfront to cover keeper gas costs. Excess fee is refunded.
Integration paths:
- SDK (
@gmx-io/sdk) — Read pool data, balances, and market info. Write operations (deposit/withdraw) are not yet in the SDK. - Contract-level (viem) — Full read + write via
ExchangeRouter.multicall()andGlvRouter.multicall().
This skill complements gmx-trading which covers perpetual trading and swaps.
GM Pools
Each GM pool is a pair of tokens backing a specific market:
- Long token — The asset (e.g., WETH for ETH/USD)
- Short token — The stablecoin (e.g., USDC)
- GM token — The LP token representing a share of the pool
Deposits can be:
- Balanced — Deposit both long and short tokens proportionally. Lower fees (helps balance the pool).
- Single-sided — Deposit only one token. The protocol swaps a portion internally. Higher fees if it imbalances the pool.
Withdrawals burn GM tokens and return the underlying long and short tokens. A withdrawal can specify minLongTokenAmount and minShortTokenAmount for slippage protection.
What ships with it
1 file 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 · 580 lines · 45 tokens per session scan A d47cc931b756
gmx-liquidity is a skill published in the GitHub repository gmx-io/gmx-ai (11 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 5,669 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 skills, from other repositories
awaken-agent-skills
Awaken DEX trading and market data operations for agents.
SunSwap DEX Trading
Execute token swaps, manage liquidity, and query market data on SunSwap DEX via the sun-cli.
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…
crypto-token-analysis
Deep-dive framework for analyzing crypto tokens — market data, liquidity health, tokenomics, unlock schedules, and risk assessment. Combines on-chain data, API queries, and multi-source validation to generate actionable investment verdicts.
portkey-eoa-agent-skills
Portkey EOA wallet lifecycle and asset operations for creating, importing, listing, backing up, selecting, and deleting wallets; querying tokens, NFTs, prices, balances, and history; and performing transfers, approvals, bridge, view, send, and fee estimation operations on AElf. Use by default for direct EOA wallets…
eforest-agent-skills
Skill "eforest-agent-skills" from eforest-finance/eforest-agent-skills, covering eforest agent skill, when to use, capabilities, safe usage rules and command recipes.