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 holon-run/uxc --skill okx-mcp-skillgit clone --depth 1 https://github.com/holon-run/uxcWrote 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/holon-run/uxc/okx-mcp-skill)<a href="https://agentmods.dev/skills/holon-run/uxc/okx-mcp-skill"><img src="https://agentmods.dev/badge/skills/holon-run/uxc/okx-mcp-skill/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/holon-run/uxc/okx-mcp-skill"><img src="https://agentmods.dev/badge/skills/holon-run/uxc/okx-mcp-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.01330 |
| Opus 5 | $0.00039 | $0.00665 |
| Sonnet 5 | $0.00016 | $0.00266 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
okx-mcp-skill 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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKX MCP Skill
Use this skill to run OKX MCP operations through uxc.
Reuse the uxc skill for shared protocol discovery, output parsing, and generic auth/binding flows.
Prerequisites
uxcis installed and available inPATH.- Network access to
https://web3.okx.com/api/v1/onchainos-mcp. - OKX Onchain API key is available for real calls.
Quick Trial Key
For quick read-only trial, OKX docs currently expose a shared demo key:
d573a84c-8e79-4a35-b0c6-427e9ad2478d
Example:
uxc auth credential set okx-mcp --auth-type api_key --api-key-header OK-ACCESS-KEY --secret d573a84c-8e79-4a35-b0c6-427e9ad2478d
Use your own key for regular usage, stability, and production workflows.
Core Workflow
- Confirm endpoint and protocol with help-first probing:
uxc https://web3.okx.com/api/v1/onchainos-mcp -h
- Configure credential/binding for repeatable auth:
uxc auth credential set okx-mcp --auth-type api_key --api-key-header OK-ACCESS-KEY --secret-env OKX_ACCESS_KEYuxc auth credential set okx-mcp --auth-type api_key --api-key-header OK-ACCESS-KEY --secret-op op://Engineering/okx/OK-ACCESS-KEYuxc auth binding add --id okx-mcp --host web3.okx.com --path-prefix /api/v1/onchainos-mcp --scheme https --credential okx-mcp --priority 100
- Use fixed link command by default:
command -v okx-mcp-cli- If missing, create it:
uxc link okx-mcp-cli https://web3.okx.com/api/v1/onchainos-mcp okx-mcp-cli -h
- Inspect operation schema before execution:
okx-mcp-cli dex-okx-market-price -hokx-mcp-cli dex-okx-market-token-search -hokx-mcp-cli dex-okx-balance-total-value -hokx-mcp-cli dex-okx-dex-quote -h
- Prefer read operations first, then high-impact operations.
Capability Map
- Market:
dex-okx-market-pricedex-okx-market-tradesdex-okx-market-candlesticksdex-okx-market-candlesticks-historydex-okx-index-current-pricedex-okx-index-historical-price
- Token discovery/enrichment:
dex-okx-market-token-searchdex-okx-market-token-rankingdex-okx-market-token-holderdex-okx-market-token-basic-infodex-okx-market-token-price-info
- Wallet:
dex-okx-balance-chainsdex-okx-balance-total-valuedex-okx-balance-total-token-balancesdex-okx-balance-specific-token-balance
- Swap:
dex-okx-dex-aggregator-supported-chainsdex-okx-dex-liquiditydex-okx-dex-quotedex-okx-dex-approve-transactiondex-okx-dex-swapdex-okx-dex-solana-swap-instruction
What ships with it
3 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.
- 10d ago First seen · 111 lines · 78 tokens per session scan A 210ed8cf8f41
okx-mcp-skill is a skill published in the GitHub repository holon-run/uxc (113 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,330 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
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
linear
Linear project management — issues, cycles, and projects via GraphQL API.
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
gmgn-contract-dd
Contract due-diligence score for one token address — contract safety, holder structure and price action combined into a single 0-100 composite, capped by GMGN's own rug label, where every deduction names the field it read and an absent field is never a passing check. Use when the user wants one verdict number rather…
gmgn-market
Get crypto and meme token price charts (K-line, candlestick, OHLCV), trending meme coin rankings by volume, newly launched tokens on launchpads (pump.fun, fourmeme, letsbonk, Raydium, etc.), the hot-search ranking (most-searched tokens), and search for a specific token or wallet by name, symbol, contract address…