okx-exchange-websocket-skill

okx-exchange-websocket-skill is a skill for Codex from holon-run/uxc. It costs 40 tokens per session (905 once invoked), scanned A, original, MIT.

A read-only WebSocket connection to OKX's public exchange feeds, using UXC to receive live market events. WebSockets are long-lived connections that stream updates as they happen.

In plain words
What is it for?
Streaming ticker updates, trades, order-book data, and candle data for selected OKX instruments into an NDJSON file.
Why use it?
It avoids repeated polling when you need current exchange data and handles the subscription message required by OKX's public service.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Streaming ticker updates, trades, order-book data, and candle data for selected OKX instruments into an NDJSON file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/holon-run/uxc/okx-exchange-websocket-skill
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 holon-run/uxc --skill okx-exchange-websocket-skill
Clone the repo
git clone --depth 1 https://github.com/holon-run/uxc

Made for: Codex.

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 okx-exchange-websocket-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/holon-run/uxc/okx-exchange-websocket-skill/github.svg)](https://agentmods.dev/skills/holon-run/uxc/okx-exchange-websocket-skill)
Your own site
<a href="https://agentmods.dev/skills/holon-run/uxc/okx-exchange-websocket-skill"><img src="https://agentmods.dev/badge/skills/holon-run/uxc/okx-exchange-websocket-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.

agentmods 80×15 button for okx-exchange-websocket-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/holon-run/uxc/okx-exchange-websocket-skill"><img src="https://agentmods.dev/badge/skills/holon-run/uxc/okx-exchange-websocket-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 905 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 pass 7 Sept 2026
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 $0.00040 $0.00905
Opus 5 $0.00020 $0.00452
Sonnet 5 $0.00008 $0.00181
Haiku 4.5 $0.00004 $0.00090

Measured 10d ago against content hash fa26e8bf03ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

okx-exchange-websocket-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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/okx-exchange-websocket-skill/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OKX Exchange WebSocket Skill

Use this skill to run OKX public exchange WebSocket channels through uxc subscribe raw WebSocket mode.

Reuse the uxc skill for generic runtime behavior, sink handling, and event-envelope parsing.

Prerequisites

  • uxc is installed and available in PATH.
  • Network access to the OKX public WebSocket endpoint.
  • A writable sink path for NDJSON output.

Scope

This skill covers OKX public exchange channels such as:

  • tickers
  • trades
  • books and books5
  • candle channels

This skill does not cover:

  • OKX OnchainOS MCP
  • private WebSocket login flows
  • trading, account, or order-management channels
  • REST API workflows

Endpoint Model

Use the OKX public WebSocket endpoint:

  • wss://ws.okx.com:8443/ws/v5/public

OKX public channels require a subscribe frame after connect, for example:

{"op":"subscribe","args":[{"channel":"tickers","instId":"BTC-USDT"}]}

Core Workflow

  1. Start a raw WebSocket subscription:
    • uxc subscribe start wss://ws.okx.com:8443/ws/v5/public --transport websocket --init-frame '{"op":"subscribe","args":[{"channel":"tickers","instId":"BTC-USDT"}]}' --sink file:$HOME/.uxc/subscriptions/okx-btcusdt-ticker.ndjson
  2. Inspect sink output:
    • tail -n 5 $HOME/.uxc/subscriptions/okx-btcusdt-ticker.ndjson
  3. Query runtime status:
    • uxc subscribe list
    • uxc subscribe status <job_id>
  4. Stop the job when finished:
    • uxc subscribe stop <job_id>

Common Subscribe Frames

  • tickers:
    • {"op":"subscribe","args":[{"channel":"tickers","instId":"BTC-USDT"}]}
  • trades:
    • {"op":"subscribe","args":[{"channel":"trades","instId":"BTC-USDT"}]}
  • books5:
    • {"op":"subscribe","args":[{"channel":"books5","instId":"BTC-USDT"}]}
  • candles:
    • {"op":"subscribe","args":[{"channel":"candle1m","instId":"BTC-USDT"}]}

Runtime Validation

The following live raw WebSocket flow has been validated successfully through uxc:

  • endpoint: wss://ws.okx.com:8443/ws/v5/public
  • transport: --transport websocket
  • init frame:
    • {"op":"subscribe","args":[{"channel":"tickers","instId":"BTC-USDT"}]}

Read the full file on GitHub · 106 lines

Files

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.

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. 10d ago First seen · 106 lines · 40 tokens per session scan A fa26e8bf03ba

Subscribe to this mod's changes

okx-exchange-websocket-skill is a skill published in the GitHub repository holon-run/uxc (113 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 905 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.

Related

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-Platform/LAP · 89 tokens

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-Platform/LAP · 89 tokens

linear

Linear project management — issues, cycles, and projects via GraphQL API.

furkangonel/cowrangler · 17 tokens

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.

sickn33/agentic-awesome-skills · 95 tokens

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…

GMGNAI/gmgn-skills · 153 tokens

gmgn-swap

BEFORE RUNNING ANY COMMAND: Run gmgn-cli config --check. If exit code is 0, proceed normally. If exit code is 1, (1) run gmgn-cli config and show the output to the user; (2) once the user sends the API Key, run gmgn-cli config --apply to complete configuration and verification, then show the output to the user. If…

GMGNAI/gmgn-skills · 404 tokens