okx-cex-auth

okx-cex-auth is a skill for Claude Code, Codex from okx/agent-skills. It costs 228 tokens per session (4,553 once invoked), scanned A, a copy of okx-cex-auth, MIT.

A setup and login workflow for the OKX command-line tool. OKX is a cryptocurrency exchange, and authentication proves that the tool may access the selected account.

In plain words
What is it for?
Logging in, reconnecting an OKX account, choosing the correct regional site, configuring credentials, checking authentication status, and logging out.
Why use it?
It guides first-time account connection and recovery when a session expires or a command reports an authentication error. It supports OKX's OAuth login flow and API-key setup for different regional sites.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Logging in, reconnecting an OKX account, choosing the correct regional site, configuring credentials, checking authentication status, and logging out.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/okx/agent-skills/okx-cex-auth
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 okx/agent-skills --skill okx-cex-auth
Clone the repo
git clone --depth 1 https://github.com/okx/agent-skills

Made for: Claude Code, 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-cex-auth

README.md
[![agentmods](https://agentmods.dev/badge/skills/okx/agent-skills/okx-cex-auth/github.svg)](https://agentmods.dev/skills/okx/agent-skills/okx-cex-auth)
Your own site
<a href="https://agentmods.dev/skills/okx/agent-skills/okx-cex-auth"><img src="https://agentmods.dev/badge/skills/okx/agent-skills/okx-cex-auth/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-cex-auth

Your own site · 80×15
<a href="https://agentmods.dev/skills/okx/agent-skills/okx-cex-auth"><img src="https://agentmods.dev/badge/skills/okx/agent-skills/okx-cex-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 228 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,553 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
  • Socket pass 19 Oct 2026
  • Snyk pass 19 Oct 2026
How audits are shown
Origin 100% copy Near-identical to another mod 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 $0.00228 $0.04553
Opus 5.5 $0.00091 $0.01821
Sonnet 5.5 $0.00046 $0.00911
Haiku 4.5 $0.00023 $0.00455

Measured 7d ago against content hash 87feba9d1142, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

okx-cex-auth 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 7d 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.

Origin

This is a copy

100% identical to okx-cex-auth — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/okx-cex-auth/SKILL.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OKX CEX Authentication

OAuth 2.0 device flow authentication for OKX CLI. Guides first-time setup, re-authentication after session expiry, and logout.

Supported Sites

Site Region URL
global Global www.okx.com
eea EEA my.okx.com
us US app.okx.com
tr TR tr.okx.com

Site is a separate dimension from auth method. Both API-key and OAuth paths require a site. Once selected, a site is persisted:

  • API-key users: profile.site in ~/.okx/config.toml (written by okx config init).
  • OAuth users: saved inside the okx-auth binary state the first time okx auth login --site <X> succeeds, and returned by okx auth status --json as the site field.

There is no okx config set-site command — site cannot be persisted independently of an auth attempt. For OAuth flows, the agent must remember the user's choice within the conversation and pass --site <X> on okx auth login.

Prerequisites

Install okx CLI if not already installed:

npm install -g @okx_ai/okx-trade-cli

Step 0: Pre-flight Check (MANDATORY)

Unconditional rule — do NOT skip Step 0 under any circumstances. Even if a prior skill (preflight, okx-cex-portfolio, etc.) already ran auth status and passed you a conclusion like "user is not_logged_in, go log in" — you MUST re-run the two commands below yourself and walk Steps 0.1 → 0.2 → 0.3 in order. Upstream tool output does not substitute for your own pre-flight. The single most common failure mode for this skill is an agent that reads an upstream "not authenticated" signal, skips Step 0.1 site selection, and calls okx auth login with a silently-defaulted site.

Run both in parallel:

okx config show --json
okx auth status --json

Then apply the following three checks in strict order — each step short-circuits the rest.

Step 0.1 — Site check (independent of auth mode)

Read the full file on GitHub · 331 lines

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. 7d ago Changed 87feba9d1142
  2. 1mo ago Changed 02c8b59b8259
  3. 1mo ago Changed 65d18afdaed4
  4. 1mo ago Changed a0de361ae12b
  5. 1mo ago Changed 3f2e9ac3aad1
  6. 1mo ago First seen · 331 lines · 228 tokens per session scan A c4f16c49e766

Subscribe to this mod's changes

okx-cex-auth is a skill published in the GitHub repository okx/agent-skills (195 stars, last pushed 7d ago), licensed MIT. It adds 228 tokens to every session and 4,553 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to okx-cex-auth, differing in 0 lines, and is treated as a copy.