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 dex-original/okx-agent-trade-kit --skill okx-cex-botgit clone --depth 1 https://github.com/dex-original/okx-agent-trade-kitWrote 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/dex-original/okx-agent-trade-kit/okx-cex-bot)<a href="https://agentmods.dev/skills/dex-original/okx-agent-trade-kit/okx-cex-bot"><img src="https://agentmods.dev/badge/skills/dex-original/okx-agent-trade-kit/okx-cex-bot/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/dex-original/okx-agent-trade-kit/okx-cex-bot"><img src="https://agentmods.dev/badge/skills/dex-original/okx-agent-trade-kit/okx-cex-bot.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 | $0.00112 | $0.08383 |
| Opus 5.5 | $0.00045 | $0.03353 |
| Sonnet 5.5 | $0.00022 | $0.01677 |
| Haiku 4.5 | $0.00011 | $0.00838 |
Grade A, and why
okx-cex-bot 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 1mo 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.
This is a copy
95% identical to okx-cex-bot — 449 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.
How it starts
The opening of the file, as written. The whole thing — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKX CEX Bot Trading
Grid and DCA (Spot & Contract Martingale) bot management on OKX. All bots are native OKX server-side — they run on OKX and do not require a local process.
Preflight
Before running any command, follow ../_shared/preflight.md.
Use metadata.version from this file's frontmatter as the reference for Step 2.
Prerequisites
npm install -g @okx_ai/okx-trade-cli
okx config init # select site -> follow browser OAuth flow
Security: NEVER accept credentials in chat. Guide users to
okx config initfor setup.
Credential & Profile Check
Run before every authenticated command. The auth method is detected during preflight Step 2 and remembered for the session.
Step A — Verify credentials
Run both commands — the apiKey field from okx auth status --json is the auth-binary's internal state and is always false regardless of whether ~/.okx/config.toml has an API-key profile. okx config show --json is the only authoritative source for API-key presence.
okx config show --json # reveals API-key profiles (TOML config)
okx auth status --json # reveals OAuth session state (auth-binary state)
Apply in this order — first match wins:
config show --jsonhas any profile with a non-emptyapi_keyfield → API Key mode. Proceed to Step B.- No API-key profile AND
auth status --jsonreturns"status":"logged_in"→ OAuth mode. Proceed to Step B. - No API-key profile AND
"status":"pending"— login is in progress, wait for it to complete. - No API-key profile AND
"status":"not_logged_in"— stop, loadokx-cex-authskill and follow login steps, wait for completion.
Step B — Confirm trading mode
Resolution:
- User intent is clear ("real"/"实盘"/"live" → live; "test"/"模拟"/"demo" → demo) → use it, inform user
- No explicit declaration → check conversation context for previous choice → reuse if found
- Nothing found → ask: "Live (实盘) or Demo (模拟盘)?" — wait before proceeding
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.
- 1mo ago First seen · 571 lines · 112 tokens per session scan A bb6e5a0ebe2e
okx-cex-bot is a skill published in the GitHub repository dex-original/okx-agent-trade-kit (113 stars, last pushed 4mo ago), licensed MIT. It adds 112 tokens to every session and 8,383 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to okx-cex-bot, differing in 449 lines, and is treated as a copy.
Other skills, from other repositories
obai-strategy
Quantitative equity strategy design and backtesting via the OBaI backtest MCP server (http://localhost:8007/mcp). Use when the user wants to build, test, backtest, optimize, refine, repair, or compare a trading strategy, run walk-forward robustness validation, inspect trade logs, or follow up on a backtest job.…
obai-prediction-markets
Polymarket prediction-market analysis via the OBaI prediction-markets MCP server (http://localhost:8009/mcp). Use for market discovery, event odds, YES/NO executable pricing and depth, price history, trade flow, holder concentration, trader leaderboards, wallet analysis, trade decision memos, calibration/longshot-bias…
autotrader
Set up or run authorized Alpaca paper-trading routines for long US stocks and ETFs: account/order reconciliation, strategy signal checks, order submission and trading-job reviews, using standalone scripts plus OBaI MCP skills for analysis. Never trades options, crypto or prediction markets. General financial research…
obai-hub
Route financial research, market data, portfolio analysis, and equity, prediction-market or crypto backtests directly to OBaI MCP servers and specialist skills. Use when MCP access is available or being configured, without requiring the OBaI CLI. Does not place broker orders; authorized Alpaca paper execution belongs…
obai
Use the installed OBaI CLI for financial research, market data, portfolio analysis, strategy backtests, and requested health/evaluation commands. Run obai query with JSON output and a persistent session for related questions. Use when the user requests the CLI or only the obai binary is available; use obai-hub instead…
obai-strategy-routing
Use when the user wants to build, test, backtest, optimize, refine, repair, compare, or follow up on a systematic trading strategy. Covers strategy design, backtesting, optimization, robustness analysis, rule generation, strategy repair/comparison, execution handoff, and strategy job follow-ups. Excludes prediction…