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 xiazhi88/desic-okx-agent --skill okx-account-analysisgit clone --depth 1 https://github.com/xiazhi88/desic-okx-agentWrote 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/xiazhi88/desic-okx-agent/okx-account-analysis)<a href="https://agentmods.dev/skills/xiazhi88/desic-okx-agent/okx-account-analysis"><img src="https://agentmods.dev/badge/skills/xiazhi88/desic-okx-agent/okx-account-analysis/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/xiazhi88/desic-okx-agent/okx-account-analysis"><img src="https://agentmods.dev/badge/skills/xiazhi88/desic-okx-agent/okx-account-analysis.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 | $0.00049 | $0.00191 |
| Opus 5 | $0.00024 | $0.00096 |
| Sonnet 5 | $0.00010 | $0.00038 |
| Haiku 4.5 | $0.00005 | $0.00019 |
Grade A, and why
okx-account-analysis 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.
What it actually says
OKX Account Analysis
- Select the requested account alias; use the configured default only when no account was specified.
- Start with
account_get_snapshotfor current state, then use history, fills, or bills for reconciliation. - Report environment and account alias with every conclusion.
- Distinguish equity, available balance, margin, notional exposure, realized results, and pending orders.
- Treat empty data as an observed empty result only when no warning or upstream error is present.
- Never request, print, infer, or return API credentials.
- Do not call any
trade_*tool while using this read-only analysis workflow.
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 · 15 lines · 49 tokens per session scan A e3e021f14b8e
okx-account-analysis is a skill published in the GitHub repository xiazhi88/desic-okx-agent (0 stars, last pushed 17d ago), licensed MIT. It adds 49 tokens to every session and 191 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 2026-08-31.
Other skills, from other repositories
OKX AI Trading Co-Pilot
AI-powered cryptocurrency trading assistant with 4-agent analysis, real-time OKX exchange integration, and autonomous trading capabilities.
polymarket
Query Polymarket: markets, prices, orderbooks, history.
quantdata-daily-bias
Reads rolling Brooks price-action events for a stock, ETF, futures contract, FX pair or crypto pair from the Quant Data Brooks Events API — range breakouts with measured failure rates and a calibrated per-event estimate, breakout follow-through, range position, long-range breakouts and climactic spikes — together with…
quantdata-max-pain
Looks up options positioning for US stocks and ETFs — max pain, open-interest call and put walls, put/call ratio, and estimated dealer gamma exposure (GEX) with the zero gamma flip level. Reads Quant Data's free public pages when no API key is set, and prefers the JSON endpoints /v1/maxpain and /v1/gamma when…
quantdata-weis-wave
Reads Weis Wave volume-price structure for a symbol from the Quant Data Weis Wave API — current wave direction and volume, recent completed waves, and detected events (climax-into-buying, no-supply, no-demand, sign-of-thrust) each carrying its pre-registered measured win rate. Use when the user asks about volume…
polymarket
Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.