Borrowing it
Nothing to install: this file belongs to nirholas/three.ws. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nirholas/three.ws/main/.agents/skills/okx-ai-guide/SKILL.mdgit clone --depth 1 https://github.com/nirholas/three.wsWrote 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/nirholas/three.ws/okx-ai-guide)<a href="https://agentmods.dev/skills/nirholas/three.ws/okx-ai-guide"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/okx-ai-guide/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/nirholas/three.ws/okx-ai-guide"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/okx-ai-guide.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 | $0.00205 | $0.02047 |
| Opus 5.5 | $0.00082 | $0.00819 |
| Sonnet 5.5 | $0.00041 | $0.00409 |
| Haiku 4.5 | $0.00020 | $0.00205 |
Grade A, and why
okx-ai-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKX.AI Guide
The OKX.AI onboarding entry. Introduces OKX.AI (the Agent economic system), detects whether the current runtime can run OKX.AI, and routes the user into one of the three identity-registration flows — or, on an incompatible platform, tells them how to get a compatible one.
Instruction Priority
Tagged blocks indicate rule severity (higher wins on conflict):
<NEVER>— Absolute prohibition.<MUST>— Mandatory step.<SHOULD>— Best practice.
Scope & Boundary
This skill owns: OKX.AI intro + platform detection + login & identity detection (new vs returning user) + routing into registration. It does NOT:
- own the Onchain OS welcome banner — that is
okx-how-to-play. - implement registration — delegated to
okx-agent-identity(see §Step 5). - own the wallet-login flow — Step 1 only checks login via
wallet statusand hands off tookx-agentic-wallet's existing login flow when needed; the registration playbooks also run their own preflight.
Step 0 — Platform detection
detect_harness() {
if [ "${CLAUDECODE:-}" = "1" ]; then
echo "Claude Code"
elif [ -n "${HERMES_INTERACTIVE:-}" ] || [ -n "${HERMES_SESSION_SOURCE:-}" ] \
|| [ -n "${HERMES_YOLO_MODE:-}" ] || [ -n "${HERMES_QUIET:-}" ]; then
echo "Hermes"
elif [ -n "${OPENCLAW_CLI:-}" ] || [ -n "${OPENCLAW_SHELL:-}" ]; then
echo "OpenClaw"
elif [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_CI:-}" ]; then
echo "Codex"
else
echo "unknown"
fi
}
detect_harness
- Output ∈ {
Claude Code,Hermes,OpenClaw,Codex} → compatible → Step 1. - Output =
unknown→ incompatible → Step 3.
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.
- 2mo ago First seen · 112 lines · 205 tokens per session scan A e6e237b37179
okx-ai-guide is a skill published in the GitHub repository nirholas/three.ws (269 stars, last pushed yesterday), licensed Apache-2.0. It adds 205 tokens to every session and 2,047 once invoked, about $0.0008 per session on Opus 5.5. 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.
okx-ai-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| okx-ai-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 205 | Claude Code |
| cesiumjsznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 93 | Claude Code, Codex |
| decision-avatarellmos-ai/skills | Skill | 9 | 4d ago | MIT | A | 49 | Claude Code, Codex |
| sheleg-designssheleg/sheleg-design-skill | Skill | 4 | 4d ago | MIT | A | 80 | Cursor |
| p5jsmateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | A | 20 | Claude Code, Codex |
| threejs-docspledgeandgrow/pledge-skills | Skill | 10 | 3mo ago | MIT | A | 112 | Claude Code, Codex |
| 3d-website-architectdeveshpunjabi/3d-website-skill | Skill | 8 | 8mo ago | MIT | A | 240 | Claude Code, Codex |