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 agentmods add skills/nirholas/three.ws/okx-securitynpx skills add nirholas/three.ws --skill okx-securitygit clone --depth 1 https://github.com/nirholas/three.wsWhat 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 | $0.00284 | $0.02154 |
| Opus 5 | $0.00142 | $0.01077 |
| Sonnet 5 | $0.00057 | $0.00431 |
| Haiku 4.5 | $0.00028 | $0.00215 |
Grade A, and why
okx-security 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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onchain OS Security
5 commands for token risk analysis, DApp phishing detection, transaction pre-execution security, signature safety, and approval management.
Pre-flight Checks
Read
../okx-agentic-wallet/_shared/preflight.md. If that file does not exist, read_shared/preflight.mdinstead.
Fail-safe Principle (CRITICAL)
Scan completed — risk detected
If a security scan completes successfully and returns action: "block" or action: "warn", follow the Risk Action Priority Rule below. The Agent MUST NOT override risk verdicts.
Scan failed — infrastructure error
If a security scan fails to complete (network error, API timeout, rate limiting, malformed response), the Agent MUST:
- Report the error clearly to the user.
- Ask the user whether to retry the scan or proceed without scan results.
- If the user chooses to proceed, display a warning:
"⚠️ Security scan could not be completed. Proceeding without verification — please ensure you trust this operation."
- Log the skipped scan for auditability.
A security scan that fails to complete is NOT a "pass". Always inform the user and let them make an explicit decision.
Risk Action Priority Rule
tx-scan / sig-scan (transaction & signature scanning)
block > warn > safe (empty). The top-level action field reflects the highest priority from riskItemDetail.
action value |
Risk Level | Agent Behavior |
|---|---|---|
| (empty/null) | Low risk | Safe to proceed |
warn |
Medium risk | Show risk details, ask for explicit user confirmation |
block |
High risk | Do NOT proceed, show risk details, recommend cancel |
- Risk scan result is still valid even if simulation fails (
simulator.revertReasonmay contain the revert reason). - If
warningsfield is populated, the scan completed but some data may be incomplete. Still present available risk information. - An empty/null
actionin a successful API response means "no risk detected". But if the API call failed, the absence ofactiondoes NOT mean safe — apply the fail-safe principle.
What ships with it
5 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.
- 2d ago First seen · 141 lines · 284 tokens per session scan A 5049efc90c0e
okx-security is a skill published in the GitHub repository nirholas/three.ws (107 stars, last pushed 3d ago), licensed Apache-2.0. It adds 284 tokens to every session and 2,154 once invoked, about $0.0014 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.
Other skills, from other repositories
blender-mcp
Drive Blender via the catalog blender MCP, with bpy recipes.
blender-mcp
Control Blender directly from Gauss via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.
blender-mcp
Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.
blender-mcp
Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.
3d-website-architect
Expert skill for designing, building, and deploying modern premium websites with advanced animations and 3D interactive experiences using Three.js, React Three Fiber, GSAP, and Framer Motion. Use this skill whenever the user wants to build a website with 3D elements, create an immersive web experience, add interactive…
blender-mcp
Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.