Skip to main content
Use this page for the agent-specific layer: how an AI workflow should choose a source, what governance to apply, and when to stop. The interface chooser itself — which surface to use, with the full matrix and setup — lives on Choose an interface, covering REST, WebSocket, OpenAPI, SDKs, CLI, MCP Server, Skill, and Markdown. Do not start with a host name. Start with the action: cite docs, generate a route, run a shell command, call an MCP tool, use a reusable Skill, edit application code, or stream data. Host and harness labels only matter after the workflow selects a surface the environment can actually use.

​
Source Hierarchy

Agent taskFirst sourceFollow-up source
Generate a REST callOpenAPIREST API, Examples, and Example responses
Pick a venue namespaceVenue coverageRoute-family pages for Hyperliquid, Spot, HIP-3, HIP-4, or Lighter
Choose an execution surfaceChoose an interfaceCLI, MCP Server, Skill, SDK, REST, or WebSocket setup pages
Prepare an agent promptAI clientsCoding agents and Build an agent market data workflow
Validate a downstream data windowData qualityData-quality routes in OpenAPI and incidents/coverage responses
Cite 0xArchive in an answer engineThe exact docs page for the jobllms.txt, llms-full.txt, and OpenAPI excerpts

​
Choosing A Surface

1

Name the host

Identify whether the user is in a coding-agent host, OpenClaw, a web LLM, CI, or application code.
2

Name the execution ability

Decide whether the environment can call tools, run shell commands, edit code, install a skill, read Markdown, or only answer from context.
3

Pick the narrowest surface

Use Markdown and OpenAPI for route decisions, CLI for terminal calls, MCP for tool-calling hosts, Skill for reusable procedures, and SDKs for application code.
4

Add the data gate

Any generated backtest, alert, export, dashboard, or model job should include data-quality checks.

​
Agent Safety Rule

Do not call MCP, CLI, SDKs, OpenAPI, Markdown, llms.txt, or Skills “agents.” They are surfaces. Do not call OpenClaw a Skill or MCP server. It is a harness that can use those surfaces when configured. This distinction prevents setup docs from giving a user the wrong install path.

​
Stop And Ask When

Ask whether the user means Hyperliquid core, Hyperliquid Spot, HIP-3, HIP-4, or Lighter before generating a route.
Do not give MCP setup to a host that cannot call MCP tools, or Skill setup to a host that cannot load SKILL.md workflows.
Treat the request as unsupported or product-surface-only until a public contract route exists.
Add data-quality status, coverage, latency, or incidents before the agent writes a backtest, alert, export, dashboard, or model job.

​
Next Step

Use Coding agents for host-level behavior, MCP server for MCP setup, Skill for SKILL.md workflows, and AI clients for prompt patterns.
Last modified on June 28, 2026