Skip to content

Overview

Understand ai_stp, its trust model, and the path from catalog to installed setup.

ai_stp

ai_stp helps a developer and their coding agent select, verify and safely install a complete setup for an AI harness.

A setup covers instructions, skills, MCP, hooks, commands, agents, plugins and settings. ai_stp records provenance, compatibility, exact versions and trust decisions so that an agent never has to guess at a configuration.

Where to start

  • Quickstart: install the CLI, check the environment and see the first commands.
  • Harnesses: what the MVP supports, what is in beta, and what the undefined mode means.
  • Concepts: harness, setup, component, passport and trust line.
  • Components: how skill, mcp, hook, command, agent, plugin, instruction and setting differ.
  • Trust and safety: why a verified author is not the same thing as safe content.
  • Troubleshooting: recovering when an install or a check does not pass.

What the MVP does

The MVP supports Claude Code, Codex and Grok Build as primary harnesses. Pi and OpenCode are available as beta lines, and an unknown harness falls back to the limited undefined mode.

The main path looks like this:

CLI → passports → project index → search → setup assembly → checks
→ install plan → backup → apply through the provider → status

The web surface shows the public catalog and the account. Assembly, checks and installation are done by the CLI, the agent and the harness's own provider.

??? question "How to read this documentation" If ai_stp is new to you, start with the quickstart and the harnesses page. If you are already assembling a setup, go straight to components: each page explains what one kind is for, where its boundary is, and what it risks.

ai_stp