# About AgentPass

A small, opinionated index of whether software can read the web the way people do. Built and maintained by Scott Scheferman.

Updated November 9, 2026.

## Why this exists

Agents fail on the web for boring reasons: a robots group that hides the catalogue, a product page that needs JavaScript to state a price, a canonical tag pointing at a staging host, a contact page that only exists inside a chatbot. A browser shows a person a perfectly good page while an agent receives an empty mount node. ARI-100 narrows that gap to a repeatable measurement.

## How it is built

A single Node process with no runtime dependencies. Plain HTTP fetches, a deterministic scoring table, server-rendered HTML, and the same report as JSON, Markdown and MCP.

## What it will not tell you

It will not tell you whether an agent understood your page or whether a model will quote you. It measures affordances: the artefacts an agent needs before comprehension is possible.

## Contact

Email [hello@agentpass.dev](mailto:hello@agentpass.dev). Include the host and the report URL so the evidence line can be checked against a fresh fetch. We answer within one working day.

## Machine interfaces

- [llms.txt](https://www.agentpass.page/llms.txt)
- [AGENTS.md](https://www.agentpass.page/AGENTS.md)
- [OpenAPI 3.1](https://www.agentpass.page/openapi.json)
- [MCP endpoint](https://www.agentpass.page/mcp)