matrix

A reference guide for spotting visual patterns that often make a website look generically AI-generated. It explains what to inspect, why a pattern may look artificial, how to change it, and when the same pattern is appropriate.

In plain words
What is it for?
Use it as the rulebook for preventing or reviewing AI-looking interfaces, especially when checking screenshots, page structure, spacing, typography, colors, and repeated components.
Why use it?
It provides a consistent vocabulary and decision guide for reviewing interface design while avoiding false alarms when a visual choice fits the product.

Command

Install

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.

agentmods
npx agentmods add commands/alphabravo-oss/guild/matrix
Clone the repo
git clone --depth 1 https://github.com/alphabravo-oss/guild
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01116
Opus 5 $0.00008 $0.00558
Sonnet 5 $0.00003 $0.00223
Haiku 4.5 $0.00002 $0.00112

Measured 2d ago against content hash dbf3c78f617a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

matrix 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.

plugins/e2e/commands/matrix.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user wants every route × every role tested. Roles config and route source from $ARGUMENTS or sensible defaults.

Preflight

  1. playwright.config.ts exists.
  2. Smoke specs from /e2e:crawl exist at tests/smoke/ — if not, ask the user to run /e2e:crawl first. The matrix builds on the route inventory; don't redo discovery here.
  3. .auth/ is in .gitignore — verify, refuse to proceed if missing (auth artifacts must never be committed).

Determine roles

Look for e2e.config.json at the cwd root. If absent, ask the user for the role list and login credentials per role. Default scaffold:

{
  "baseURL": "http://localhost:3000",
  "roles": {
    "anon": null,
    "user": { "username": "[email protected]", "password": "..." },
    "admin": { "username": "[email protected]", "password": "..." }
  },
  "loginFlow": {
    "url": "/login",
    "usernameField": "Email",
    "passwordField": "Password",
    "submitButton": "Sign in"
  }
}

The anon role has null credentials — used for unauthenticated traffic. Never invent credentials. If the user hasn't provided them, ask.

Generate authenticated storageState (once per role)

For each non-anon role:

  1. Write tests/auth/<role>.setup.ts — a setup spec that logs in and saves storageState to .auth/<role>.json:
import { test as setup } from '@playwright/test';
import config from '../../e2e.config.json';

const role = '<role>';
const file = `.auth/${role}.json`;

setup(`authenticate ${role}`, async ({ page }) => {
  const creds = config.roles[role];
  await page.goto(config.loginFlow.url);
  await page.getByLabel(config.loginFlow.usernameField).fill(creds.username);
  await page.getByLabel(config.loginFlow.passwordField).fill(creds.password);
  await page.getByRole('button', { name: config.loginFlow.submitButton }).click();
  await page.waitForURL((url) => !url.pathname.includes('/login'));
  await page.context().storageState({ path: file });
});
  1. Add a setup project to playwright.config.ts that runs these before the matrix:

Read the full file on GitHub · 124 lines

Changes

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.

  1. 2d ago First seen · 124 lines · 16 tokens per session scan A dbf3c78f617a

Subscribe to this mod's changes

matrix is a command published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 1,116 once invoked, about $0.0001 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 2026-08-31.