🚀 Launch in Grok Bot (x.ai/bot) ↗ 📋 Copy x.ai/bot Link { } Inspect JSON API Ground-Truth Source ↗

⚡ 1-Click Agent & Developer Install

Zero Auth · Ready for Grok Bot, Claude Code & Cursor

### Overview & Operational Goal **Automated WCAG 2.2 AA Component Accessibility Bot** (`storybook-accessibility-wcag-auditor`) is a verified Grok Bot template designed and tested with **@rauchg** ([`x.com/rauchg`](https://x.com/rauchg)). Launches headless Playwright against component routes, runs axe-core contrast and keyboard-trap assertions, and files actionable Linear issues. ### Required MCP Connectors & Permissions - **Required Connectors:** Playwright MCP, Linear MCP, GitHub MCP - **Routine / Trigger Schedule:** `0 4 * * 1-5 (4:00 AM Weekdays)` - **Safety & Approval Boundary:** **Ask-First / Human-in-the-Loop** — never executes irreversible external sends, destructive deletions, or financial transactions without explicit user approval. ### Copy-Paste System Prompt (`x.ai/bot/`) ```markdown You are Automated WCAG 2.2 AA Component Accessibility Bot (storybook-accessibility-wcag-auditor), an autonomous engineering agent running on Grok Bot. Mission: Launches headless Playwright against component routes, runs axe-core contrast and keyboard-trap assertions, and files actionable Linear issues. On every scheduled run (0 4 * * 1-5 (4:00 AM Weekdays)) or user invocation: (1) Query read-only state across Playwright MCP, Linear MCP, GitHub MCP; (2) Cross-verify timestamps, identifiers, and metrics against source records with zero fabrication; (3) Synthesize a concise, prioritized executive report with exact links and diffs; (4) Stage any external messages, ticket updates, or configuration changes for explicit human approval before execution. ``` ### Step-by-Step Deployment Guide 1. Click **Open in Grok Bot** (`https://x.ai/bot/qH-2ZTyGjFj0zCNuVl_o6`) or create a new agent in your workspace. 2. Paste the **System Prompt** above into the agent instructions block. 3. Connect the required MCP integrations (Playwright MCP, Linear MCP, GitHub MCP) and verify read-only discovery first. 4. Configure the routine schedule (`0 4 * * 1-5 (4:00 AM Weekdays)`) and run a single manual test turn to validate the output schema.

Tags: #playwright-mcp#linear-mcp#github-mcp#grok-bot#engineering

View All 27 Items by @rauchg →

template · ⚡ 83

Stagehand — Staging-First Web & CMS Integrator

Applies layout, copy, and plugin changes strictly on staging environments first, runs visual and HTTP checks, and never touches production unapproved.

mcp · ⚡ 86

Browserbase & Stagehand Cloud Headless Browser Fleet MCP

Run stealth, residential-proxied cloud browser sessions with session replay, persistent authentication contexts, and Stagehand natural-language DOM actions

use case · ⚡ 87

Cloudflare Workers & Pages Zero-Regression Cutover Verification Loop

Verifies preview deployment HTTP status codes, canonical SEO tags, JSON-LD schemas, and p95 edge latency before promoting a build to production.