aissue
Pick up an open issue from the amux issue tracker, mark it doing, work it, and mark it done.
Use when you need to test the amux dashboard UI, investigate a visual bug, or verify a frontend change works correctly
How it fires
How this command gets triggered: by you, by Claude, or both.
/pw-testContext preview
What this command does when you run it.
Use when you need to test the amux dashboard UI, investigate a visual bug, or verify a frontend change works correctly
description: Use when you need to test the amux dashboard UI, investigate a visual bug, or verify a frontend change works correctly allowed-tools: Bash, Read, Grep, Glob, Edit, Write argument-hint: [run|investigate <description>] context: fork
Run the amux Playwright test suite or investigate specific UI issues with a headless browser.
The user's request is: **$ARGUMENTS**
Run all Playwright UI tests:
node tests/browser-comparison.js
Parse the output and report:
The results JSON is also written to `/tmp/pw-test-results.json` for programmatic access.
Use Playwright programmatically to investigate a specific UI issue. Write and run a temporary Node.js script that:
1. Launches a persistent Chromium context with the auth profile:
const { chromium } = require('playwright');
const { homedir } = require('os');
const ctx = await chromium.launchPersistentContext(
`${homedir()}/.amux/playwright-auth/profile`,
{ headless: true, viewport: { width: 1440, height: 900 }, ignoreHTTPSErrors: true }
);
const page = await ctx.newPage();
await page.goto(process.env.AMUX_URL || 'https://localhost:8824', { waitUntil: 'domcontentloaded', timeout: 10000 });
await page.waitForTimeout(2000);2. Performs whatever DOM inspection, screenshot capture, CSS analysis, or interaction is needed to investigate the described issue.
3. Takes screenshots to `/tmp/pw-investigate-*.png` as evidence.
4. Outputs findings as structured console.log statements.
5. Closes the context when done.
Write the script to `/tmp/pw-investigate.js`, run it with `node /tmp/pw-investigate.js`, and report findings.
**Key patterns for investigation scripts:**
Add a new test case to `tests/browser-comparison.js`: 1. Read the existing test file to understand the pattern 2. Add the new test following the same `record()` pattern 3. Increment test numbering 4. Run the suite to verify the new test passes 5. Report results
Open-source control plane for AI coding agents. Run an AI engineering team: parallel Claude Code, Codex, and Gemini workers with a shared board, atomic tasks, schedules, loops, origin-stamped messaging, model switching, and self-healing recovery. One dashboard, or your phone. MIT, single Rust binary.
Pick up an open issue from the amux issue tracker, mark it doing, work it, and mark it done.
Use when the user says "add to board", "create a task", or wants to track a todo on the amux kanban board
Use when you need to interact with the amux system — manage board tasks, check sessions/workers, send emails, message via Telegram, automate browsers, work…
Use when the user asks to interact with a web page, take a screenshot of a site, click or type in Chrome, scrape content, or debug a web UI. Connects to real…
Repo/branch/file hygiene sweep — stray artifacts, doc drift, stale branches, worktrees, upstream sync, backup sprawl, duplicate build caches. Verifies before…
Scaffold a closed orchestrator loop — creates the mission note, state/constraints notes, and a scheduler entry from the v2 template.