playwright-responsive-audit-skill

playwright-responsive-audit-skill is a skill for OpenCode from darellchua2/opencode-config-template. It costs 48 tokens per session (6,802 once invoked), scanned A, original, Apache-2.0.

A Playwright-based method for checking and fixing how a web interface behaves at different screen sizes. Playwright is a browser-testing tool, and responsive design means adapting a site to phones, tablets, and desktops.

In plain words
What is it for?
Use it to audit responsive pages, apply fixes by confidence level, rerun browser checks, and save end-to-end tests for detected issues.
Why use it?
It helps find layout defects on smaller or wider screens and verify that fixes do not break the same problem later.

Skill for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: mentions subagents; mentions OpenCode.

Good fit Use it to audit responsive pages, apply fixes by confidence level, rerun browser checks, and save end-to-end tests for detected issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/darellchua2/opencode-config-template/playwright-responsive-audit-skill
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.

Any agent
npx skills add darellchua2/opencode-config-template --skill playwright-responsive-audit-skill
Clone the repo
git clone --depth 1 https://github.com/darellchua2/opencode-config-template

Made for: OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for playwright-responsive-audit-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/playwright-responsive-audit-skill.svg)](https://agentmods.dev/skills/darellchua2/opencode-config-template/playwright-responsive-audit-skill)
Your own site
<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/playwright-responsive-audit-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/playwright-responsive-audit-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 18 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 46
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 47
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 50
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 57
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 351
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 354
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 374
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 375
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 376
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 377
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 378
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 611
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 612
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 613
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 621
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 623
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 632
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Excessive Agency · line 560
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 5.1 $0.00048 $0.06802
Opus 5 $0.00024 $0.03401
Sonnet 5 $0.00010 $0.01360
Haiku 4.5 $0.00005 $0.00680

Measured 4d ago against content hash ccfe99878018, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

playwright-responsive-audit-skill 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 4d 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.

opencode_app/.opencode/skills/playwright-responsive-audit-skill/SKILL.md · 781 lines

How it starts

The opening of the file, as written. The whole thing — 781 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I do

I define the methodology for auditing and fixing responsive UI defects in Next.js (or any web) projects using Playwright. This is a checker-and-fixer capability: detect responsive issues, apply fixes by confidence tier, and emit permanent regression specs.

When to use me

Loaded exclusively by responsive-audit-subagent via permission.skill. Not auto-triggered. The primary session spawns the subagent once; the subagent runs the closed loop internally over a persistent PTY session (detect→fix→re-verify), delegating only screenshot review to image-analyzer-subagent.

Prerequisite: Playwright Setup

Before running any responsive audit, Playwright must be installed and configured in the target project. This section covers detection, installation, auth setup, fixtures, and E2E best practices.

Step 0a: Detect if Playwright is Installed

# Check for Playwright config and dependencies
if [ ! -f "playwright.config.ts" ] || ! grep -q "@playwright/test" package.json 2>/dev/null; then
  echo "PLAYWRIGHT_NOT_INSTALLED"
else
  echo "PLAYWRIGHT_INSTALLED"
fi

Step 0b: Install Playwright (If Not Detected)

If PLAYWRIGHT_NOT_INSTALLED, run the full installation sequence:

# 1. Install Playwright and its test runner
npm init playwright@latest -- --quiet --browser=chromium

# 2. Install browser binaries (chromium is enough for CI; add firefox/webkit for cross-browser)
npx playwright install chromium
npx playwright install-deps chromium

# 3. Verify installation
npx playwright --version

For existing Next.js projects that already have a test runner (Vitest/Jest), Playwright coexists fine — install as a separate dependency:

npm install -D @playwright/test
npx playwright install chromium

Step 0c: Configure playwright.config.ts

Full configuration with responsive viewport matrix, auth, and best-practice settings:

import { defineConfig, devices } from '@playwright/test';

export default defineConfig({
  // Test directory
  testDir: './e2e',

  // Fail fast on CI, allow retries locally
  fullyParallel: true,
  forbidOnly: !!process.env.CI,
  retries: process.env.CI ? 2 : 0,
  workers: process.env.CI ? 1 : undefined,

  // Reporter
  reporter: process.env.CI
    ? [['html', { open: 'never' }], ['github']]
    : 'html',

  // Shared settings for all projects
  use: {
    baseURL: process.env.E2E_BASE_URL || 'http://localhost:3000',

    // Trace on failure (debugging gold)
    trace: 'on-first-retry',
    screenshot: 'only-on-failure',
    video: 'retain-on-failure',

    // Auth state (shared across all projects)
    storageState: 'e2e/.auth/user.json',
  },

  // Projects: responsive viewport matrix
  projects: [
    // Auth setup runs first (no storageState yet)
    {
      name: 'setup',
      testMatch: /.*\.setup\.ts/,
      use: {
        storageState: undefined, // Don't load state during setup
      },
    },

    // Desktop
    {
      name: 'desktop-chromium',
      dependencies: ['setup'],
      use: {
        ...devices['Desktop Chrome'],
        viewport: { width: 1280, height: 720 },
      },
    },

    // Mobile (touch)
    {
      name: 'mobile-chrome',
      dependencies: ['setup'],
      use: {
        ...devices['Pixel 5'],
        viewport: { width: 375, height: 667 },
        hasTouch: true,
      },
    },

    // Tablet (touch)
    {
      name: 'tablet',
      dependencies: ['setup'],
      use: {
        ...devices['iPad (gen 7)'],
        viewport: { width: 768, height: 1024 },
        hasTouch: true,
      },
    },
  ],

  // Auto-start dev server
  webServer: {
    command: 'npm run dev',
    url: 'http://localhost:3000',
    reuseExistingServer: !process.env.CI,
    timeout: 120_000,
  },
});

Read the full file on GitHub · 781 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. 4d ago First seen · 781 lines · 48 tokens per session scan A ccfe99878018

Subscribe to this mod's changes

playwright-responsive-audit-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 6,802 once invoked, about $0.0002 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 2026-09-03.