responsive-audit

responsive-audit is a command for coding agents from oalders/kitchen-sink. It costs 21 tokens per session (2,614 once invoked), scanned B, original, MIT.

A command that opens live web pages in a real browser at several screen widths and checks how their layouts respond. It uses Playwright MCP, a browser-control connection that must already be available.

In plain words
What is it for?
Use it to inspect one or more already-running URLs for layout problems on phones, tablets, and desktops, using browser navigation, resizing, JavaScript checks, and screenshots.
Why use it?
Static code review can miss problems that only appear when a page is rendered at different sizes. This reports visible responsive breakage without changing source files or creating tests.

Command

Part of the kitchen-sink plugin — 9 skills, 20 commands, 12 hooks shipped together

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/oalders/kitchen-sink/responsive-audit
Clone the repo
git clone --depth 1 https://github.com/oalders/kitchen-sink

Or install kitchen-sink, the plugin that ships this one along with the rest of its 9 skills, 20 commands, 12 hooks.

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 responsive-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/oalders/kitchen-sink/responsive-audit.svg)](https://agentmods.dev/commands/oalders/kitchen-sink/responsive-audit)
Your own site
<a href="https://agentmods.dev/commands/oalders/kitchen-sink/responsive-audit"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/responsive-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,614 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00021 $0.02614
Opus 5 $0.00010 $0.01307
Sonnet 5 $0.00004 $0.00523
Haiku 4.5 $0.00002 $0.00261

Measured 5d ago against content hash d4e7bd51bbbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

responsive-audit scanned grade B with 1 finding 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 5d 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

address (`169.254.0.0/16`, `[fd00:ec2::254]`, `metadata.google.internal`, etc.); for any host that

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

commands/responsive-audit.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Responsive Audit

Overview

Live-discovery responsive audit: drives the Playwright MCP to load one or more already-serving URLs at several viewport widths and reports responsive breakage that static review can't see. It fills the gap between /frontend-review (which reasons about a source diff and only recommends manual screenshots) and /playwright-review (which reviews existing test source) — neither actually drives a browser against a live page.

Discovery/reporting only: no test files are written, no source is modified, and no dev server is started.

Deliberate departure from the sibling review commands: the steps below drive the Playwright MCP tools directly (navigate, resize, evaluate JS, screenshot) rather than spawning a Task(general-purpose) subagent the way /frontend-review and /playwright-review do. There is a live browser session to hold, so the work stays in the caller's context and ## Output Format is a top-level section (no subagent to nest it in). This inconsistency is intentional.

Hard prerequisite: a working Playwright MCP must be available in the session. The command cannot probe tool availability up front — if the MCP is absent it simply fails on the first browser call. State the prerequisite before starting and surface that failure clearly rather than pretending to detect it. The target URL(s) must already be reachable.

When to Use

Use when:

  • You have a live, already-serving page and want to find responsive layout breakage across viewport widths (overflow, occluded controls, tiny touch targets / text).
  • You want measured evidence plus full-page screenshots, not just a reasoned guess from a diff.
  • A /frontend-review flagged possible responsive risk and you want to confirm it on the real page.

Don't use when:

  • The page isn't serving yet — this command does not start a dev server (start it yourself first).
  • You want a source-diff review (use /frontend-review) or a review of Playwright test source (use /playwright-review).
  • You want tests written, source auto-fixed, or issues/PRs filed — all explicit non-goals.

Read the full file on GitHub · 198 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. 5d ago First seen · 198 lines · 21 tokens per session scan B d4e7bd51bbbb

Subscribe to this mod's changes

responsive-audit is a command published in the GitHub repository oalders/kitchen-sink (4 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 2,614 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.