A command that helps diagnose CSS problems, including layout, responsive design, browser compatibility, specificity, and the cascade—the rules that decide which style wins.

Use it when Flexbox, Grid, media queries, positioning, stacking, spacing, or styles that are being overridden do not behave as expected.

It replaces trial-and-error styling with questions and checks that narrow down why an element is misplaced, overflowing, hidden, or using the wrong appearance.

css-debug — Command for Claude Code by andronics/claude-plugin-css-pro

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.

Clone the repo

git clone --depth 1 https://github.com/andronics/claude-plugin-css-pro

Made for: Claude Code.

Or install css-pro, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 7 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/andronics/claude-plugin-css-pro/css-debug/github.svg)](https://agentmods.dev/commands/andronics/claude-plugin-css-pro/css-debug)

Your own site

<a href="https://agentmods.dev/commands/andronics/claude-plugin-css-pro/css-debug"><img src="https://agentmods.dev/badge/commands/andronics/claude-plugin-css-pro/css-debug/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/andronics/claude-plugin-css-pro/css-debug"><img src="https://agentmods.dev/badge/commands/andronics/claude-plugin-css-pro/css-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,936 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.01936
Opus 5.5	$0.00005	$0.00774
Sonnet 5.5	$0.00003	$0.00387
Haiku 4.5	$0.00001	$0.00194

Measured 1mo ago against content hash d9b83a057c5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

css-debug 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 1mo 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.

commands/css-debug.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CSS Debugging Assistant

I'll help you debug CSS issues systematically using proven techniques and tools.

What's the Problem?

Describe your CSS issue: $ARGUMENTS

If no description provided, I'll ask diagnostic questions.

Common CSS Issues I Can Debug

1. Layout Problems

Flexbox not working
Grid items overflowing
Collapsed container height
Centering not working
Unexpected wrapping

2. Specificity Conflicts

Styles not applying
Rules being overridden
!important issues
Cascade problems

3. Visual Bugs

Elements overlapping
Z-index not working
Positioning issues
Gap/spacing problems

4. Responsive Issues

Media queries not triggering
Mobile layout broken
Container queries not working

5. Browser Compatibility

Works in Chrome, broken in Safari
Vendor prefix missing
Feature not supported

Debugging Process

Step 1: Information Gathering

I'll ask:

What's the expected behavior?
What's actually happening?
When does it occur? (viewport size, browser, etc.)
Which element(s) are affected?
Can you share the CSS code?

Step 2: Systematic Analysis

I'll check:

✓ CSS syntax validity
✓ Selector specificity
✓ Cascade order
✓ Box model values
✓ Display properties
✓ Positioning context
✓ Z-index stacking
✓ Browser DevTools computed values

Step 3: Root Cause Identification

Using elimination:

Remove styles until problem disappears
Add back one at a time
Identify the specific rule causing the issue
Understand why it's causing the problem

Step 4: Solution & Fix

Provide:

Root cause explanation
Specific fix with code
Why the fix works
How to prevent in future

Example Debugging Sessions

Example 1: "My flexbox isn't working!"

Your code:

.container {
  display: flex;
}

.item {
  width: 100%;
}

Problem: Items not growing/shrinking as expected

Analysis:

width: 100% prevents flex-grow from working
Flex items have min-width: auto by default
Content width determines minimum size

Read the full file on GitHub · 391 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.

1mo ago First seen · 391 lines · 13 tokens per session scan A d9b83a057c5a

Subscribe to this mod's changes

css-debug is a command published in the GitHub repository andronics/claude-plugin-css-pro (3 stars, last pushed 12mo ago), licensed MIT. It adds 13 tokens to every session and 1,936 once invoked, about $0.0001 per session on Opus 5.5. 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.

CSS and styling Debugging Frontend

ui-bug.template

This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.

evan043/claude-cli-advanced-starter-pack · 0 tokens

ui-fix.template

This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.

evan043/claude-cli-advanced-starter-pack · 0 tokens

rust:tauri:exec-js

Execute JavaScript code in the Tauri app's webview context.

qdhenry/Claude-Command-Suite · 21 tokens

debug-ui

A front-end debugging assistant that reviews an interface as both a visual designer and an engineer. It translates vague design feedback into concrete changes to layout, colour, spacing, typography, hierarchy, and animation, while recording work in `.debug` files.

samqin123/Claude_skill_pool · 31 tokens

doctor

Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…

doncheli/don-cheli-sdd · 76 tokens

http-service

Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.

MadAppGang/magus · 27 tokens