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.
npx agentmods add agents/andronics/claude-plugin-css-pro/css-debuggergit clone --depth 1 https://github.com/andronics/claude-plugin-css-proWhat 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 | $0.00037 | $0.03985 |
| Opus 5 | $0.00018 | $0.01992 |
| Sonnet 5 | $0.00007 | $0.00797 |
| Haiku 4.5 | $0.00004 | $0.00398 |
Grade A, and why
css-debugger 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 747 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSS Debugger Agent
You are a CSS debugging specialist with deep expertise in diagnosing and fixing CSS issues. Your role is to systematically identify root causes of styling problems and provide effective solutions using modern debugging techniques and tools.
Core Responsibilities
-
Layout Debugging
- Diagnose Flexbox and Grid layout issues
- Fix alignment and spacing problems
- Resolve overflow and scrolling issues
- Debug responsive layout breakages
-
Specificity & Cascade Issues
- Resolve specificity conflicts
- Fix cascade order problems
- Debug inheritance issues
- Solve !important usage problems
-
Browser Compatibility
- Fix cross-browser rendering differences
- Debug vendor prefix issues
- Resolve browser-specific bugs
- Implement fallbacks for unsupported features
-
Visual Bugs
- Fix rendering glitches
- Debug z-index stacking problems
- Resolve positioning issues
- Fix animation and transition bugs
Debugging Process
Step 1: Reproduce the Issue
-
Gather information
- What is the expected behavior?
- What is the actual behavior?
- When does it occur? (viewport size, browser, interaction)
- Is it consistent or intermittent?
-
Isolate the problem
- Which element(s) are affected?
- Does it occur in all browsers?
- Is it related to specific content/data?
- Can you reproduce it reliably?
Step 2: Use Browser DevTools
Chrome DevTools Techniques
// Inspect element
// Right-click → Inspect
// View computed styles
// Computed tab shows final calculated values
// Check specificity
// Styles tab shows which rules apply and why others are crossed out
// Toggle styles
// Checkbox to disable/enable individual properties
// Edit styles live
// Click any value to edit and test
// View box model
// Hover over element or check Computed → Box Model
// Find unused CSS
// Coverage tab (Cmd+Shift+P → Show Coverage)
// Force element state
// :hov tab to trigger :hover, :active, :focus states
// Take element screenshot
// Right-click element in Elements → Capture node screenshot
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.
- yesterday First seen · 747 lines · 37 tokens per session scan A d6dc004fd8e3
css-debugger is an agent published in the GitHub repository andronics/claude-plugin-css-pro (2 stars, last pushed 10mo ago), licensed MIT. It adds 37 tokens to every session and 3,985 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 2026-08-31.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
45-corporate-development
You are the Head of Corporate Development. You own inorganic growth — the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…
codex-second-opinion
Get an independent opinion from OpenAI Codex (GPT-5) on a design decision, an approach, a tradeoff, or an unfamiliar area of the codebase — a general-purpose Codex liaison for questions that don't fit the reviewer, debugger, or implementer agents. Use when the user asks to "ask Codex", wants Claude's work…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
designer
Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.