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 skills add slamb2k/mad-skills --skill pixel-pushergit clone --depth 1 https://github.com/slamb2k/mad-skillsWrote 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.
[](https://agentmods.dev/skills/slamb2k/mad-skills/pixel-pusher)<a href="https://agentmods.dev/skills/slamb2k/mad-skills/pixel-pusher"><img src="https://agentmods.dev/badge/skills/slamb2k/mad-skills/pixel-pusher/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.
<a href="https://agentmods.dev/skills/slamb2k/mad-skills/pixel-pusher"><img src="https://agentmods.dev/badge/skills/slamb2k/mad-skills/pixel-pusher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.02399 |
| Opus 5 | $0.00051 | $0.01200 |
| Sonnet 5 | $0.00020 | $0.00480 |
| Haiku 4.5 | $0.00010 | $0.00240 |
Grade A, and why
pixel-pusher 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pixel Pusher Design System
Professional UI/UX design skill that transforms vague requirements into polished web interfaces through systematic design thinking and iterative refinement.
Design Philosophy
Never accept vague design requests. Transform "make it beautiful" into concrete design systems with specific colors, typography, spacing, and component patterns. Work systematically through discovery, design system creation, mockup generation, and iterative refinement.
Multi-Stage Design Process
Stage 1: Discovery & Requirements Gathering
Begin by understanding what the user wants to create and gathering design inspiration.
Initial questions to ask if not provided:
- Purpose: What is this interface for? (landing page, web app, dashboard, portfolio, etc.)
- Audience: Who will use this? (consumers, professionals, internal team, etc.)
- Key features: What are the 3-5 most important elements? (hero section, forms, data visualization, etc.)
- Inspiration: Do you have reference designs? (URLs, screenshots, or describe style preferences)
- Brand elements: Do you have existing brand colors, fonts, or logo?
- Technical constraints: Any specific frameworks or technologies? (React, Vue, vanilla HTML, etc.)
Critical assets to request:
- Screenshots or URLs of designs they like
- Existing brand guidelines or assets
- Content examples (copy, images, data)
- Specific interactions or animations they envision
Do not proceed to design system creation until you have:
- Clear understanding of purpose and audience
- At least 2-3 reference designs (screenshots or URLs)
- Key features and content requirements
- Any brand constraints
Stage 2: Design System Extraction
Extract a comprehensive JSON design system from reference materials. If user provides URLs, fetch them first to analyze the design patterns.
For each reference, analyze and extract:
- Color palette - All colors with hex values, usage context (primary, secondary, accent, surface, text)
- Typography - Font families, sizes, weights, line heights for each text level
- Spacing system - Margin/padding patterns (identify the base unit: 4px, 8px, etc.)
- Component styles - Buttons, cards, inputs, navigation patterns
- Layout patterns - Grid systems, container widths, breakpoints
- Shadows & effects - Elevation values, gradients, borders
- Interaction patterns - Hover states, transitions, animations
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 313 lines · 101 tokens per session scan A d7ea417b505f
pixel-pusher is a skill published in the GitHub repository slamb2k/mad-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 101 tokens to every session and 2,399 once invoked, about $0.0005 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.