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 skillmds/skillmd --skill playstation-design-analysisgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/playstation-design-analysis)<a href="https://agentmods.dev/skills/skillmds/skillmd/playstation-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/playstation-design-analysis/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/skillmds/skillmd/playstation-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/playstation-design-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00209 | $0.10256 |
| Opus 5.5 | $0.00084 | $0.04102 |
| Sonnet 5 | $0.00042 | $0.02051 |
| Haiku 4.5 | $0.00021 | $0.01026 |
Grade A, and why
PlayStation-design-analysis 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.
How it starts
The opening of the file, as written. The whole thing — 662 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
PlayStation's marketing system reads like a console launch trailer scrolling past the viewer in chapters. Each section is a full-bleed band — pure black {colors.canvas-dark}, true white {colors.canvas-light}, or PlayStation Blue {colors.primary} — and each chapter owns one editorial moment: hero console photography, a games-coming-soon strip, the PlayStation Plus tier banner, the "30 Years of PlayStation" anniversary band, the news strip from the PlayStation Blog. There is no decorative chrome between chapters; the section background change IS the divider. Sections stack at {spacing.section} (96px) rhythm with the next band's color taking over the page edge-to-edge.
The system has two distinct surface modes that alternate down the page: a dark canvas mode for editorial product moments (hero, "ON PLAYSTATION" band, marathon game pages) and a light canvas mode for utility surfaces (PS5 games listing, support pages, news index). Both modes use the same chrome vocabulary — fully-rounded {rounded.full} pill buttons, 8px-radius {rounded.md} cards, the proprietary PlayStation SST face — only the surface and on-surface colors change. The third surface mode is the PlayStation Blue band ({colors.primary} — #0070d1) reserved for the highest-priority moments: the Marathon launch CTA strip, the footer, and any "Action Required" banner.
The typography is the system's most distinctive choice. PlayStation SST renders display headlines at weight 300 (light) — unusual for a gaming brand that could easily reach for bold geometric display faces. The light weight gives the chrome an airy, almost editorial quality that lets the imagery speak; copy is information rather than decoration. Heading sizes drop in tight increments (54 → 44 → 35 → 28 → 22 → 18) and body settles at 18px with 1.5 line-height for comfortable long-form reading on support and games pages.
Key Characteristics:
- Three-canvas chapter system:
{colors.canvas-dark}(black),{colors.canvas-light}(white),{colors.primary}(PlayStation Blue) alternating down the page - PlayStation Blue (
{colors.primary}—#0070d1) is the universal primary CTA — fully-rounded pill at{rounded.full}(9999px) - Commerce orange (
{colors.commerce}—#d53b00) is the secondary CTA reserved for "Buy now" / "Pre-order" / store actions - PlayStation SST display tier renders at weight 300 with -0.1px to +0.4px tracking — the brand's signature airy editorial voice
- 8px-radius (
{rounded.md}) for product cards and feature panels; 4px-radius ({rounded.sm}) for inputs; pills ({rounded.full}) for every CTA - Game tiles, console renders, and PS Plus tier illustrations occupy 60-90% of each section — imagery does the storytelling
- Color-block page rhythm (one observed band sequence): dark hero → light console showcase → dark "Great PS4 & PS5 games" rail → light "Discover PlayStation Plus" tier band → light "30 years of PlayStation" callout → dark "ON PLAYSTATION" band → light news strip → blue footer
What ships with it
1 file 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.
- 4d ago First seen · 662 lines · 209 tokens per session scan A 49f82a062b12
PlayStation-design-analysis is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 209 tokens to every session and 10,256 once invoked, about $0.0008 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 2026-09-19.
Other skills, from other repositories
get-context
Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
antv-infographic
Create beautiful infographics based on given text content. Use when users request to create infographics.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…