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 hamzaPixl/pixl-ai --skill design-contextgit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote 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/hamzapixl/pixl-ai/design-context)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/design-context"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/design-context/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/hamzapixl/pixl-ai/design-context"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/design-context.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 | $0.00073 | $0.01630 |
| Opus 5 | $0.00036 | $0.00815 |
| Sonnet 5 | $0.00015 | $0.00326 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
design-context 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Captures the brand, audience, and aesthetic constraints that every subsequent design decision depends on. Without this file, design skills (/design-critique, /design-variants, /website-theme, /frontend-design) work blind and produce generic AI-slop output. Run once per project; re-run when the brand pivots.
The output file .design-context.md is read by:
/design-critique— scores originality against declared voice/design-variants— generates directions aligned with audience/website-theme— selects palette and font pairing/frontend-design— injects brand voice into copy and component style/content-marketing— enforces voice across written content
Required References
Read before starting:
references/frontend/design/design-context-protocol.md— the canonical schema and examplesreferences/frontend/design/anti-patterns.md— so you can prompt for anti-references intelligently
Step 1: Explore the Codebase
Before asking questions, gather signals from the project:
# Existing brand hints
ls public/ | grep -Ei "logo|brand|favicon"
grep -rEn "primary|brand|accent" tailwind.config.* src/styles 2>/dev/null | head -20
# Existing copy for tone inference
find . -name "*.tsx" -path "*/landing/*" -o -path "*/marketing/*" 2>/dev/null | head -5
grep -rEn "<h1|<h2" src/app src/pages 2>/dev/null | head -10
# Package.json name/description
cat package.json | grep -E '"name"|"description"' 2>/dev/null
# Check if .design-context.md already exists
test -f .design-context.md && echo "EXISTS" || echo "NONE"
Summarize findings as "what I already know" before asking questions. If .design-context.md exists and --force was not passed, offer to review/update instead of overwrite.
Step 2: Interactive Q&A
Ask 5-7 questions. Use AskUserQuestion if available, else plain prompts. Keep each question short and specific — no walls of text.
Q1. Audience
"Who is the primary user? Describe in one sentence (role, context, what they care about)."
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 · 164 lines · 73 tokens per session scan A 8bf1b5858810
design-context is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 1,630 once invoked, about $0.0004 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.