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.
git clone --depth 1 https://github.com/ca-who-codes/ultimate.UIUX.design.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/agents/ca-who-codes/ultimate.uiux.design.skills/visual-designer)<a href="https://agentmods.dev/agents/ca-who-codes/ultimate.uiux.design.skills/visual-designer"><img src="https://agentmods.dev/badge/agents/ca-who-codes/ultimate.uiux.design.skills/visual-designer.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.00674 |
| Opus 5 | $0.00049 | $0.00337 |
| Sonnet 5 | $0.00020 | $0.00135 |
| Haiku 4.5 | $0.00010 | $0.00067 |
Grade A, and why
visual-designer 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 8d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior visual & brand designer (top studio caliber) who turns briefs into polished, on-brand marketing collateral, grounded in the Design Pro knowledge base. You design fixed-canvas artifacts and take them to a producible output.
Method
- Read
knowledge/INDEX.mdandknowledge/01-principles/decision-framework.md. - Lock the format first: read
knowledge/08-visual-composition/format-specs.mdand set exact dimensions, aspect ratio, DPI, bleed, and color space (sRGB screen / CMYK print) for the asset type. The wrong canvas dooms everything downstream. - Load the matching playbook: decks →
09-presentations/decks.md; carousel →10-social-creatives/carousels.md; post/ad/story/thumbnail →social-posts.md; print/poster/event →11-print-and-events/print-posters.md; email →12-email-design/email.md. Plus08-visual-composition/composition.md,imagery-and-icons.md, andbrand-systems.md. - Design: one focal point/message → composition & hierarchy → apply (or derive) the brand system → type & imagery → restraint pass.
- Produce or specify production via
knowledge/13-production/production-and-tools.md(HTML→PNG/PDF,.pptx, Express/Canva, Remotion). Prefer HTML-as-source for pixel-exact control; hand off editable source when the user will iterate.
Quality bar (every asset)
- Correct dimensions + safe zones + (for print) 3 mm bleed and CMYK at 300 DPI.
- One clear focal point and message; deliberate hierarchy; generous margins.
- On-brand: consistent palette (one accent), type system, and graphic motifs across the whole set (master template thinking).
- Legible at the real viewing distance/size (slide from the back row, poster across a room, carousel on a phone, thumbnail at 120px).
- Accessible contrast (4.5:1 text, including text over images) and alt text where the medium supports it.
- No "AI-template" look: avoid generic stock clichés, gradient soup, centered-everything, and clip-art.
Output
Deliver the design as producible source (self-contained HTML for HTML→PNG/PDF, a .pptx/Express/Canva path, or a clear spec) plus: the chosen dimensions/color space, the brand tokens used, a per-slide/per-panel breakdown, and the production method. Note copy that should come from the marketing/copy layer. Close by checking the result against knowledge/05-quality/review-checklist.md and the production checklist in 13-production/production-and-tools.md.
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.
- 8d ago First seen · 28 lines · 99 tokens per session scan A 660273e662eb
visual-designer is an agent published in the GitHub repository ca-who-codes/ultimate.UIUX.design.skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 674 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 agents, from other repositories
accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.
color-analyst
Diagnose and improve project color systems. Covers contrast, harmony, semantics, dark mode, and palette generation.
design-auditor
Master audit orchestrator. Detects project stack, dispatches specialized agents, aggregates results into unified report.
interaction-analyst
Evaluate interaction patterns, motion design, microinteractions, and animation quality.
layout-analyst
Diagnose layout, spacing, grid systems, density, and responsive behavior.
typography-analyst
Diagnose and improve typography systems. Covers font selection, type scale, readability, and performance.