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/tdimino/claude-code-minoanWrote 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/commands/tdimino/claude-code-minoan/designer)<a href="https://agentmods.dev/commands/tdimino/claude-code-minoan/designer"><img src="https://agentmods.dev/badge/commands/tdimino/claude-code-minoan/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 | $0.00000 | $0.00732 |
| Opus 5 | $0.00000 | $0.00366 |
| Sonnet 5 | $0.00000 | $0.00146 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designer Mode
Use ultrathink for deep analysis.
Tool Preferences (per CLAUDE.md):
- Use Firecrawl over WebFetch for scraping design inspiration
- Use Exa over WebSearch for researching UI/UX patterns
- Use agent-browser for taking browser snapshots
Design Baselines (2025-2026)
Audit against these five reference points:
| Company | Learn From |
|---|---|
| Linear | Quality-as-strategy, keyboard-first, performance IS design, opinionated software, zero-bugs policy |
| Vercel | Web Interface Guidelines (read via minoan-frontend-design skill's references/vercel-web-interface-guidelines.md), Geist design system, design engineering |
| Stripe | Accessible color systems, light-mode-first premium, documentation-as-design, signature visual elements. Deep references: references/stripe-design-tokens.md, references/stripe-component-patterns.md, references/stripe-signature-techniques.md |
| Raycast | Progressive disclosure via action bar, search-centered architecture, Fast > Simple > Delightful priority |
| Resend | Code-first design (codebase IS the source of truth, not Figma), polish IN code, design as discipline anyone exercises |
| Mintlify | Dark-first dual-mode, AI-native docs (llms.txt + MCP + skill.md), progressive disclosure, semantic component naming, keyboard-first (Cmd+K), border-over-shadow elevation. Deep references: references/mintlify-design-tokens.md, references/mintlify-component-patterns.md, references/mintlify-signature-techniques.md |
Guiding Frameworks
- Novelty budget (Arc/Dia): Every product has a limited novelty budget. Innovate where it matters, use familiarity everywhere else. "Familiar, but elevated."
- Workbench over chatbox (Linear): For AI interfaces, build functional domain-specific tools with traditional UI, then complement with AI—don't default to chat.
- Quality creates gravity (Linear): Quality pulls people in rather than requiring push. Ship nothing half-baked.
- APCA contrast (Vercel): Use Accessible Perceptual Contrast Algorithm over WCAG 2 for more accurate perceptual contrast measurement.
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 · 51 lines · 0 tokens per session scan A 14f0421f5402
designer is a command published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 732 tokens. 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 2026-08-30.
Other commands, from other repositories
ui-evidence
Discover, configure, and run ui-evidence for before/after UI review in this repo.
bmad-ux
Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX".
ux-onboarding
Get familiar with a project's UX/design choices and patterns — a guided, part-by-part walkthrough that sends you to read the real code, checks your understanding with questions, and has you reimplement a small recent change.
dataviz
Define chart types, color encoding, and data display conventions.
icon-design
Find and select the right icon for a concept using Lucide, Heroicons, or Phosphor libraries.
design
Interview-driven design. Extracts requirements, writes spec, suggests new session.