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 sssstwee/tastedistill --skill designgit clone --depth 1 https://github.com/sssstwee/tastedistillWrote 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/sssstwee/tastedistill/design)<a href="https://agentmods.dev/skills/sssstwee/tastedistill/design"><img src="https://agentmods.dev/badge/skills/sssstwee/tastedistill/design.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 | $0.00053 | $0.00413 |
| Opus 5 | $0.00026 | $0.00206 |
| Sonnet 5 | $0.00011 | $0.00083 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
design 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- tasted-design — 95% identical, 2 lines differ
What it actually says
Design: Make The Interface Intentional
Use this skill for UI and product-facing work.
Prefix your first response line with ⚗️ inline, not as its own paragraph.
Before the workflow, apply ../../shared-rules/personalization.md for explicit TasteD/TasteDistill invocations.
Apply ../../shared-rules/runtime-hygiene.md when design verification uses browser screenshots, snapshots, local servers, or generated artifacts.
Outcome Contract
- Outcome: a usable interface direction or concrete UI change with clear interaction behavior.
- Done when: layout, information hierarchy, states, responsiveness, and visual consistency have been considered and verified when possible.
- Evidence: screenshots, rendered UI, existing components, design tokens, accessibility constraints, and user goals.
Workflow
- Identify the user workflow and the primary decision on the screen.
- Inspect existing UI patterns, tokens, components, and states before adding new ones.
- Choose a visual direction in concrete terms, not generic adjectives.
- Design the required states: empty, loading, error, disabled, selected, hover, focus, and success.
- Implement with the existing design system where available.
- Verify in a real browser or rendered output when the task changes visible UI.
Product Principles
- Prefer clear hierarchy over decoration.
- Make high-frequency tools compact and scannable.
- Keep controls predictable and stateful.
- Disabled controls should explain their dependency when possible.
- Do not introduce a second visual system unless the project requires it.
Do Not
- Ship UI based only on compilation.
- Add decorative surfaces that do not support the workflow.
- Hide unavailable actions when disabled-with-explanation is clearer.
- Ignore responsive text fitting and layout overlap.
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.
- 7d ago First seen · 44 lines · 53 tokens per session scan A ccc9c609d252
design is a skill published in the GitHub repository sssstwee/tastedistill (2 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 413 once invoked, about $0.0003 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
design-is
Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design…
frontend-design
A design and coding guide for building distinctive web interfaces, including pages, dashboards, landing pages, and reusable components.
repo-visualiser
Render a repository as a rotatable, animated isometric system map — varied 3D buildings on a grid, with live payload pulses tracing real control and data paths, plus a legend and an explainer panel. Use when the user wants a repo's infrastructure seen as an isometric or 3D city map. Not for a knowledge-graph dashboard…
design
Use for UI, UX, visual hierarchy, frontend-design judgment, references, redesigns, and design critique when the user's Emulo taste should guide the task. Do not use for unrelated execution or marketing/social writing alone.
ui-ux-pro-max
UI/UX design intelligence with 50+ styles, 161 palettes, 57 font pairings, 99 UX guidelines, and 25 chart types. Searchable database with priority-based recommendations for web and mobile.
design-explore
Explore 2-4 design options with pros/cons/criteria matrix before writing code. Use for L3-L4 tasks (refactors, architecture, new subsystems). Pairs with savedecision MCP tool.