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 agentmods add skills/zhpeng24/devkit/taste-skillnpx skills add zhpeng24/devkit --skill taste-skillgit clone --depth 1 https://github.com/zhpeng24/devkitWhat 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 | $0.00025 | $0.00646 |
| Opus 5 | $0.00013 | $0.00323 |
| Sonnet 5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
taste-skill 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 2d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Design Taste
Create a page-specific visual system, not a copied aesthetic. This skill owns web design direction and implementation quality; it does not own image-only deliverables or reference-to-code fidelity work.
Scope and routing
Use for expressive web pages and redesigns. Route pure image concepts to imagegen-frontend-web; route an approved screenshot, Figma frame, or reference-led implementation to image-to-code-skill. Do not use it to redesign product flows, native mobile UI, or to impose a framework.
Read before changing
- Inspect the brief: audience, page purpose, conversion/action, real content, success criteria, constraints, and source assets.
- For an existing UI, audit its routes, components, tokens, breakpoints, states, accessibility, and what users already recognize. Preserve what works before proposing a change.
- Identify the actual stack, installed dependencies, and local conventions. Keep the existing framework and component system unless the brief explicitly authorizes a change.
Existing design tokens, components, logos, imagery, and brand rules are authoritative. Do not replace them with a personal palette, substitute unlicensed assets, or invent claims, metrics, testimonials, or product data.
Define the visual grammar
Write a short direction before implementation: hierarchy, palette use, type scale, spacing rhythm, shape/radius, image treatment, density, and motion policy. Make those choices fit the audience and content; avoid generic centered-gradient heroes, uniform card grids, nested containers, decorative pills, and repeated boxed sections when they do not serve the page.
When the brief has no brand reference, derive the direction from the product, audience, content, and desired action. A familiar framework or a short deadline is not permission to migrate the existing stack or fall back to a generic “premium AI” recipe.
Use purposeful variation in composition while keeping a coherent system. Prefer real content and assets; label unknown content as a placeholder rather than presenting it as fact.
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.
- 2d ago First seen · 42 lines · 25 tokens per session scan A c53cc3418140
taste-skill is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 646 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.