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 nWave-ai/nWave --skill nw-taste-evaluationgit clone --depth 1 https://github.com/nWave-ai/nWaveWrote 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/nwave-ai/nwave/nw-taste-evaluation)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-taste-evaluation"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-taste-evaluation/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/nwave-ai/nwave/nw-taste-evaluation"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-taste-evaluation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.01680 |
| Opus 5.5 | $0.00016 | $0.00672 |
| Sonnet 5.5 | $0.00008 | $0.00336 |
| Haiku 4.5 | $0.00004 | $0.00168 |
Grade A, and why
nw-taste-evaluation 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 1mo 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste Evaluation
The Taste Problem
Design taste cannot remain tacit. In the age of AI-assisted product development, taste must be encoded as explicit evaluation criteria — operable, auditable, reproducible. Gut feel is the source from which taste criteria are derived; the weighted matrix is the mechanism that makes taste operational.
Key insight: Taste is a fourth lens applied after DVF, not instead of it. An option can be Desirable, Feasible, and Viable — and still fail taste by adding three new concepts to the user's mental model when zero would suffice.
Phase 1: DVF Filter — Primary Triage
Apply IDEO's three-lens filter first. Any option failing two or more lenses is eliminated before taste scoring.
| Lens | Question | Score 1-5 |
|---|---|---|
| Desirability | Do users want this? Does it address the validated job? | 1 = no evidence of want, 5 = clear expressed need |
| Feasibility | Can we build it with available skills/tools/time? | 1 = requires unavailable technology, 5 = straightforward to build |
| Viability | Does it support a sustainable business model? | 1 = no path to revenue/retention, 5 = clear value capture |
Elimination threshold: DVF total < 6 → option eliminated before taste scoring.
Phase 2: Taste Criteria — Four Apple/Jobs Principles
Apply these four criteria to all options that pass DVF. Each is scored 1-5 with explicit rubrics — no subjective override.
Criterion T1: Subtraction
"Innovation is saying no to a thousand things." — Jobs, 1997
Test: Could this option achieve its goal with one fewer feature/concept/step?
| Score | Description |
|---|---|
| 5 | Nothing can be removed without breaking the core value |
| 4 | One minor element could be removed; core intact |
| 3 | Multiple removable elements, value unclear without them |
| 2 | Clearly bloated; several non-essential parts |
| 1 | Feature accumulation masquerading as a product |
Criterion T2: Concept Count
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.
- 1mo ago First seen · 169 lines · 41 tokens per session scan A c8bdfd3ee5a5
nw-taste-evaluation is a skill published in the GitHub repository nWave-ai/nWave (620 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,680 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-06.
Other skills, from other repositories
tdd
Use this skill to practice test-driven development — writing tests before implementation, using tests to drive design, and validating implementation against pre-written tests. Activates when implementing new functionality, refactoring code, or fixing bugs where regression coverage is needed.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
moai-domain-frontend
Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.
craft-studio
Router for the ArtCraft craft apps (PhotoCraft, VectorCraft, FilmCraft, LightCraft, PdfCraft, EffectCraft, DesignCraft, FigCraft, WordCraft, SoundCraft, DeckCraft, CADCraft, GridCraft) driven headless via pi-craft. Use to choose which app fits a job and run the discover-execute-save-verify loop - "which craft app…
tailwind-shadcn
Tailwind CSS utility patterns with shadcn/ui component usage, theming via CSS variables, and responsive design. Use when styling components, installing shadcn components, implementing dark mode, or creating consistent design systems.