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 Kevin-Liu-01/Agent-Machines --skill taste-skills-playbookgit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/taste-skills-playbook)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/taste-skills-playbook"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/taste-skills-playbook/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/kevin-liu-01/agent-machines/taste-skills-playbook"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/taste-skills-playbook.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 | $0.00085 | $0.00728 |
| Opus 5 | $0.00043 | $0.00364 |
| Sonnet 5 | $0.00017 | $0.00146 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
taste-skills-playbook 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 9d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste Skills Playbook
Routing layer for the 13 taste-* skills. Pick one visual-style skill per project, layer universal enforcement and workflow modifiers on top.
Decision Tree
| Task | Primary skill | Layer with |
|---|---|---|
| "Build a landing page" (no style hint) | taste-core |
taste-output if long file expected |
| "Premium SaaS landing page, Linear-tier" | taste-soft |
taste-imagegen-web if visual-first |
| "Notion-style document UI", "workspace clone" | taste-minimalist |
— |
| "Data dashboard", "terminal aesthetic" | taste-brutalist |
— |
| "Image-first design then implementation" | taste-image-to-code |
+ style fork |
| "Generate website reference images" | taste-imagegen-web |
feeds into taste-image-to-code |
| "Generate mobile screens" | taste-imagegen-mobile |
— |
| "Brand kit", "logo concepts" | taste-brandkit |
— |
| "Audit this site", "redesign without rewriting" | taste-redesign |
+ style fork for direction |
| "DESIGN.md for Google Stitch" | taste-stitch |
— |
| Long output (multi-component) | taste-output |
layered on every other skill |
The One Style Per Project Rule
Never mix visual-style skills (soft/minimalist/brutalist/gpt) in the same project. They are archetypes, not feature sets. Workflow modifiers (image-to-code, imagegen-*, redesign, output) compose freely on top.
Variance Dials
Three dials drive every taste skill. Defaults 8/6/4.
| Project | Variance | Motion | Density |
|---|---|---|---|
| Marketing landing page | 8 | 7 | 3 |
| Premium SaaS app | 6 | 5 | 5 |
| Data dashboard | 4 | 3 | 8 |
| Documentation site | 4 | 2 | 4 |
| Portfolio | 9 | 7 | 3 |
Skill Graph
ALWAYS-ON: taste-enforcement.mdc (variance dials, banned patterns)
BASELINE: taste-core + frontend-design-taste
STYLE: taste-soft | taste-minimalist | taste-brutalist | taste-gpt (pick ONE)
WORKFLOW: taste-image-to-code, taste-imagegen-web, taste-imagegen-mobile,
taste-brandkit, taste-redesign, taste-stitch, taste-output (layer freely)
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.
- 9d ago First seen · 59 lines · 85 tokens per session scan A e3d1336e46b7
taste-skills-playbook is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 728 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
omarchy-theme-maker
Use when an Omarchy desktop should be themed from a wallpaper or photo by deriving a contrast-checked colors.toml palette from the image, installing it as the theme background, and applying it with omarchy theme set.
kernelcad-authoring
Author or modify kernelCAD models in TypeScript. Scripts live in .kcad.ts files; the kernelCAD CLI (kernelcad evaluate and kernelcad export stl|step|dxf|3mf|glb -o ) executes them via an OpenCASCADE WASM kernel.
maya-primitives
Authoring stage — schema-validated quick path for creating polygon primitives and editing transforms. Use for predictable, agent-driven primitive creation; the parameters are validated by inputSchema and the results carry structured object names. For complex mesh editing use maya-mesh-ops, for materials use…
kernelcad-trace-from-image
Convert pixel-space features from a reference photo into normalized [0,1] waypoints, then into mm coordinates feedable to path().spline / path().nurbsSegment. Uses the tracefromimage MCP tool. Load when your blockout is in place and the next step is an organic-curve outline (eyewear brow, ergonomic handle, sneaker…
holix-cron
Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).