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 phuonghx/aim-cli --skill taste-skillgit clone --depth 1 https://github.com/phuonghx/aim-cliWrote 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/phuonghx/aim-cli/taste-skill)<a href="https://agentmods.dev/skills/phuonghx/aim-cli/taste-skill"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/taste-skill/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/phuonghx/aim-cli/taste-skill"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/taste-skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00100 | $0.05995 |
| Opus 5.5 | $0.00040 | $0.02398 |
| Sonnet 5.5 | $0.00020 | $0.01199 |
| Haiku 4.5 | $0.00010 | $0.00600 |
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 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
taste-skill — A Filter Against Generic Frontend Output
Scope: landing pages, portfolios, marketing sites, and redesigns of those. Out of scope: dashboards, dense data tables, admin panels, multi-step wizards, native mobile. Nothing here is a default that fires on its own. Read the brief, then pull in only the rules that fit it.
How to use this skill
- Work through Step 1 — Read the brief and state a one-line direction.
- Set the three dials (Step 2). They gate every layout, motion, and density call below.
- Decide foundation: a real design system, or a hand-built aesthetic (Step 3 →
design-systems.mdfor the lookup table, install lines, and source links). - Build against the principles (Steps 4–7), avoiding the tells catalogued in
tells.md. - For scroll-driven and physics motion, follow the patterns in
motion-recipes.md. - Clear the pre-flight checklist (Step 8) before you ship a single line.
| Reference file | Open it when |
|---|---|
| design-systems.md | Choosing a foundation; need official package names, install lines, or canonical docs |
| tells.md | Auditing output for machine-generated signatures; the full ban list |
| motion-recipes.md | Implementing sticky-stack, horizontal-pan, or scroll-reveal motion |
Step 1 — Read the brief before anything else
Most weak design output comes from jumping straight to a house aesthetic instead of listening. Resist that.
Signals to extract:
- Surface type — SaaS / consumer / agency / event landing; developer / designer / studio portfolio; redesign (keep the brand vs. replace it); editorial or blog.
- Mood language the person actually used — "calm", "minimal", "premium", "playful", "brutalist", "editorial", "dark/technical", and so on.
- References — links, screenshots, named products, competitors.
- Who reads it — a procurement committee, a design-literate shopper, and a recruiter skimming a portfolio each want a different language. Their context picks the aesthetic, not your preference.
- Existing brand material — logo, colors, type, photography. On a redesign these are inputs, not suggestions (Step 7).
- Hard constraints — accessibility-critical, regulated, public-sector, children's products, trust-first commerce. These override any aesthetic instinct.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 260 lines · 100 tokens per session scan A c3b72467dba4
taste-skill is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 5,995 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
design-critique
Use this skill to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states, accessibility and copy, ending in a ranked fix list. Triggers: user says "review the design", "critique this UI", "why does this…
design-craft
Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique. Use for new screens, landing pages, redesigns, typography/layout work, or UI that feels generic or AI-generated. For small fixes, preserve the existing design without starting a…
von-restorff-effect
Apply the Von Restorff Effect — the element that differs from its neighbours is the one remembered. Use when a single action must dominate. For overall ordering rather than single-element emphasis, use visual-hierarchy.
handoff-spec
Write the implementation handoff — measurements, behaviours, assets, states, and edge cases. Use when engineering picks up the work. For verifying the result afterwards use design-qa-checklist; for reusable library components use component-spec (design-systems).
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
readable-measure
Set line length and measure for comfortable reading across type sizes and breakpoints. Use when tuning body text. Covers measure only — for the full size and weight scale, use typography-scale.