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 pyros-projects/limitless --skill taste-distillergit clone --depth 1 https://github.com/pyros-projects/limitlessWrote 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/pyros-projects/limitless/taste-distiller)<a href="https://agentmods.dev/skills/pyros-projects/limitless/taste-distiller"><img src="https://agentmods.dev/badge/skills/pyros-projects/limitless/taste-distiller/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/pyros-projects/limitless/taste-distiller"><img src="https://agentmods.dev/badge/skills/pyros-projects/limitless/taste-distiller.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 | $0.00093 | $0.00774 |
| Opus 5 | $0.00046 | $0.00387 |
| Sonnet 5 | $0.00019 | $0.00155 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
taste-distiller 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 8d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste Distiller
Overview
This skill extracts the hidden governing rules behind something that feels unusually good.
It is not about copying surface features. It is about finding the deeper constitution: pacing, density, tone, restraint, naming, interaction cadence, and the small repeated choices that create the feeling.
When to Use
Use this when:
- the user says "I like this, but I can't explain why"
- a reference feels promising but still fuzzy
- the team needs stronger language for taste and direction
- someone wants to learn from a reference without making a cheap clone
Do not use this for generic design critique. This skill is for extracting the rules beneath the style.
What to Produce
Distill the reference into:
- governing rules
- recurring patterns
- what it consistently avoids
- how tone, spacing, density, or interaction create the effect
- a short "constitution of taste" summary
When useful, separate:
- direct observation
- inference
- likely consequences if these rules are broken
Working Loop
-
Gather the reference carefully. Look at a product, interface, writing sample, or codebase with enough surface area to reveal patterns.
-
Ignore first-order imitation. Do not start with colors, animations, or other obvious artifacts. Instead, inspect concrete dimensions such as:
- information density
- pacing between actions or beats
- what gets prominent placement versus what stays hidden
- how errors, empty states, and uncertainty are handled
- the ratio of explanation to assumption
- how often the system trusts the user versus over-guiding them
-
Extract rules. What does it consistently do? What does it avoid? Where does it spend attention? Where does it stay restrained?
-
Write the constitution. Turn the observed pattern into a reusable set of principles the user can carry into new work.
Suggested Output Shape
What gives this its feelHidden rules it seems to obeyWhat it consistently avoidsWhat would break the effectPortable lessons
What ships with it
2 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.
- 8d ago First seen · 98 lines · 93 tokens per session scan A a9272e50a293
taste-distiller is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 26d ago), licensed MIT. It adds 93 tokens to every session and 774 once invoked, about $0.0005 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
ux-spec
Generates UI/UX specifications with wireframes and design system. Creates UXSPEC.md and DESIGNSYSTEM.md from PRD and Architecture specs. Use when designing app interface and creating design system.
liquid-glass
Implement Liquid Glass design using .glassEffect() API for iOS/macOS 26+. Covers SwiftUI, AppKit, UIKit, and WidgetKit. Use when creating modern glass-based UI effects.
app-icon-generator
Generates an app icon for macOS or iOS — a fast CoreGraphics placeholder and/or flat layered source art to finish in Icon Composer (the Liquid Glass / iOS 26+ standard). Produces appearance variants (light/dark/tinted) and installs into the asset catalog. Use when the user wants to create, generate, iterate, or update…
onboarding-generator
Generates value-moment-first onboarding flows for iOS/macOS apps — the default architecture races a new user to the first felt experience of the app's promised outcome, branching on whether they can experience it right now or need to plan for later. The classic paged welcome-carousel tour is an explicit fallback for…
ui-prototyping
Explore multiple divergent UI directions for a screen as named Swift.
assistive-access
Assistive Access implementation for cognitive accessibility including simplified scenes, navigation icons, runtime detection, and design principles. Use when optimizing apps for Assistive Access mode.