tune

tune is a command for coding agents from koolamusic/claudefiles. It costs 55 tokens per session (986 once invoked), scanned A, original, MIT.

A command for changing a design’s visual intensity: making it more distinctive, more restrained, or more colorful. It supports bolder, quieter, and colorize modes, plus an option to recommend a direction.

In plain words
What is it for?
Use it to increase visual impact, tone down an overbearing interface, add color to a mostly monochrome design, or assess which adjustment fits best.
Why use it?
It helps adjust a design that feels too plain, too aggressive, or too monochromatic while keeping the intended audience and brand tone in view.

Command

Part of the ux plugin — 1 skill, 6 commands shipped together

Install

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.

agentmods
npx agentmods add commands/koolamusic/claudefiles/tune
Clone the repo
git clone --depth 1 https://github.com/koolamusic/claudefiles

Or install ux, the plugin that ships this one along with the rest of its 1 skill, 6 commands.

Wrote 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.

agentmods badge for tune

README.md
[![agentmods](https://agentmods.dev/badge/commands/koolamusic/claudefiles/tune.svg)](https://agentmods.dev/commands/koolamusic/claudefiles/tune)
Your own site
<a href="https://agentmods.dev/commands/koolamusic/claudefiles/tune"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/tune.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 986 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00055 $0.00986
Opus 5 $0.00028 $0.00493
Sonnet 5 $0.00011 $0.00197
Haiku 4.5 $0.00006 $0.00099

Measured 4d ago against content hash c00f04b0939a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tune 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 4d 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.

plugins/ux/commands/tune.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adjust the visual intensity dial. Three directions, one skill.

First: Use the ux skill for design principles and anti-patterns.

MANDATORY PREPARATION

Gather context: target audience, brand personality/tone, and existing design direction. If you can't infer these confidently from the codebase, STOP and ask via AskUserQuestion. Guessing leads to generic AI slop.

Pick the direction

$ARGUMENTS determines the mode:

  • bolder — Amplify safe or boring designs. More impact, more personality, more drama.
  • quieter — Tone down aggressive designs. More refined, more sophisticated, easier on the eyes.
  • colorize — Add strategic color to monochromatic designs. More warmth, more meaning, more engagement.
  • empty — Assess the interface and recommend which direction.

Bolder

Increase visual impact while maintaining usability. "Bolder" means distinctive and confident, not chaotic.

WARNING: AI slop trap — when making things "bolder," don't default to cyan/purple gradients, glassmorphism, neon accents, or gradient text. These are generic, not bold.

  • Typography: Replace generic fonts with distinctive choices. Extreme scale jumps (3-5x, not 1.5x). Pair 900 weights with 200 weights.
  • Color: Increase saturation. Bold palette with unexpected combinations. Let one color own 60%. Tinted neutrals.
  • Space: Extreme scale jumps. Break the grid intentionally. Asymmetric layouts. Generous whitespace (100-200px gaps).
  • Effects: Dramatic shadows for elevation. Texture and depth (grain, halftone, duotone). Custom decorative elements.
  • Motion: Staggered entrance choreography. Scroll-triggered effects. Satisfying hover feedback. Use ease-out-quart/quint/expo, never bounce.
  • Composition: Clear focal point with dramatic treatment. Full-bleed elements. Unexpected proportions (70/30, 80/20).

Quieter

Reduce visual intensity while maintaining character. "Quieter" means refined and sophisticated, not boring.

  • Color: Reduce saturation to 70-85%. Soften palette to muted tones. Fewer colors, more neutrals. Tinted grays, never pure gray.
  • Weight: Reduce font weights (900→600, 700→500). Decrease sizes where appropriate. Use space and weight for hierarchy instead of color.
  • Simplification: Remove decorative gradients, shadows, patterns that don't serve purpose. Flatten layering. Clean up blur effects and glows.
  • Motion: Shorter distances (10-20px not 40px). Remove decorative animations. Keep only functional motion. Reduce or remove if not clearly purposeful.
  • Composition: Smaller scale jumps for calmer feel. Bring elements back to grid. Consistent spacing rhythm.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 4d ago First seen · 62 lines · 55 tokens per session scan A c00f04b0939a

Subscribe to this mod's changes

tune is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 986 once invoked, about $0.0003 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 2026-08-30.