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 agentmods add commands/koolamusic/claudefiles/polishgit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/commands/koolamusic/claudefiles/polish)<a href="https://agentmods.dev/commands/koolamusic/claudefiles/polish"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/polish.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00956 |
| Opus 5 | $0.00016 | $0.00478 |
| Sonnet 5 | $0.00006 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
polish 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 5d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meticulous final pass — catch the details that separate good from great. Includes design system normalization and complexity reduction.
First: Use the ux skill for design principles and anti-patterns.
CRITICAL: Polish is the last step. Don't polish work that isn't functionally complete.
Pre-Polish Assessment
- Is it functionally complete?
- Does a design system exist? (Search for design system docs, component libraries, style guides)
- What's the quality bar? (MVP vs flagship)
- Where are the obvious inconsistencies?
Design System Normalization
If a design system exists:
- Replace custom implementations with design system components
- Replace hard-coded colors/spacing/typography with design tokens
- Match animation timing, easing, and interaction patterns to established conventions
- Match responsive breakpoints and patterns
- Match progressive disclosure and information hierarchy
If deviations from the design system exist, fix them. If the design system doesn't cover a pattern, note it for extraction (use /ux:reshape extract).
Complexity Reduction
Before polishing, simplify:
- One primary action per view — reduce competing buttons and CTAs
- Progressive disclosure — hide complexity behind clear entry points
- Remove redundancy — if it's said elsewhere, don't repeat it
- Flatten structure — reduce nesting, remove unnecessary containers and cards
- Shorter copy — cut every sentence in half, then do it again
- Fewer colors, fonts, sizes — use the minimum that serves hierarchy
- Smart defaults — make common choices automatic
Polish Systematically
Visual Alignment & Spacing
- Everything lines up to grid. Use spacing scale consistently (no random 13px gaps).
- Optical alignment for visual weight (icons may need offset).
- Responsive consistency at all breakpoints.
Typography
- Same elements use same sizes/weights throughout
- Line length 45-75 chars for body text
- No widows/orphans, appropriate hyphenation
- Font loading — no FOUT/FOIT flashes
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.
- 5d ago First seen · 121 lines · 32 tokens per session scan A 386fb61676b8
polish is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 956 once invoked, about $0.0002 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.
Other commands, from other repositories
combo
Command "combo" from jiushiwon/wg-skills, covering 组合指令详解, 指令列表, icon-tag, badge and icon-btn.
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
designer
DaisyUI로 예쁜 UI를 만들거나, 기존 UI를 바꿔줘요.
design-system
Validate a project against the design-system guardrails — token-only styling, one component library, variants over call-site restyling. Reports drift by rule, and can fix it or scaffold the guardrails.