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/muminur/frontend-design-craft-skill/polishgit clone --depth 1 https://github.com/Muminur/frontend-design-craft-skillWrote 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/muminur/frontend-design-craft-skill/polish)<a href="https://agentmods.dev/commands/muminur/frontend-design-craft-skill/polish"><img src="https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/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 5.1 | $0.00014 | $0.00527 |
| Opus 5 | $0.00007 | $0.00264 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00053 |
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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polish
Apply fixes across motion, polish, and taste. This is the inverse of /audit: change the code, do not just report on it.
Target
$ARGUMENTS
Procedure
Apply fixes in this strict order. Skipping ahead will produce inferior results.
Pass 1 — Polish (structural)
Fix anything in the foundation before touching aesthetics or motion:
- Normalize spacing to a single scale (default 4px base).
- Define or normalize a type scale; remove any arbitrary
font-sizevalues. - Calibrate line-height per size (lower for large headings, higher for body).
- Replace pure black and pure white with tinted neutrals.
- Verify and fix contrast to WCAG AA minimum.
- Reduce border radius and shadow values to a coherent set (1–2 radii, layered shadows).
- Verify breakpoints actually change layout, not just rescale.
Pass 2 — Taste (aesthetic)
Once structure is sound:
- Strip banned patterns (purple-blue gradients, glassmorphism, gradient text, default Inter, default shadcn theme, etc. — see
skills/taste/SKILL.md). - Replace placeholder content (
Lorem ipsum,John Doe, fake stats, stock photos). - Confirm or pick an archetype; align the design to it.
- Override default icon library settings if used unchanged.
Pass 3 — Motion
With structure and taste in place:
- Audit every existing animation: does it communicate something or decorate?
- Make easing consistent across related elements.
- Calibrate timing to perceived weight (see
skills/motion/SKILL.md). - Convert any animated layout properties (
width,height,margin) totransform/opacity. - Add
prefers-reduced-motioncoverage.
Output
After each pass, summarize what was changed in 3–5 bullets. After all three passes:
## Polish complete
**Files modified:** [list]
**Pass 1 — Polish:** [n] changes
**Pass 2 — Taste:** [n] changes
**Pass 3 — Motion:** [n] changes
**Open questions for the user:**
- [anything that required a judgment call]
Do not skip the open-questions section. If everything was unambiguous, say so explicitly.
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.
- 6d ago First seen · 66 lines · 14 tokens per session scan A bfe50878f914
polish is a command published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 527 once invoked, about $0.0001 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 commands, from other repositories
frontend-review
Frontend code review for images, accessibility, responsive design, and CSS patterns.
web-design-cleanup
I want you to act as a Web Design expert. You know HTML, JavaScript, CSS, and related technologies well. You embrace DRY principles and are good at reviewing others' code.
css-audit
Full CSS audit covering performance, accessibility, best practices, and compatibility.
css-review
Comprehensive CSS code review with best practices, accessibility, and performance analysis.
/a11y-audit
Auditoría de accesibilidad WCAG 2.2 completa con escaneo de HTML/componentes. Detecta: alt text faltante, problemas de contraste, navegación por teclado, etiquetas ARIA, gestión de focus, jerarquía de encabezados, etiquetas de formularios. Genera reporte accionable con instrucciones de remediación.
review-arch
Review the current branch for code quality, TypeScript, and React/Next.js patterns. Supports whole-branch review or scoped review by path, feature, or base branch.