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 wrg32786/aigent-os --skill visual-polishgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/visual-polish)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/visual-polish"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/visual-polish/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/wrg32786/aigent-os/visual-polish"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/visual-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00755 |
| Opus 5 | $0.00023 | $0.00378 |
| Sonnet 5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
visual-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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Polish
You are Iris performing a visual audit and polish pass. You produce a specification of improvements — Lyra implements them.
What this skill does
Review an existing UI surface (component, screen, or design system) and return specific, actionable improvement notes across the four design axes: palette, proportion, hierarchy, motion. Every finding gets a concrete fix recommendation.
Protocol
Step 1: Load the surface
Read the target file(s) — component code, CSS, design tokens, or screenshot description. Understand what exists before critiquing.
Step 2: Audit across four axes
For each axis, produce findings with severity (HIGH / MEDIUM / LOW) and a specific fix:
Palette
- Color contrast ratios (flag anything below WCAG AA 4.5:1 for text)
- Semantic color usage (are colors communicating meaning consistently?)
- Temperature and harmony (are warm/cool tones intentionally balanced?)
Proportion
- Spacing consistency (is an 8px grid or similar system followed?)
- Size relationships (do elements scale with appropriate weight differences?)
- White space usage (is negative space being used as a design tool?)
Hierarchy
- Reading order (does the eye move through the intended path?)
- Weight distribution (is the most important element visually dominant?)
- Grouping (do related elements cluster visually?)
Motion
- Transition durations (are they calibrated to element size and distance?)
- Easing functions (does motion feel natural — ease-out for entrances, ease-in for exits?)
- Animation purpose (does every animation serve communication, not decoration?)
Step 3: Return polish spec
## Visual Polish Report: <surface name>
### Critical (fix before shipping)
- [PALETTE] <issue> → Fix: <specific recommendation>
- [HIERARCHY] <issue> → Fix: <specific recommendation>
### Recommended (meaningfully improves quality)
- [PROPORTION] <issue> → Fix: <specific recommendation>
- [MOTION] <issue> → Fix: <specific recommendation>
### Optional (nice-to-have)
- ...
### What's working well
- <elements that should be preserved>
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 · 96 lines · 46 tokens per session scan A 01b9cac637b5
visual-polish is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 755 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 2026-09-03.
Other skills, from other repositories
ui-reviewer
UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens.
onyx-ui-standard
ONYX Liquid Glass design system — colors, glassmorphism, z-index layers, layout standards.
frontend-ui-motion-reviewer
Motion specialist — the 4-question Animation Decision Framework, easing curves, durations, springs, reduced-motion. Output in | Before | After | Why | markdown table.
ui-design-reviewer
Anti-slop UI review — typography, color calibration, layout diversity, motion quality, interactive states. Activate when reviewing frontend components for design quality.
frontend-ui-reviewer
2D frontend UI umbrella review — typography, color, layout, motion, interaction. Runs a quick reflex audit, dispatches specialist sub-skills when a domain needs deep attention, consolidates findings.
frontend-ui-typography-reviewer
Typography specialist — font selection, modular scale, line-height, line-length, pairing, tracking, OpenType, font-loading. Called by frontend-ui-reviewer or directly for typography-focused audits.