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 acryldev/acryl --skill acryl-improve-uigit clone --depth 1 https://github.com/acryldev/acrylWrote 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/acryldev/acryl/acryl-improve-ui)<a href="https://agentmods.dev/skills/acryldev/acryl/acryl-improve-ui"><img src="https://agentmods.dev/badge/skills/acryldev/acryl/acryl-improve-ui/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/acryldev/acryl/acryl-improve-ui"><img src="https://agentmods.dev/badge/skills/acryldev/acryl/acryl-improve-ui.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 | $0.00043 | $0.00174 |
| Opus 5.5 | $0.00017 | $0.00070 |
| Sonnet 5.5 | $0.00009 | $0.00035 |
| Haiku 4.5 | $0.00004 | $0.00017 |
Grade A, and why
acryl-improve-ui 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.
What it actually says
Improve or change an existing UI plugin
Call acryl_list_plugins to find the package directory, then read its client.js completely and {{pack}}/docs/extending/client-slot.md. Edit in place: keep the wrapper id, keep exports, keep the localStorage key so the user's data survives. Prefer small edits over rewrites. Keep no-build rules (createElement, require, no JSX/import). Run acryl_verify_plugin, then acryl_install_plugin again (it updates in place) and ask the user to look: it updates live, with no reload. Tell the user exactly what changed.
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 Changed · -1 lines 6ac756eaa6ac
- 25d ago First seen · 12 lines · 43 tokens per session scan A c4a2af1f1580
acryl-improve-ui is a skill published in the GitHub repository acryldev/acryl (256 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 174 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
figma-implement-motion
Translates Figma motion and animations into production-ready application code. Use when implementing animation/motion from a Figma design — user mentions "implement this motion", "add animation from Figma", "animate this component", provides a Figma URL whose node is animated, or when getdesigncontext returns motion…
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
workdsh-web-design
A workflow guide for designing and building websites, landing pages, and web applications. It covers content structure, visual styles, responsive layouts, bilingual content, interactions, previews, and delivery within the supported WorkDSH tools.
ipollowork-plugin-ui
A set of instructions for building iPolloWork plug-in interfaces with shared components, colours, fonts, and interaction rules. It covers both React plug-ins and standalone HTML or iframe plug-ins.
emil-design-eng
Create, implement, or review design engineering craft work with format, accessibility, performance, and visual-verification controls. Use when the requested deliverable depends on design engineering craft.
tailwind-design-system
Create, implement, or review tailwind design system work with format, accessibility, performance, and visual-verification controls. Use when the requested deliverable depends on tailwind design system.