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 skills/softaworks/agent-toolkit/muinpx skills add softaworks/agent-toolkit --skill muigit clone --depth 1 https://github.com/softaworks/agent-toolkitWhat 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 | $0.00048 | $0.02553 |
| Opus 5 | $0.00024 | $0.01277 |
| Sonnet 5 | $0.00010 | $0.00511 |
| Haiku 4.5 | $0.00005 | $0.00255 |
Grade A, and why
mui 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mui — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MUI v7 Patterns
Purpose
Material-UI v7 (released March 2025) patterns for component usage, styling with sx prop, theme integration, and responsive design.
Note: MUI v7 breaking changes from v6:
- Deep imports no longer work - use package exports field
onBackdropClickremoved from Modal - useonCloseinstead- All components now use standardized
slotsandslotPropspattern - CSS layers support via
enableCssLayerconfig (works with Tailwind v4)
When to Use This Skill
- Styling components with MUI sx prop
- Using MUI components (Box, Grid, Paper, Typography, etc.)
- Theme customization and usage
- Responsive design with MUI breakpoints
- MUI-specific utilities and hooks
Quick Start
Basic MUI Component
import { Box, Typography, Button, Paper } from '@mui/material';
import type { SxProps, Theme } from '@mui/material';
const styles: Record<string, SxProps<Theme>> = {
container: {
p: 2,
display: 'flex',
flexDirection: 'column',
gap: 2,
},
header: {
mb: 3,
fontSize: '1.5rem',
fontWeight: 600,
},
};
function MyComponent() {
return (
<Paper sx={styles.container}>
<Typography sx={styles.header}>
Title
</Typography>
<Button variant="contained">
Action
</Button>
</Paper>
);
}
Styling Patterns
Inline Styles (< 100 lines)
For components with simple styling, define styles at the top:
import type { SxProps, Theme } from '@mui/material';
const componentStyles: Record<string, SxProps<Theme>> = {
container: {
p: 2,
display: 'flex',
flexDirection: 'column',
},
header: {
mb: 2,
color: 'primary.main',
},
button: {
mt: 'auto',
alignSelf: 'flex-end',
},
};
function Component() {
return (
<Box sx={componentStyles.container}>
<Typography sx={componentStyles.header}>Header</Typography>
<Button sx={componentStyles.button}>Action</Button>
</Box>
);
}
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 505 lines · 48 tokens per session scan A d1a9a06753be
mui is a skill published in the GitHub repository softaworks/agent-toolkit (2,401 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 2,553 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 skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…