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/pproenca/dot-skills/mui-basenpx skills add pproenca/dot-skills --skill mui-basegit clone --depth 1 https://github.com/pproenca/dot-skillsWrote 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/pproenca/dot-skills/mui-base)<a href="https://agentmods.dev/skills/pproenca/dot-skills/mui-base"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/mui-base.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 | $0.00072 | $0.01144 |
| Opus 5 | $0.00036 | $0.00572 |
| Sonnet 5 | $0.00014 | $0.00229 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
mui-base 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 4d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MUI Headless UI Best Practices
Comprehensive style guide for building headless React component libraries following MUI Base UI patterns. Contains 48 rules across 5 categories, prioritized by impact.
When to Apply
Reference these guidelines when:
- Building headless/unstyled component libraries
- Creating compound components with context-based composition
- Implementing accessible UI primitives with ARIA patterns
- Using render props and className callbacks for styling flexibility
- Writing components that support both controlled and uncontrolled modes
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Component Patterns | CRITICAL | comp- |
| 2 | Naming Conventions | HIGH | name- |
| 3 | Organization | HIGH | org- |
| 4 | Error Handling | HIGH | err- |
| 5 | Style | MEDIUM | style- |
Quick Reference
1. Component Patterns (CRITICAL)
comp-forward-ref-named- Use forwardRef with Named Functioncomp-props-parameter-naming- Name Props Parameter componentPropscomp-use-render-element- Use useRenderElement for DOM Renderingcomp-context-undefined-default- Create Context with Undefined Defaultcomp-context-error-message- Context Error Messages with Hierarchycomp-use-controlled- Use useControlled Hook for Dual Modescomp-state-memoization- Memoize State Objectscomp-context-value-memo- Memoize Context Provider Valuescomp-plain-function-root- Plain Function for Non-DOM Rootscomp-hook-namespace-exports- Hook Namespace Exportscomp-props-destructure-order- Props Destructuring Ordercomp-use-client-directive- Add use client Directive
2. Naming Conventions (HIGH)
name-component-naming- Component Naming as ParentPartname-file-matches-export- File Name Matches Primary Exportname-directory-kebab-case- Directory Naming kebab-casename-part-directory-lowercase- Part Directory Naming lowercasename-context-suffix- Context Naming with Suffixname-context-hook- Context Hook as useComponentContextname-props-interface- Props Interface as ComponentPropsname-state-interface- State Interface as ComponentStatename-namespace-type-exports- Namespace Type Exportsname-event-type- Event Type Naming Conventionname-constants- Constant Naming SCREAMING_SNAKE_CASEname-data-attributes- Data Attribute Naming lowercasename-hooks- Hook Naming with use Prefixname-refs- Ref Variable Naming with Suffixname-handlers- Handler Naming Convention
What ships with it
53 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.
- AGENTS.md 9.0 KB
- assets/templates/_template.md 444 B
- metadata.json 1.5 KB
- README.md 4.5 KB
- references/_sections.md 1.3 KB
- references/comp-context-error-message.md 1.4 KB
- references/comp-context-undefined-default.md 1.6 KB
- references/comp-context-value-memo.md 1.4 KB
- references/comp-forward-ref-named.md 1.2 KB
- references/comp-hook-namespace-exports.md 1.4 KB
- references/comp-plain-function-root.md 1.6 KB
- references/comp-props-destructure-order.md 1.0 KB
- references/comp-props-parameter-naming.md 1.2 KB
- references/comp-state-memoization.md 1.2 KB
- references/comp-use-client-directive.md 1.1 KB
- references/comp-use-controlled.md 1.7 KB
- references/comp-use-render-element.md 1.8 KB
- references/err-cancelable-events.md 1.7 KB
- references/err-context-error-guidance.md 1.3 KB
- references/err-deduplicated-warnings.md 1.2 KB
- references/err-dev-only-warnings.md 1.5 KB
- references/err-event-reason-constants.md 1.3 KB
- references/err-message-prefix.md 976 B
- references/err-prop-validation-timing.md 1.5 KB
- references/err-typed-event-reasons.md 1.5 KB
- references/name-component-naming.md 1.3 KB
- references/name-constants.md 895 B
- references/name-context-hook.md 1.4 KB
- references/name-context-suffix.md 1.2 KB
- references/name-data-attributes.md 1.1 KB
- references/name-directory-kebab-case.md 709 B
- references/name-event-type.md 1.0 KB
- references/name-file-matches-export.md 976 B
- references/name-handlers.md 1.6 KB
- references/name-hooks.md 1.1 KB
- references/name-namespace-type-exports.md 1.3 KB
- references/name-part-directory-lowercase.md 849 B
- references/name-props-interface.md 1.1 KB
- references/name-refs.md 1.1 KB
- references/name-state-interface.md 1.0 KB
- references/org-component-directory.md 1.1 KB
- references/org-context-placement.md 791 B
- references/org-css-vars-file.md 1.1 KB
- references/org-data-attributes-file.md 1.4 KB
- references/org-dual-barrel-exports.md 1.7 KB
- references/org-package-exports.md 1.3 KB
- references/org-state-attributes-mapping.md 1.5 KB
- references/org-test-colocation.md 1011 B
- references/style-default-values.md 1.2 KB
- references/style-explicit-undefined.md 1.0 KB
- references/style-internal-imports.md 1.2 KB
- references/style-jsdoc-documentation.md 1.4 KB
- references/style-react-import.md 1.1 KB
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.
- 4d ago First seen · 110 lines · 72 tokens per session scan A e83eb09db123
mui-base is a skill published in the GitHub repository pproenca/dot-skills (201 stars, last pushed 19d ago), licensed MIT. It adds 72 tokens to every session and 1,144 once invoked, about $0.0004 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
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.
accessibility-analysis
服務可達性分析工具箱(accessibility / service coverage)。當用戶說「30km 路網可達」「最近 X 站」「服務範圍」「沙漠」「孤島」「等時圈」「isochrone」「可達性分析」「路網覆蓋」或要新增任何「離 POI 多遠」類型的分析時觸發。整合 mini-taiwan-pulse + taipei-gis-analytics 兩端 SOP,覆蓋三種視覺模式(路網染色 / Polygon 沿路網 / Hex 格點)、三套既有 reference pipeline 對照、模式選擇決策樹、常見坑(Overpass mirror 不穩 / pyrosm 爆 RAM / multi-bucket /…
ui-design
UI 样式修改协作流程(已有界面的视觉层微调)。触发硬条件:页面已经在代码里跑着,改的只是它的视觉表现——布局、间距、颜色、字号、圆角、组件搭配。通过"读代码 + ASCII 画出现状让用户确认 → 给 2-3 个 ASCII 方案 → 用户选定 → 最小改动 → 微调"的流程,减少沟通偏差、避免浪费 token。产出:只动样式的代码 diff。硬边界:不动业务逻辑、不动数据流、不改交互行为、不顺手重构。不适用于:界面还不存在、要从零探索长什么样(用 design-exploration)、改的是功能或交互逻辑而不只是视觉(用 req-change-workflow)、照着设计图/截图复刻整页(用…