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/peterhdd/agent-skills/engineering-frontend-developernpx skills add PeterHdd/agent-skills --skill engineering-frontend-developergit clone --depth 1 https://github.com/PeterHdd/agent-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/peterhdd/agent-skills/engineering-frontend-developer)<a href="https://agentmods.dev/skills/peterhdd/agent-skills/engineering-frontend-developer"><img src="https://agentmods.dev/badge/skills/peterhdd/agent-skills/engineering-frontend-developer.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 | $0.00077 | $0.05388 |
| Opus 5 | $0.00039 | $0.02694 |
| Sonnet 5 | $0.00015 | $0.01078 |
| Haiku 4.5 | $0.00008 | $0.00539 |
Grade A, and why
engineering-frontend-developer 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 3d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Development Guide
Overview
This guide covers modern frontend development with React, Vue, Angular, and Svelte, including component architecture, performance optimization, accessibility, and testing. Use it when building web applications, component libraries, or optimizing frontend performance.
Framework and Layout Decision Rules
- When choosing a framework, match it to team expertise and project constraints; default to React for broad ecosystem needs, Vue for progressive enhancement into existing pages, Svelte for bundle-size-critical apps, and Angular when the project requires an opinionated full-framework with built-in DI and routing.
- When implementing a design, use CSS Grid for two-dimensional page layouts and Flexbox for one-dimensional component alignment; avoid absolute positioning for layout purposes because it breaks responsive reflow.
- When building a component library, expose each component as a named export with TypeScript props interface, a Storybook story, and a unit test -- components without all three are not merged.
- When integrating with backend APIs, centralize fetch logic in a typed API client layer (e.g., a single
api.tsmodule usingfetchoraxioswith interceptors) so auth headers, error transforms, and retries are handled in one place.
Performance Decision Rules
- When a page's Largest Contentful Paint exceeds 2.5 seconds in Lighthouse CI, treat it as a blocking bug -- profile with Chrome DevTools Performance tab and fix the largest bottleneck before merging.
- When adding animations, use CSS
transformandopacityproperties (compositor-only) rather thanwidth,height, ortop/leftto avoid triggering layout recalculations that cause jank. - When the app needs offline support, register a service worker with a cache-first strategy for static assets and a network-first strategy for API requests, falling back to cached responses when offline.
- When initial JS bundle exceeds the budget (e.g., 200 KB gzipped), add route-based code splitting with
React.lazy()or dynamicimport()and defer non-critical scripts below the fold. - When supporting older browsers, define a browserslist config and let the build tool (Vite, Webpack) auto-polyfill; do not manually add polyfills or feature checks unless browserslist coverage is insufficient.
- When adding images, use
<picture>with WebP/AVIF sources and explicitwidth/heightattributes to prevent layout shift; for images below the fold, addloading="lazy". - When a route is not needed on initial page load, wrap it in
React.lazy()(or framework equivalent) with a<Suspense>fallback so the main bundle excludes that route's code. - When serving static assets, configure the CDN or server to set
Cache-Control: public, max-age=31536000, immutableon content-hashed filenames andno-cacheonindex.html.
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.
- 3d ago First seen · 211 lines · 77 tokens per session scan A 246f9a2cffb2
engineering-frontend-developer is a skill published in the GitHub repository PeterHdd/agent-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 5,388 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
wxjava-module-selector
根据微信公众号、小程序、微信支付、企业微信、开放平台、视频号或微信小店、腾讯企点和微信智能对话等业务场景,为用户选择合适的 WxJava Maven 模块、BOM 和示例入口。适用于用户询问“该用哪个模块”、依赖坐标、产品边界或单/多账号 Starter 选择时。.
cpp-pro
Writes, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques. Use when building or refactoring C++ code requiring concepts, ranges, coroutines, SIMD optimization, or careful memory management — or when addressing performance…
rust-pro
Master modern Rust (2024 edition) with async patterns, advanced type system features, and production-ready systems programming. Expert in the current Rust ecosystem including Tokio, axum, and modern crates. Use PROACTIVELY for Rust development, performance optimization, or systems programming.
ax-python-agent
Use when writing Python code with axllm for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.
mps-aspect-actions
Use when defining or editing MPS node factories (the "actions" aspect) — NodeFactories roots, per-concept NodeFactory setup functions that initialize a freshly created node and optionally copy data from a replaced sampleNode, plus the actions aspect's CopyPasteHandlers and PasteWrappers roots. Reach for this skill…
typescript-functions
Apply, review, and explain TypeScript function conventions. Use automatically for tasks involving function responsibility, statelessness, purity, side effects, function arguments, function API design, or return types.