github/copilot-plugins is GitHub's collection of extensions for GitHub Copilot, including reusable skills, hooks, MCP servers, and other tools that add capabilities to the coding assistant. It provides workflows and building blocks for using or creating Copilot plugins.
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 github/copilot-plugins --skill spark-app-templategit clone --depth 1 https://github.com/github/copilot-pluginsWrote 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/github/copilot-plugins/spark-app-template)<a href="https://agentmods.dev/skills/github/copilot-plugins/spark-app-template"><img src="https://agentmods.dev/badge/skills/github/copilot-plugins/spark-app-template/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/github/copilot-plugins/spark-app-template"><img src="https://agentmods.dev/badge/skills/github/copilot-plugins/spark-app-template.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 | $0.00072 | $0.03976 |
| Opus 5.5 | $0.00029 | $0.01590 |
| Sonnet 5.5 | $0.00014 | $0.00795 |
| Haiku 4.5 | $0.00007 | $0.00398 |
Grade A, and why
spark-app-template 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 1mo 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 — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spark App Template
Purpose
Spark App Template provides defaults and guidance for building web applications. When a user asks to build a web app, this skill provides the technical foundation and design direction to create functional applications.
When to Use This Skill
Activate Spark App Template when the user:
- Wants to build a new web application from scratch
- Asks "what stack should I use?"
- Needs guidance on design, styling, or tech choices
- Wants to start a dashboard, interactive tool, data app, or content site
- Requests help choosing between frameworks, libraries, or approaches
Quick Start Workflow
CRITICAL: Follow this exact order to avoid configuration errors:
- Create project:
pnpm create vite@latest my-app --template react-ts - Install base dependencies:
pnpm install - Configure TypeScript path aliases (tsconfig.json AND tsconfig.app.json - see Step 1 below)
- Install Tailwind and tooling:
pnpm add -D tailwindcss @tailwindcss/vite @biomejs/biome - Configure vite.config.ts: Add Tailwind plugin and path aliases
- Initialize shadcn:
pnpm dlx shadcn@latest init(will now succeed with proper aliases) - Install required shadcn components:
pnpm dlx shadcn add button card avatar ...(BEFORE writing components) - Install additional packages: TanStack Router, Query, Zustand, etc.
- Write custom components (NOW safe to import from
@/components/ui/*) - Configure routing and state management
- Implement features
Steps 3, 6, and 7 must happen in this exact order to avoid TypeScript errors and failed shadcn installations.
Complexity Levels
Understanding complexity helps choose the right stack variation and design approach:
-
Micro Tool (single-purpose)
- Examples: Calculator, converter, color picker, timer
- Stack:
stacks/default-webapp.md - Focus: Simple, focused UI with minimal state
-
Content Showcase (information-focused)
- Examples: Landing page, portfolio, blog, documentation
- Stack:
stacks/content-showcase.md - Focus: Typography, reading experience, visual hierarchy
What ships with it
11 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.
- references/color-palettes.md 12 KB
- references/component-patterns.md 25 KB
- references/design-system.md 14 KB
- references/performance-checklist.md 13 KB
- references/prd-template.md 8.2 KB
- references/radix-migration-guide.md 7.1 KB
- references/typography-pairings.md 11 KB
- stacks/complex-application.md 22 KB
- stacks/content-showcase.md 11 KB
- stacks/data-dashboard.md 11 KB
- stacks/default-webapp.md 9.8 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.
- 1mo ago First seen · 491 lines · 72 tokens per session scan A 9c402f3582e5
spark-app-template is a skill published in the GitHub repository github/copilot-plugins (377 stars, last pushed 14d ago), licensed MIT. It adds 72 tokens to every session and 3,976 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…