agentmods.dev

taste-skill copilot-instructions.md

A set of instructions for GitHub Copilot, an AI coding assistant, that guides its code and interface-design choices. It asks Copilot to avoid generic layouts, leave room around elements, use spring-like animation, and provide complete implementations.

In plain words
What is it for?
It helps generate frontend code with stronger visual hierarchy, spacing, alignment, animation, and more complete implementations.
Why use it?
It gives Copilot clearer style expectations instead of leaving it to produce default templates or unfinished placeholder code.

Instructions file for GitHub Copilot

82k 7d ago A scan 214 tokens original MIT
View the source file Leonxlnx/taste-skill
Install

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.

agentmods
npx agentmods add instructions/leonxlnx/taste-skill/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Leonxlnx/taste-skill

Made for: GitHub Copilot.

Per session 214 This file is loaded in full into every session.
When invoked 214 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00214 $0.00214
Opus 5 $0.00107 $0.00107
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00021 $0.00021

Measured yesterday against content hash bb3a5ee79ef5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

taste-skill copilot-instructions.md 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.

.github/copilot-instructions.md · 12 lines

What it actually says

Copilot Instructions: Taste Standard

Note: GitHub Copilot automatically reads this file to set its global behavior. By including this in the .github folder, Copilot stops writing generic "slop" code and adheres to the premium Taste Skill standards.

The "Anti-Slop" Manifesto for Copilot

  1. No Generic UI: Stop generating default SaaS templates. Use high contrast, strong typographic hierarchy, and extreme care for alignment.
  2. Premium Whitespace: Elements need room to breathe. Use proportional clamp() spacing over rigid padding.
  3. Cinematic Motion: Never use linear easing. All animations must use spring physics (stiffness: 100, damping: 20 or similar).
  4. Complete Implementation: No placeholders. No // TODO: add actual code here. Write the full, working implementation every single time.
  5. Contextual Awareness: For deep style configurations, read the localized SKILL.md files in the skills/ directory.
Changes

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.

  1. yesterday First seen · 12 lines · 214 tokens per session scan A bb3a5ee79ef5

Subscribe to this mod's changes

taste-skill copilot-instructions.md is an instructions file published in the GitHub repository Leonxlnx/taste-skill (82,438 stars, last pushed 7d ago), licensed MIT. It adds 214 tokens to every session, about $0.0011 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.

Creative and mediaFrontendagentaicodinglowcodenocodeskill
Related

Other instructions, from other repositories

show-me-the-story AGENTS.md

Instructions for Nigh/show-me-the-story, covering agents.md — ai 小说生成器项目指南, 项目概述, 编译与运行, 完整编译（含前端构建） and 或手动分步.

Nigh/show-me-the-story · 24,384 tokens

Undefined CLAUDE.md

Instructions for 69gg/Undefined, covering claude.md, 项目概述, 开发命令, 依赖安装 / 初始化 and 启动.

69gg/Undefined · 3,571 tokens

skill-based-architecture AGENTS.md

Instructions for WoJiSama/skill-based-architecture, covering agents.md, quick routing (survives context truncation), auto-triggers and red flags — stop.

WoJiSama/skill-based-architecture · 829 tokens

pruna-skills AGENTS.md

Instructions for PrunaAI/pruna-skills, covering pruna skills (agent notes), how it works, clarification (library-wide), install and layout.

PrunaAI/pruna-skills · 1,052 tokens

generative-media-skills AGENTS.md

Instructions for calesthio/generative-media-skills, covering agent instructions, non-negotiable rules and allowed consistency.

calesthio/generative-media-skills · 619 tokens

specship CLAUDE.md

Instructions for bonnguyenitc/specship, covering specship — dev guide, verify every change and learnings.

bonnguyenitc/specship · 643 tokens