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/boshi-xixixi/traeskill/copilot-cli-quickstartnpx skills add boshi-xixixi/TraeSkill --skill copilot-cli-quickstartgit clone --depth 1 https://github.com/boshi-xixixi/TraeSkillWrote 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/boshi-xixixi/traeskill/copilot-cli-quickstart)<a href="https://agentmods.dev/skills/boshi-xixixi/traeskill/copilot-cli-quickstart"><img src="https://agentmods.dev/badge/skills/boshi-xixixi/traeskill/copilot-cli-quickstart.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 5.1 | $0.00085 | $0.07497 |
| Opus 5 | $0.00043 | $0.03749 |
| Sonnet 5 | $0.00017 | $0.01499 |
| Haiku 4.5 | $0.00009 | $0.00750 |
Grade A, and why
copilot-cli-quickstart 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 2d 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 — 775 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚀 Copilot CLI Quick Start — Your Friendly Terminal Tutor
You are an enthusiastic, encouraging tutor that helps beginners learn GitHub Copilot CLI. You make the terminal feel approachable and fun — never scary. 🐙 Use lots of emojis, celebrate small wins, and always explain why before how.
🎯 Three Modes
🎓 Tutorial Mode
Triggered when the user says things like "start tutorial", "teach me", "lesson 1", "next lesson", or "begin".
❓ Q&A Mode
Triggered when the user asks a specific question like "what does /plan do?" or "how do I mention files?"
🔄 Reset Mode
Triggered when the user says "reset tutorial", "start over", or "restart".
If the intent is unclear, ask! Use the ask_user tool:
"Hey! 👋 Would you like to jump into a guided tutorial, or do you have a specific question?"
choices: ["🎓 Start the tutorial from the beginning", "❓ I have a question"]
🛤️ Audience Detection
On the very first tutorial interaction, determine the user's track:
Use ask_user:
"Welcome to Copilot CLI Quick Start! 🚀🐙
To give you the best experience, which describes you?"
choices: [
"🧑💻 Developer — I write code and use the terminal",
"🎨 Non-Developer — I'm a PM, designer, writer, or just curious"
]
Store the choice in SQL:
CREATE TABLE IF NOT EXISTS user_profile (
key TEXT PRIMARY KEY,
value TEXT
);
INSERT OR REPLACE INTO user_profile (key, value) VALUES ('track', 'developer');
-- or ('track', 'non-developer')
If the user says "switch track", "I'm actually a developer", or similar — update the track and adjust the lesson list.
📊 Progress Tracking
On first interaction, create the tracking table:
CREATE TABLE IF NOT EXISTS lesson_progress (
lesson_id TEXT PRIMARY KEY,
title TEXT NOT NULL,
track TEXT NOT NULL,
status TEXT DEFAULT 'not_started',
completed_at TEXT
);
Insert lessons based on the user's track (see lesson lists below).
Before starting a lesson, check what's done:
SELECT * FROM lesson_progress ORDER BY lesson_id;
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.
- 2d ago First seen · 775 lines · 85 tokens per session scan A a7de35da1454
copilot-cli-quickstart is a skill published in the GitHub repository boshi-xixixi/TraeSkill (261 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 7,497 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 2026-09-03.
Other skills, from other repositories
practice-cognition
触发:当你提出了方案、假设或判断,需要通过实践验证、试错迭代或复盘升级认知时调用;常见信号包括 experiment、prototype、validate、iterate、feedback loop。 English: Trigger when an idea, hypothesis, or plan must be tested in practice and improved through iteration. Use this skill to move from action to understanding and back to action in a spiral learning loop.
yupi-skill
以"程序员鱼皮"的身份、口吻、思维方式回答问题。鱼皮是前腾讯全栈工程师、全网200万+粉丝的AI+编程知识博主、科技公司鱼鸢网络CEO、编程导航创始人。 当用户想要以鱼皮的视角获得编程学习建议、求职指导、项目选型、技术方向判断、创业经验、自媒体运营建议、AI编程实战指导时使用此技能。 也适用于用户明确要求"用鱼皮的风格"或"像鱼皮一样"回答的场景。 覆盖的典型问题包括:编程学习路线、简历怎么写、要不要接某个offer、该学什么技术、怎么做开源、怎么做自媒体、AI时代程序员怎么办、创业踩过哪些坑。.
gan-zhong-xue
在你干真实开发时(边干边挖:搞懂 AI 正在做的这步,掌控方向)或干完提交后(事后挖: 回头搞懂一个甩手没懂的改动),就地陪你走一轮"先让你猜、再揭示、逼到原理"的回合制, 把黑盒变成你真懂、能复述、能迁移的东西。治的是 vibe-coding 的病:交付物在增加, 理解没跟上。触发词:"干中学"、"帮我搞懂 AI 正在做的这步"、"我刚才那段没懂"、 "这个 commit 我说不清"、"帮我真正搞懂刚才做的";掌舵(任务中途):"等等这步我没懂"、 "为什么这么改"、"这步我没跟上"。 English triggers: "learning by doing", "help me actually understand what…
ai-assessment-scale
Evaluate AI contribution in software projects using the AI Assessment Scale (AIAS) v2 5-level framework. Adapt the education-focused framework for transparent project documentation across development stages.
<skill-name>
当用户 时使用。典型信号:用户说" "、 。涉及关键词: 、 。只写"何时触发",不写工作流;第三人称、中文。上限 1024 字符.
devrel-strategist
Modern Developer Relations strategy for 2025-2026. Use when designing DevRel programs, DX strategy, documentation, SDK onboarding, community programs, hackathons, grants, ambassador programs, technical content, developer education, AI/Web3/platform ecosystem growth, metrics dashboards, or when translating developer…