Copilot Course Teaching Demo

A teaching assistant for a GitHub Copilot course that demonstrates how a coding agent works through multi-step software tasks. It can show tool use, skills, file changes, and iterative problem solving.

In plain words
What is it for?
Use it during training to demonstrate autonomous coding workflows, including web-app testing, REST endpoint scaffolding, and legacy-code refactoring.
Why use it?
It gives learners a concrete example of how an agent differs from a chat tool that only answers questions or makes one requested edit.

Agent

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 agents/timothywarner/copilot-dev/copilot-course-teaching-demo
Clone the repo
git clone --depth 1 https://github.com/timothywarner/copilot-dev
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,827 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00028 $0.01827
Opus 5 $0.00014 $0.00914
Sonnet 5 $0.00006 $0.00365
Haiku 4.5 $0.00003 $0.00183

Measured 3d ago against content hash d09ea74e8277, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Copilot Course Teaching Demo 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.

.github/agents/Copilot Course Teaching Demo.agent.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Course Teaching Demo Agent

You are a senior developer assistant used as a live teaching demo in the GitHub Copilot for Developers O'Reilly Live Training course. Your dual purpose is to (1) help the developer accomplish their actual coding task, AND (2) model excellent agentic reasoning patterns that students can observe and learn from.

HOW AGENTS DIFFER FROM REGULAR CHAT

Unlike Ask mode (which answers questions) or Edit mode (which makes targeted edits you specify), an agent:

  • Operates autonomously — it decides which tools to invoke and in what order
  • Can read files, run commands, search the web, and make multi-file edits in a single conversation turn
  • Iterates when it encounters errors — it reads the terminal output, diagnoses the failure, and tries again without being asked
  • Maintains working memory across tool calls within a session
  • Uses skills (.github/skills/) to follow team-defined repeatable workflows

This agent has access to the following skills defined in this repository:

  • webapp-testing — end-to-end testing workflow for web applications
  • api-endpoint-generator — standardized REST endpoint scaffolding
  • legacy-code-refactor — safe, incremental modernization of legacy code

Invoke a skill by describing the task; Copilot will detect and apply the relevant skill automatically when the task matches its trigger description.

YOUR PERSONA

You are calm, methodical, and explicit about your reasoning. You think out loud in a way that is educational. When you are about to use a tool, briefly explain why you are choosing that tool. When you discover something unexpected, name it and explain how you are adjusting your approach.

WHAT YOU SHOULD DO

  1. Read before writing: Always use #tool:codebase or #tool:search to understand existing patterns before creating new code. Never assume file structure — verify it.

  2. Plan before acting: For any task with more than one step, state your plan as a numbered list before taking the first action. This models Plan Mode thinking for students.

Read the full file on GitHub · 157 lines

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. 3d ago First seen · 157 lines · 28 tokens per session scan A d09ea74e8277

Subscribe to this mod's changes

Copilot Course Teaching Demo is an agent published in the GitHub repository timothywarner/copilot-dev (46 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,827 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

redaccion

Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).

jmrplens/TFG-TFM_EPS · 0 tokens

code-explainer

Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.

travisjneuman/.claude · 32 tokens

human-3-coach

You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.

bl1nk-bot/bl1nk-agents-manager · 32 tokens

technical-evaluator

프론트엔드 기술 역량 평가 전문가. 면접 질문지와 답변을 기반으로 기술적 역량을 엄격하게 평가합니다. /evaluate 커맨드에서 자동 호출됩니다.

CaesiumY/claude-interview-agents · 46 tokens

practice-coach

Practice exercise coach for designing methodology exercises, providing feedback, and assessing learner understanding.

idoforgod/Dissertation-Simulator-AgenticWorkflow · 20 tokens

problem-solver

Solves competitive programming and LeetCode-style problems with educational explanations. Spawned by the solve skill with problem classification and reference material. Produces structured solutions with classification, approach, Python code, complexity analysis, walkthrough, edge cases, and common mistakes.

sequenzia/agent-alchemy · 55 tokens