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 instructions/microsoft/lets-learn-mcp-python/copilot-instructionsgit clone --depth 1 https://github.com/microsoft/lets-learn-mcp-pythonWhat 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 | $0.01116 | $0.01116 |
| Opus 5 | $0.00558 | $0.00558 |
| Sonnet 5 | $0.00223 | $0.00223 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
lets-learn-mcp-python 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Study Buddy MCP Server Instructions
Activation Trigger: Use these instructions whenever the user mentions:
- Learning Python
- Python study/practice
- Python Study Buddy application
- Python exercises or tutorials
Required Server: learnpython-mcp (must be enabled)
Workflow Overview
This is a 5-step sequential process. Each step must be completed before moving to the next.
- Assess Experience → 2. Generate Exercises → 3. Create Exercises → 4. Track Progress → 5. Start App
Step 1: Assess User Experience Level
Action Required:
- Instruct user to use the
python_topicsprompt - Wait for user to select their experience level
Response Template:
Welcome to the Python Study Buddy application! 🐍📚✨
Let's start by understanding your Python experience level.
**How to proceed:**
1. Type `/` in the chat
2. Select `mcp.learnpython-mcp.python_topics` from the menu
3. Enter your experience level in the input box:
- `Beginner` (new to Python)
- `Intermediate` (familiar with basics)
- `Advanced` (experienced developer)
*Note: If you press enter without selecting, it defaults to "Beginner"*
Press enter to generate your personalized topic list!
After Topics Are Generated:
Present the topics in this format:
Here are Python topics tailored to your level:
1. `[Topic 1 Name]`
2. `[Topic 2 Name]`
3. `[Topic 3 Name]`
4. `[Topic 4 Name]`
5. `[Topic 5 Name]`
Which topic interests you? Reply with either:
- The topic number (1-5), or
- The exact topic name
I'll create custom exercises based on your selection!
Step 2: Generate Exercises
Action Required:
Guide user to run the generate_exercises prompt with their selected topic
Response Template:
Excellent choice! Let's create exercises for [selected topic].
**Next steps:**
1. Type `/` in the chat
2. Select `mcp.learnpython-mcp.generate_exercises`
3. Copy and paste these details into the input box:
**Topic:** `[selected topic]`
**Level:** `[user's level]`
**Number of exercises:** `5` (or specify your preference)
Press enter to generate your custom exercises!
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.
- yesterday First seen · 185 lines · 1,116 tokens per session scan A 90716411d403
lets-learn-mcp-python copilot-instructions.md is an instructions file published in the GitHub repository microsoft/lets-learn-mcp-python (1,066 stars, last pushed 11mo ago), licensed MIT. It adds 1,116 tokens to every session, about $0.0056 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 instructions, from other repositories
LLM-dev-demo AGENTS.md
Instructions for A3RDLab/LLM-dev-demo, covering agents.md, 仓库性质, 环境与密钥约定, 依赖管理 and 常用命令.
python-cheatsheet copilot-instructions.md
Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.
python-cheatsheet GEMINI.md
Gemini CLI instructions for labex-labs/python-cheatsheet, covering gemini customization file, project overview, technologies, coding style and conventions and routing & layout system.
template-advisor-aget AGENTS.md
Instructions for aget-framework/template-advisor-aget, covering agent configuration - advisor aget template, agent compatibility, project context, purpose and key characteristics.
mini-claude-code-python AGENTS.md
Instructions for Xiaxia1997/mini-claude-code-python, covering mini claude code python 协作规则, 项目目标, 默认语言与风格, 代码来源边界 and 章节一致性要求.
multi-agent-system-pattern AGENTS.md
Instructions for vpeetla-ai/multi-agent-system-pattern, covering agent instructions — vpeetla-ai org, agentic engineering (karpathy), stack awareness, repo conventions and skills repo.