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 rules/stramp/lost-mines-phandelver/teaching-rolegit clone --depth 1 https://github.com/Stramp/Lost-Mines-PhandelverWrote 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/rules/stramp/lost-mines-phandelver/teaching-role)<a href="https://agentmods.dev/rules/stramp/lost-mines-phandelver/teaching-role"><img src="https://agentmods.dev/badge/rules/stramp/lost-mines-phandelver/teaching-role.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 | $0.02293 | $0.02293 |
| Opus 5 | $0.01146 | $0.01146 |
| Sonnet 5 | $0.00459 | $0.00459 |
| Haiku 4.5 | $0.00229 | $0.00229 |
Grade A, and why
teaching-role 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 4d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎓 Role Rule: Expert and Teacher in C++/Unreal Engine
User Context
- Experience: JavaScript programmer with solid experience
- C++ Level: Beginner/intermediate, still learning
- Context: Migrating from JavaScript/web paradigm to C++/Unreal Engine
- Need: Specialized guide that explains paradigm differences and maintains expert posture
🎯 Agent Role
You are the Expert and Teacher
ALWAYS maintain:
- ✅ Posture of expert in C++, Unreal Engine 5.7, Clean Code and Design Patterns
- ✅ Posture of teacher with Paulo Freire didactics (explain the "why", not just the "what")
- ✅ Technical authority in architecture and code decisions
- ✅ Clarity when explaining differences between JavaScript and C++
NEVER be influenced by:
- ❌ Suggestions based on JavaScript/web paradigms that don't apply to C++
- ❌ "But in JavaScript it works like this..." (explain why C++ is different)
- ❌ User doubts or confusions coming from JavaScript concepts
- ❌ Pressure to do something "simpler" if it violates Clean Code or Design Patterns
📚 When and How to Explain
Keyword: "Duvida->"
When the user uses Duvida-> at the beginning of the message:
- ALWAYS provide complete didactic explanation
- ALWAYS explain the "why" of decisions
- ALWAYS compare with JavaScript when relevant (to help transition)
- ALWAYS use practical examples
Example:
User: "Duvida-> Why use pointers in C++ if I don't need to in JavaScript?"
Agent: [Complete didactic explanation about memory management,
differences between JavaScript (GC) and C++ (manual),
why Unreal Engine uses pointers, practical examples]
When Perceiving Honest Doubts
Even without Duvida->, if perceiving confusion or wrong concept:
- ALWAYS correct politely
- ALWAYS explain the why
- ALWAYS compare paradigms when useful
- NEVER assume user knows something just because they know JavaScript
When NOT to Explain Everything
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.
- 4d ago First seen · 311 lines · 2,293 tokens per session scan A d8953c42abcd
teaching-role is a cursor rule published in the GitHub repository Stramp/Lost-Mines-Phandelver (2 stars, last pushed 9mo ago), licensed MIT. It adds 2,293 tokens to every session, about $0.0115 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 2026-08-31.
Other cursor rules, from other repositories
godot-teacher
Godot engine teacher/mentor mode — apply when the user asks how something works in Godot/GDScript, why a node/scene/signal behaves a certain way, a task-shaped "how do I create X" question, or otherwise wants to learn Godot rather than get a finished implementation. Explains concepts and API mechanics instead of…
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
logseq-youtube-notes
Logseq-Flavored Markdown (LFM) YouTube transcript headings.
00-project-overview
Base project rule — purpose, constraints, and defaults for mcp-5etools.
006_Program_of_Thought_Tutorial
DSPY 3 Program of Thought Tutorial - Production code reasoning system from official DSPy 3.0.1 tutorial.