A project-specific rule set that gives an AI coding agent background about a Windows Unreal Engine project written in C++ and Blueprints.

Guiding changes to Unreal Engine source code, Blueprints, assets, configuration, tests, documentation, and commit messages according to the project's conventions.

It reduces guesswork by describing the project structure, coding expectations, testing rules, documentation style, and conditions that should stop execution.

ai-context — Cursor rule for Cursor by Stramp: A project-specific rule set that gives an AI coding…

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 rules/stramp/lost-mines-phandelver/ai-context

Clone the repo

git clone --depth 1 https://github.com/Stramp/Lost-Mines-Phandelver

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/stramp/lost-mines-phandelver/ai-context.svg)](https://agentmods.dev/rules/stramp/lost-mines-phandelver/ai-context)

Your own site

<a href="https://agentmods.dev/rules/stramp/lost-mines-phandelver/ai-context"><img src="https://agentmods.dev/badge/rules/stramp/lost-mines-phandelver/ai-context.svg" alt="Measured on agentmods" height="20"></a>

Per session 516 This file is loaded in full into every session.

When invoked 516 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.

Model	Per session	Once invoked
Fable 5	$0.00516	$0.00516
Opus 5	$0.00258	$0.00258
Sonnet 5	$0.00103	$0.00103
Haiku 4.5	$0.00052	$0.00052

Measured 3d ago against content hash ba359b832ead, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-context 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.

.cursor/rules/ai-context.mdc · 58 lines

What it actually says

AI Context

Project Information

Name: MyProject2
Engine: Unreal Engine 5.7
Platform: Windows (Win64)
Language: C++ and Blueprints
Structure: Standard Unreal Engine project

Important Directory Structure

Source/MyProject2/ - Main C++ code
Content/ - Assets (Blueprints, Textures, Models)
Config/ - Configuration files (.ini)
.cursor/rules/ - Cursor rules for the project

Project Conventions

Use rules in .cursor/rules/ as reference
CRITICAL: ALWAYS follow Clean Code and Design Patterns (see clean-code-mandatory.mdc)
CRITICAL: ALWAYS stop execution if request conflicts with architecture or code quality (see execution-guard.mdc)
ALWAYS use Conventional Commits format (see git-commits.mdc)
ALWAYS write tests for helper functions (see testing.mdc)
ALWAYS maintain expert/teacher posture in C++/Unreal (see teaching-role.mdc)
ALWAYS use collapsible sections in Markdown files (see markdown-organization.mdc)
Always follow Unreal Engine standards
Document complex code
Keep code clean and organized

⚠️ CRITICAL RULE - MAXIMUM PRIORITY ⚠️

ALWAYS apply Clean Code and Design Patterns in ALL situations
NEVER create "temporary" or "just for testing" code that violates these rules
ALWAYS place reusable helper functions in Utils/ or Helpers/
See complete rule at: .cursor/rules/clean-code-mandatory.mdc

When Suggesting Changes

ALWAYS explain the reason
ALWAYS consider impact on Blueprints
ALWAYS verify it compiles before suggesting
ALWAYS mention if rebuild is required

File Context

When working with files, consider:
- Project structure
- Established patterns
- Blueprint compatibility
- Performance (especially in hot paths)

Communication

Always respond in Brazilian Portuguese
Be clear and direct
Provide examples when useful
Explain complex concepts

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.

3d ago First seen · 58 lines · 516 tokens per session scan A ba359b832ead

Subscribe to this mod's changes

ai-context is a cursor rule published in the GitHub repository Stramp/Lost-Mines-Phandelver (2 stars, last pushed 9mo ago), licensed MIT. It adds 516 tokens to every session, about $0.0026 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.

Game development Memory and context

ai-context