agentmods.dev

unreal-ai-connection: Instructions file for GitHub Copilot

.github/copilot-instructions.md

unreal-ai-connection copilot-instructions.md is an instructions file for GitHub Copilot from NAJEMWEHBE/unreal-ai-connection. It costs 1,862 tokens per session, scanned A, original, MIT.

Code-review instructions for an Unreal Engine plugin and Python bridge that let AI clients automate the Unreal editor through MCP, an open protocol for connecting AI tools to software.

In plain words
What is it for?
Use them when reviewing changes to the plugin, bridge, or its many editor-automation tools.
Why use it?
They focus reviews on the repository's established error handling, path rules, and handler patterns instead of generic suggestions.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

This is NAJEMWEHBE/unreal-ai-connection's own configuration. It tells GitHub Copilot how to work on unreal-ai-connection itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unreal-ai-connection configures →

not rated 9repo 1mo ago A scan 1,862 tokens original MIT
View source ↗ NAJEMWEHBE/unreal-ai-connection
Reuse

Borrowing it

Nothing to install: this file belongs to NAJEMWEHBE/unreal-ai-connection. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NAJEMWEHBE/unreal-ai-connection/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/NAJEMWEHBE/unreal-ai-connection

Made for: GitHub Copilot.

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.

agentmods badge for unreal-ai-connection copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/najemwehbe/unreal-ai-connection/copilot-instructions/github.svg)](https://agentmods.dev/instructions/najemwehbe/unreal-ai-connection/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/najemwehbe/unreal-ai-connection/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/najemwehbe/unreal-ai-connection/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for unreal-ai-connection copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/najemwehbe/unreal-ai-connection/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/najemwehbe/unreal-ai-connection/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,862 This file is loaded in full into every session.
When invoked 1,862 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01862 $0.01862
Opus 5 $0.00931 $0.00931
Sonnet 5 $0.00372 $0.00372
Haiku 4.5 $0.00186 $0.00186

Measured 10d ago against content hash b54782e1d936, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

unreal-ai-connection 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 10d 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/copilot-instructions.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot review instructions — Unreal AI Connection

GitHub Copilot, when invoked as a PR reviewer on this repository, should review under the constraints below. These mirror the conventions already applied by the human + Codex + Gemini review loop; align with them rather than re-litigating settled patterns.

What this repo is

A UE 5.7 plugin + Python bridge exposing editor automation to any MCP-compliant client (Claude Code, Codex CLI, Cursor, Gemini CLI, Continue, …) over a localhost TCP socket. 151 tools total: 114 native C++ handlers + 37 bridge-side synthetic tools. Vendor-neutral by design — the wire protocol is open MCP.

Top-level read-first: docs/HANDOFF.md (resumption context), docs/ARCHITECTURE.md (UE 5.7 API gotchas), docs/TOOLS.md (per-tool JSON examples).

Review priorities (in order)

  1. Cross-handler consistency. Every Inspect* handler shares a shape — error format, path normalization, asset-loading helper, field-name conventions. Catch deviations:

    • Error format: "<tool>: <stable_code>: <human detail>" with '%s'-quoted path values (single-quoted; not bare %s).
    • Path normalization: UCMCPAssetPath::ToObjectPath(InputPath) — never reimplement.
    • Asset load: UEditorAssetLibrary::LoadAsset(ObjectPath) — never StaticLoadObject or LoadObject<T> (HANDOFF trap-table line 131).
    • Asset references in result fields: Asset->GetPathName() — never GetClass()->GetName() (PR #51 lesson, returns class taxonomy not asset identity).
    • Bounds shape: {min, max, size, center} across all handlers (inspect_static_mesh sets the precedent).

  2. UE 5.7 access modifiers. Direct field access on UE classes is a common defect class:

    • Bitfield flags (uint8 : 1) use explicit != 0 for unambiguous bool conversion (PR #70 lesson).
    • Always check access modifier before direct field read. Recent failures: USoundCue::SubtitlePriority is protected, MaxAudibleDistance is private (PR #76 → cleanup #79). USoundWave::SampleRate / ImportedSampleRate are protected (PR #77 → cleanup #78). Always prefer the public GetX() accessor method.
    • WITH_EDITORONLY_DATA fields must be guarded with #if WITH_EDITORONLY_DATA.
    • Forward-declared types tripping -> access need full include (e.g. Animation/AnimNotifies/AnimNotifyState.h, not Animation/AnimNotifyState.h — different subdir; cleanup PR #80 lesson).

Read the full file on GitHub · 139 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. 10d ago First seen · 139 lines · 1,862 tokens per session scan A b54782e1d936

Subscribe to this mod's changes

unreal-ai-connection copilot-instructions.md is an instructions file published in the GitHub repository NAJEMWEHBE/unreal-ai-connection (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,862 tokens to every session, about $0.0093 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.

Claude CodeCode reviewllm-toolsmcpmodel-context-protocolunreal-engine
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens