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.
curl -O https://raw.githubusercontent.com/NAJEMWEHBE/unreal-ai-connection/main/CLAUDE.mdgit clone --depth 1 https://github.com/NAJEMWEHBE/unreal-ai-connectionWrote 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/instructions/najemwehbe/unreal-ai-connection/claude-md)<a href="https://agentmods.dev/instructions/najemwehbe/unreal-ai-connection/claude-md"><img src="https://agentmods.dev/badge/instructions/najemwehbe/unreal-ai-connection/claude-md/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.
<a href="https://agentmods.dev/instructions/najemwehbe/unreal-ai-connection/claude-md"><img src="https://agentmods.dev/badge/instructions/najemwehbe/unreal-ai-connection/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01867 | $0.01867 |
| Opus 5 | $0.00933 | $0.00933 |
| Sonnet 5 | $0.00373 | $0.00373 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
unreal-ai-connection CLAUDE.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 12d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unreal AI Connection — agent context
Read docs/HANDOFF.md before doing any substantive work. The "Closing notes from prior sessions" section at the bottom captures what the previous agent was carrying in working memory — the latest entry is the operative one for resuming.
Quick orientation (deeper detail in HANDOFF.md and ARCHITECTURE.md)
UE 5.7 plugin + Python bridge exposing editor automation to MCP-compliant clients (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 — the wire protocol is open MCP; the "Claude" in the repo name is decorative.
Where to look first for any change
- C++ handlers (106) —
UnrealAIConnection/Source/UnrealAIConnection/Private/MCP/Handlers/Handler_*.cpp, one per tool. Registered inUnrealAIConnectionModule.cpp(theReg.Register(...)block). - Bridge-side synthetic tools (37:
wait_for_events,get_camera_transform,set_camera_transform,screenshot_actor,compile_mod_pak,compile_mod_pak_direct,bulk_delete_assets,bulk_move_assets,bulk_rename_assets,bulk_duplicate_assets,bulk_inspect_assets,inspect_data_asset,inspect_sound_class,inspect_sound_submix,inspect_audio_bus,inspect_material_function,inspect_metasound,find_unused_assets,get_reference_chain,bulk_compile_blueprints,audit_blueprint_compile_status,find_actors_by_class,bulk_focus_actors,bulk_screenshot_actors,bulk_set_actor_property,compare_assets,bulk_set_console_variables,inspect_dependency_graph,bulk_fix_redirectors,marketplace_search,marketplace_import,convert_hdri_to_cubemap,sequencer_add_transform_keyframe,import_mesh,material_auto_remap,batch_capture_cameras,batch_spawn_from_csv) —bridge/unreal_ai_connection_bridge.py'sSYNTHETIC_TOOLSdict. - Tool catalog (kept in sync manually across three places) —
UnrealAIConnection/Resources/mcp_manifest.json,bridge/unreal_ai_connection_bridge.py'sTOOLSlist, anddocs/TOOLS.md. Thetests/test_manifest_sync.pysuite catches drift between the first two. - Architecture notes + UE 5.7 API gotchas —
docs/ARCHITECTURE.md. - Host-build runbook — top of
docs/HANDOFF.md(steps 1–6, PowerShell). Live verification on the host machine is the perpetual next step. - Per-tool JSON schemas + examples —
docs/TOOLS.md. - Restart-recovery procedure (use after a fresh OS install / C: format) —
docs/RESTART-RECOVERY.md. Step-by-step setup (git, gh, Node, Python, VS C++ workload, Codex CLI, Claude Code, UE 5.7) plus how to restore session memory fromdocs/session-memory-archive/. - Session memory archive —
docs/session-memory-archive/. Snapshot of Claude Code's per-project memory files (directives, conventions, operational gotchas) — survives format because it lives in the repo. Restore to~/.claude/projects/.../memory/post-recovery.
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.
- 12d ago First seen · 30 lines · 1,867 tokens per session scan A 3600e586389e
unreal-ai-connection CLAUDE.md is an instructions file published in the GitHub repository NAJEMWEHBE/unreal-ai-connection (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,867 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.
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.
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.
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).
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.
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.
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).