Borrowing it
Nothing to install: this file belongs to ManageXR/claude-unity-bridge. 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/ManageXR/claude-unity-bridge/main/AGENTS.mdgit clone --depth 1 https://github.com/ManageXR/claude-unity-bridgeWrote 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/managexr/claude-unity-bridge/agents-md)<a href="https://agentmods.dev/instructions/managexr/claude-unity-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/managexr/claude-unity-bridge/agents-md.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 5.1 | $0.04674 | $0.04674 |
| Opus 5 | $0.02337 | $0.02337 |
| Sonnet 5 | $0.00935 | $0.00935 |
| Haiku 4.5 | $0.00467 | $0.00467 |
Grade A, and why
claude-unity-bridge AGENTS.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 7d 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 — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for Claude Unity Bridge
Project Overview
This is a Unity package (com.mxr.claude-bridge) that enables Claude Code to control Unity Editor operations via a file-based protocol. The package has two components:
- Unity Package - C# code that runs in Unity Editor, polls for commands, executes them
- Claude Code Skill - Python script + documentation that Claude uses to send commands
Key Architecture Decision: We use a deterministic Python script instead of in-context implementation because it guarantees consistent UUID generation, file handling, polling, and error handling across all Claude sessions.
Project Structure
Unity Package (package/)
Editor/- C# command implementations for UnityClaudeBridge.cs- Main coordinator, command dispatcherCommands/- Individual command implementations (ICommand interface)Models/- Request/Response data structures
Documentation/- Package documentationREADME.md- Package documentation and protocol specification
Claude Code Skill (skill/)
scripts/cli.py- THE CORE - Handles all command executionSKILL.md- Main documentation with YAML frontmatterreferences/- Extended documentationCOMMANDS.md- Complete command referenceEXTENDING.md- Guide for adding custom commands
tests/- pytest test suiteTESTING.md- Testing documentation
Dependencies
- Unity: 2021.3 or later (no additional Unity dependencies)
- Python: 3.8+ for the skill script (3.12 supported)
- pytest: For testing the Python script
- black/flake8: For code formatting and linting
- pre-commit: For git hooks
- GitHub Actions: CI/CD for skill tests
Setting Up Development Environment
# Install development dependencies
cd skill
pip install -r requirements-dev.txt
# Install pre-commit hooks (recommended)
pre-commit install
# Run pre-commit on all files (first time)
pre-commit run --all-files
Commands You Can Use
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.
- 7d ago First seen · 604 lines · 4,674 tokens per session scan A 03ecb9e6215a
claude-unity-bridge AGENTS.md is an instructions file published in the GitHub repository ManageXR/claude-unity-bridge (20 stars, last pushed 20d ago), licensed Apache-2.0. It adds 4,674 tokens to every session, about $0.0234 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
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).
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).
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.
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.