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 skills add ManageXR/claude-unity-bridge --skill skillgit 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/skills/managexr/claude-unity-bridge/skill)<a href="https://agentmods.dev/skills/managexr/claude-unity-bridge/skill"><img src="https://agentmods.dev/badge/skills/managexr/claude-unity-bridge/skill/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/skills/managexr/claude-unity-bridge/skill"><img src="https://agentmods.dev/badge/skills/managexr/claude-unity-bridge/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 324 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00053 | $0.03435 |
| Opus 5.5 | $0.00021 | $0.01374 |
| Sonnet 5.5 | $0.00011 | $0.00687 |
| Haiku 4.5 | $0.00005 | $0.00344 |
Grade A, and why
unity 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 1mo 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 — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Bridge Skill
Control Unity Editor operations from Claude Code using a reliable file-based communication protocol.
Overview
The Unity Bridge enables Claude Code to trigger operations in a running Unity Editor instance without network configuration or port conflicts. It uses a simple file-based protocol where commands are written to .unity-bridge/command.json and responses are read from .unity-bridge/response-{id}.json.
Key Features:
- Execute EditMode and PlayMode tests
- Trigger script compilation
- Refresh asset database
- Check editor status (compilation, play mode, etc.)
- Retrieve Unity console logs
- Control Play Mode (play, pause, step)
- Build projects (direct or custom pipeline)
Multi-Project Support: Each Unity project has its own .unity-bridge/ directory, allowing multiple projects to be worked on simultaneously.
Requirements
-
Unity Package: Install
com.mxr.claude-bridgein your Unity project- Via Package Manager:
https://github.com/ManageXR/claude-unity-bridge.git?path=package - See main package README for installation instructions
- Via Package Manager:
-
Unity Editor: Must be open with your project loaded
-
Python 3: The skill uses a Python script for reliable command execution
How It Works
The skill uses a CLI tool (unity-bridge) that handles:
- UUID generation for command tracking
- Atomic file writes to prevent corruption
- Exponential backoff polling for responses
- File locking handling
- Automatic cleanup of old response files
- Formatted, human-readable output
This approach ensures deterministic, rock-solid execution - the script is tested once and behaves identically every time, handling all edge cases (timeouts, file locking, malformed responses, etc.) without requiring Claude to manage these details in-context.
Usage
Basic Pattern
When you need to interact with Unity, use the CLI directly:
unity-bridge [command] [options]
All commands automatically:
- Generate a unique UUID for tracking
- Write the command atomically
- Poll for response with timeout
- Format output for readability
- Cleanup response files
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- pyproject.toml 1.8 KB
- README.md 4.5 KB
- references/COMMANDS.md 30 KB
- references/EXTENDING.md 26 KB
- requirements-dev.txt 270 B
- src/claude_unity_bridge/__init__.py 90 B runs code
- src/claude_unity_bridge/cli.py 38 KB runs code
- src/claude_unity_bridge/skill/references/COMMANDS.md 20 KB
- src/claude_unity_bridge/skill/references/EXTENDING.md 26 KB
- src/claude_unity_bridge/skill/SKILL.md 12 KB
- TESTING.md 5.6 KB
- tests/__init__.py 39 B runs code
- tests/test_cli.py 104 KB runs code
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.
- 1mo ago First seen · 560 lines · 53 tokens per session scan A 9ab5c0c21117
unity is a skill published in the GitHub repository ManageXR/claude-unity-bridge (21 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,435 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
i4h-workflow-train-rl
Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.
cdf-autonomous-vehicle-dataset-generation
Prepare payloads, run and monitor the Autonomous Vehicle Dataset Generation Airflow workflow, and inspect results for driving-clip retrieval and Cosmos3-Nano variants. Existing clips with no retrieval use cdf-video-data-augmentation; seed-image event or anomaly generation uses cdf-event-video-generation.
gamedev-multiplayer
Use when adding multiplayer or netcode to a game — client-server vs P2P, server authority and anti-cheat, state replication vs RPCs, prediction and reconciliation, lag compensation, plus Godot 4 / Unity NGO / Unreal wiring. NOT single-player gameplay (that is godot, unity, unreal), NOT matchmaking or server hosting…
gamedev-pathing
Use when making NPCs, enemies, or units navigate a level — grid vs waypoint vs navmesh, A/JPS, navmesh baking and agent radius, off-mesh links, steering, RVO crowd avoidance, and flow fields in Godot 4.x, Unity, Unreal. NOT collision response or character controllers (that is gamedev-physics), NOT aggro or difficulty…
game-design
Use when designing or repairing what makes a game fun — verbs and mechanics, moment-to-moment/session/meta loops, progression, economy faucets and sinks, difficulty curves, dominant strategies, juice, prototyping and scope. NOT engine code (that is godot), NOT story (that is game-storytelling), NOT level layout (that…
gamedev-physics
Use when working with a game engine's physics — rigid bodies, colliders, collision layers and masks, character controllers, joints, forces versus impulses, raycasts and shapecasts, or when a simulation is unstable (tunnelling, jitter, missed overlaps). Covers the Godot, Unity and Unreal equivalents. NOT rendering or…