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 agentmods add skills/alexeyperov/unity-open-mcp/inputsystemnpx skills add AlexeyPerov/Unity-Open-MCP --skill inputsystemgit clone --depth 1 https://github.com/AlexeyPerov/Unity-Open-MCPWrote 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/alexeyperov/unity-open-mcp/inputsystem)<a href="https://agentmods.dev/skills/alexeyperov/unity-open-mcp/inputsystem"><img src="https://agentmods.dev/badge/skills/alexeyperov/unity-open-mcp/inputsystem.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 | $0.00000 | $0.01768 |
| Opus 5 | $0.00000 | $0.00884 |
| Sonnet 5 | $0.00000 | $0.00354 |
| Haiku 4.5 | $0.00000 | $0.00177 |
Grade A, and why
inputsystem 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 4d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Open MCP — Input System Extension
Skill for AI agents driving the Unity Input System in a project through the unity-open-mcp MCP server.
This domain is embedded in the bridge and opt-in. Its tools compile in only when the project has
com.unity.inputsysteminstalled (the bridge sets theUNITY_OPEN_MCP_EXT_INPUTSYSTEMdefine automatically). Its tool group is hidden fromListToolsuntil the connected session activates it.
Preconditions
- Unity Editor is open with the target project.
unity_open_mcp_pingreturnsconnected: true.- The project has
com.unity.inputsysteminstalled. Ifcapabilitiesreports theinput-systemgroup asavailable: false, install the package and let the bridge recompile. - The
input-systemtool group is activated — callunity_open_mcp_manage_tools(action="activate", group="input-system")before invoking anyinputsystem_*tool. Fresh sessions start with two default-on groups (coreandgate-and-verify); activate the other groups you need on demand. - The Unity project has
com.unity.inputsystemavailable. ProjectSettings/ProjectSettings.assethasactiveInputHandlerset to a valid value:0(Old Input Manager),1(Input System only), or2(Both). A value of-1(Unity's "not configured" sentinel) makes the Input System throwArgumentException: Invalid value of 'activeInputHandler' setting: -1in its static constructor on every editor update, which blocks the bridge from loading. If you see that exception inread_compile_errors/ the console, setactiveInputHandler: 2directly in the asset file (or usesettings_set_playerwithactiveInputHandling: "both"once the bridge is up).
Tool prefix
All tools in this pack use unity_open_mcp_inputsystem_*. Mutating tools target a .inputactions asset path — every mutator runs the full gate path with paths_hint scoped to that asset; the read-only tool (inputsystem_get) is gate-free.
What is an InputActionAsset?
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.
- 4d ago First seen · 119 lines · 0 tokens per session scan A 0fc4e8fe78d8
inputsystem is a skill published in the GitHub repository AlexeyPerov/Unity-Open-MCP (11 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,768 tokens. 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 skills, from other repositories
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
reversi-master
One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code (Moonshot) ,Qwen Code,Aider,OpenCode,MiMo Code (Xiaomi),ZCode (Z.AI),OpenClaw,Pi,OpenScience,Vibe-Trading,Claude Desktop (3P profile),ChatGPT desktop,OpenCode Desktop.
openloomi-pet
OpenLoomi Pet sprite & state helper for Claude Code. Use when the user wants to change their Loomi Pet state, switch theme, drop in a custom character, override individual sprites, or ask Claude to mirror its lifecycle onto the pet. Triggers: pet state, /openloomi:pet, set pet, loomi pet, pet to happy, pet to working…
character-animation-qa
Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.
pose-library-design
Design reusable 2D character pose libraries, action cycles, and expression states for data-driven animation.
octocode-mannequin
Use when posing, animating, or explaining a 3D human skeleton/manikin: anatomical joints, ROM clamps, walk/run/dance/backflip sequences, Three.js viewer, or agent-driven WebMCP figure control (reach/lookat). Phrases like pose the manikin, skeleton scheme, animate a walk cycle. Not for general 3D scenes…