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 AlexeyPerov/Unity-Open-MCP --skill input-simulationgit 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/input-simulation)<a href="https://agentmods.dev/skills/alexeyperov/unity-open-mcp/input-simulation"><img src="https://agentmods.dev/badge/skills/alexeyperov/unity-open-mcp/input-simulation/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/alexeyperov/unity-open-mcp/input-simulation"><img src="https://agentmods.dev/badge/skills/alexeyperov/unity-open-mcp/input-simulation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02810 |
| Opus 5.5 | $0.00000 | $0.01124 |
| Sonnet 5.5 | $0.00000 | $0.00562 |
| Haiku 4.5 | $0.00000 | $0.00281 |
Grade A, and why
input-simulation 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Open MCP — Input Simulation Extension
Skill for AI agents testing a game in the Unity Editor by simulating input —
clicks, drags, swipes, key presses, and touches — through the unity-open-mcp
MCP server.
This domain is embedded in the bridge and opt-in. Its tool group is hidden from
ListToolsuntil the connected session activates it. The uGUI tools (pointer,step,probe,pointer3d) compile whencom.unity.uguiis present; the keyboard/touch tools compile whencom.unity.inputsystemis present. Callcapabilitiesto see which half is live.
Preconditions
- Unity Editor is open with the target project.
unity_open_mcp_pingreturnsconnected: true.- The
input-simulationtool group is activated:unity_open_mcp_manage_tools(action: "activate", group: "input-simulation"). Or use intent activation:unity_open_mcp_manage_tools(action: "activate_for", intent: "click and drag UI to test the game"). - Most tools need play mode (
pointer,key,touch,step,pointer3d). Enter it first:unity_open_mcp_editor_set_state(state: "play").probeis read-only and works in edit mode too — use it to build a click plan before entering play mode.
Tools
| Tool | Reach | Play mode? |
|---|---|---|
inputsim_pointer |
uGUI (EventSystem + ExecuteEvents) — click/drag/hover/submit on a named GameObject, object_id, or screen point |
yes |
inputsim_pointer3d |
3D / legacy — Physics.Raycast + OnMouseDown/OnMouseUp/OnMouseDrag SendMessage |
yes |
inputsim_key |
Input System keyboard device events (Keyboard.current) |
yes |
inputsim_touch |
Input System touch / swipe (Touchscreen.current) |
yes |
inputsim_step |
Advance N play-mode frames (EditorApplication.Step) |
yes |
inputsim_probe |
List active uGUI interactables (paths, ids, rects, interactable, occluded) | no (works in edit mode) |
All six are gate-free (IsMutating=false — input writes no assets).
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 Changed · +3 lines 02362c2c3460
- 1mo ago First seen · 191 lines · 0 tokens per session scan A d5ef3009e67e
input-simulation is a skill published in the GitHub repository AlexeyPerov/Unity-Open-MCP (17 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,810 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.
smoke-check
Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.
game-playtesting
Test a game end to end like a player across boot, controls, gameplay loops, UI, save state, failure recovery, rendering, audio, performance, and platform behavior. Use after game implementation or for regression investigation.
develop-web-game
Build or iterate on HTML/JS web games with Playwright input bursts, gameplay screenshots, state inspection, and console checks.
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.