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.
git clone --depth 1 https://github.com/mrf/godot-stagehandWrote 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/plugins/mrf/godot-stagehand/claude-code)<a href="https://agentmods.dev/plugins/mrf/godot-stagehand/claude-code"><img src="https://agentmods.dev/badge/plugins/mrf/godot-stagehand/claude-code/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/plugins/mrf/godot-stagehand/claude-code"><img src="https://agentmods.dev/badge/plugins/mrf/godot-stagehand/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
godot-stagehand 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 yesterday.
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.
What it actually says
{
"name": "godot-stagehand",
"displayName": "Godot Stagehand",
"version": "0.5.1",
"description": "MCP server, agent skill and CLI for automating a running Godot game",
"author": { "name": "mrf" },
"homepage": "https://github.com/mrf/godot-stagehand",
"repository": "https://github.com/mrf/godot-stagehand",
"license": "MIT",
"keywords": ["godot", "game-testing", "automation", "mcp"],
"mcpServers": {
"stagehand": {
"command": "${CLAUDE_PLUGIN_ROOT}/bin/godot-stagehand",
"env": { "STAGEHAND_BINARY": "${user_config.binary_path}" }
}
},
"userConfig": {
"binary_path": {
"type": "file",
"title": "Stagehand binary (optional)",
"description": "Use this godot-stagehand binary instead of downloading the release that matches the plugin version. Leave empty for the default.",
"default": ""
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 65 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday Changed 3799b97b8caf
- 7d ago First seen · 26 lines scan A 383aed4bd523
godot-stagehand is a plugin published in the GitHub repository mrf/godot-stagehand (9 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-04.
Other plugins, from other repositories
unreal
Develop, test, and automate Unreal Engine 5.x projects (WIP). Covers PlayUnreal automation, Remote Control API, Automation Driver, and CI-friendly E2E flows.
unity-mcp-server
Claude Code skills for Unity MCP Server. Provides workflow-oriented guidance for C# editing, Scene/GameObject management, PlayMode testing, and Asset management using 108+ Unity automation tools.
openai-develop-web-game
Use when the agent 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. Originally from O.
game-qa
Verify browser-based game features through a PM-driven QA loop. Ships a project-agnostic runner + adapter skeleton + journey schema so projects onboard by copy-and-adapt, not natural-language reconstruction. Six skills covering request → plan → execute → review → rollup, plus the bootstrap that drops the framework…
gut-skill
Claude Code skill for the GUT (Godot Unit Testing) framework — test structure, assertions, doubles, async helpers, memory management, and CLI usage for GDScript.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.