Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mrf/godot-stagehand/plugin install 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/skills/mrf/godot-stagehand/stagehand)<a href="https://agentmods.dev/skills/mrf/godot-stagehand/stagehand"><img src="https://agentmods.dev/badge/skills/mrf/godot-stagehand/stagehand/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/mrf/godot-stagehand/stagehand"><img src="https://agentmods.dev/badge/skills/mrf/godot-stagehand/stagehand.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.06277 |
| Opus 5.5 | $0.00026 | $0.02511 |
| Sonnet 5.5 | $0.00013 | $0.01255 |
| Haiku 4.5 | $0.00006 | $0.00628 |
Grade A, and why
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 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 — 622 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Godot Stagehand — Game Automation Skill
You are an expert at using the godot-stagehand MCP tools to launch, observe, and interact with Godot games. This skill teaches you how to automate any Godot game that has the Stagehand addon installed.
Architecture
Claude --stdio--> godot-stagehand (Go MCP server) --WebSocket:26700--> Godot Game
└── StagehandServer autoload
└── JSON-RPC command router
The MCP server runs as a child process of your agent client. With the Claude Code plugin, the plugin starts it for you; in other clients it is an mcpServers entry you configure. It connects to the Godot game's WebSocket server on port 26700 (configurable). The Stagehand addon runs inside Godot as an autoload singleton.
Prerequisites
- Godot game must have the
addons/stagehand/addon installed and enabled - Game must be launched with
--stagehandCLI flag ORSTAGEHAND_ENABLED=1environment variable - The
godot-stagehandMCP server must be connected: the Claude Code plugin provides it, other clients configure it in their MCP settings
First-time setup
If the project has no addons/stagehand/ directory yet, install the addon from the Godot project's root:
godot-stagehand setup .
With the Claude Code plugin, godot-stagehand is already on the Bash tool's PATH (the plugin's launcher is ${CLAUDE_PLUGIN_ROOT}/bin/godot-stagehand); it downloads the matching release binary on first use. setup copies the addon, enables the plugin, registers the StagehandServer autoload, and prints an MCP configuration snippet. Under the plugin, ignore that snippet: the plugin already connects the server, and adding a second entry makes every tool appear twice. Use godot-stagehand setup --force . to replace an older addon after an upgrade.
Tool Reference
Connection & Lifecycle
godot_launch
Launch a Godot game with stagehand enabled and connect to it.
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 · 622 lines · 65 tokens per session scan A 74cc34e866f8
stagehand is a skill published in the GitHub repository mrf/godot-stagehand (9 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 6,277 once invoked, about $0.0003 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 2026-10-04.
Other skills, from other repositories
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.
swallowtail-qa
Playtest Godot games and exported builds, capture frame spikes, compare QA baselines, and produce Swallowtail branded reports. Use for release QA and reusable game-specific test scenarios, not routine implementation-only unit tests.
godot-testing-qa
Domain skill — Run a sequence of runtime actions and assertions. Assert runtime node existence and properties. Assert visible runtime text. Compare two PNGs using bounded pixel sampling. Sample runtime performance for a bounded frame count. Return the latest runtime test report.
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.
test-playable-web-games
Test a playable browser game end to end with deterministic fixtures and real browser evidence. Use for gameplay QA, regression testing, controls, accessibility, responsive/mobile testing, save flows, console checks, performance smoke tests, and release verification.
threejs-qa-release
Verify and release Three.js browser games: playtest QA, automated bot playtests, mobile and responsive checks, production builds, static-hosting base paths, debug gating, bundle review, screenshots, visual regression baselines, canvas-pixel inspection with measured metrics, and release risk reports.