agentmods.dev

godot-stagehand: Instructions file for Claude Code

CLAUDE.md

godot-stagehand CLAUDE.md is an instructions file for Claude Code from mrf/godot-stagehand. It costs 803 tokens per session, scanned A, original, MIT.

Development instructions for Godot Stagehand, a Go server and Godot add-on for controlling and testing games from outside the game. It covers the project structure, commands, scenarios, screenshots, and connections.

In plain words
What is it for?
Use it when building, running, testing, linting, or changing Godot Stagehand automation and its game add-on.
Why use it?
It explains how the server, game add-on, test scenarios, and visual comparisons fit together, reducing guesswork when modifying the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is mrf/godot-stagehand's own configuration. It tells Claude Code how to work on godot-stagehand itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything godot-stagehand configures →

not rated 8repo 6d ago A scan 803 tokens original MIT
View source ↗ mrf/godot-stagehand
Reuse

Borrowing it

Nothing to install: this file belongs to mrf/godot-stagehand. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mrf/godot-stagehand/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mrf/godot-stagehand

Made for: Claude Code.

Wrote 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.

agentmods badge for godot-stagehand CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mrf/godot-stagehand/claude-md.svg)](https://agentmods.dev/instructions/mrf/godot-stagehand/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mrf/godot-stagehand/claude-md"><img src="https://agentmods.dev/badge/instructions/mrf/godot-stagehand/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 803 This file is loaded in full into every session.
When invoked 803 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00803 $0.00803
Opus 5 $0.00402 $0.00402
Sonnet 5 $0.00161 $0.00161
Haiku 4.5 $0.00080 $0.00080

Measured 7d ago against content hash 103d28daff34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

godot-stagehand CLAUDE.md 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.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godot Stagehand

MCP server (Go) + Godot addon (GDScript) for external game automation and testing.

Architecture

  • main.go — entry point. No arguments = MCP stdio server (hard compatibility contract); any argument dispatches to setup, --version, or internal/cli
  • internal/mcpserver/ — MCP server, tool handlers
  • internal/cli/ — CLI frontend: one-shot commands + run <scenario>. A sibling of mcpserver, not built on it
  • internal/scenario/ — scenario model, validation, runner, JSON/JUnit/trace reporters — see docs/cli.md
  • internal/gwpop/ — shared action registry: action name → GWP method + validated params, typed failure kinds, the blocked-method list. Used by cli/scenario; mcpserver deliberately does not route through it
  • internal/visual/ — screenshot decode, baselines, pixel diff (shared by mcpserver and scenario)
  • internal/godotconn/ — WebSocket connection to Godot addon
  • internal/selector/ — Selector parsing and validation
  • addons/stagehand/ — GDScript addon (WebSocket server inside the game); the only authoritative copy — see docs/addon-sync-contract.md before editing testdata/test_project/addons/stagehand or examples/minimal-game/addons/stagehand directly
  • testdata/test_project/ — Minimal Godot project for integration tests

Build & Run

go build -o godot-stagehand .     # build
go run .                           # run

Test

go test ./...                      # all tests (no Godot needed)
go test ./internal/selector/       # selector tests only

# Real-Godot scenario runner gate (mirrors CI's scenario-smoke job)
GODOT_BIN=/path/to/godot go test -tags=godot -run '^TestScenarioRunner' .

Lint

go vet ./...

Conventions

  • Go: standard library style, internal/ for non-exported packages
  • GDScript: static typing, GDScript style guide, GdUnit4 for tests
  • WebSocket port: 26700 (configurable)
  • Activation guard: STAGEHAND_ENABLED=1 or --stagehand CLI flag
  • Protocol: JSON-RPC 2.0 over WebSocket (Godot Wire Protocol), version-negotiated at ping
  • Versions: internal/version/version.go is authoritative; bump with ./scripts/set-version.sh — see docs/versioning.md

Read the full file on GitHub · 71 lines

Changes

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.

  1. 7d ago First seen · 71 lines · 803 tokens per session scan A 103d28daff34

Subscribe to this mod's changes

godot-stagehand CLAUDE.md is an instructions file published in the GitHub repository mrf/godot-stagehand (8 stars, last pushed 6d ago), licensed MIT. It adds 803 tokens to every session, about $0.0040 per session on Opus 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 2026-08-31.

Game developmentgame-testinggdscriptgodotgodot-addongodot-enginemcp
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens