hastur-operation-plugin: Skill for Claude Code

.claude/skills/godot-remote-executor/SKILL.md

godot-remote-executor is a skill for Claude Code from rayxuln/hastur-operation-plugin. It costs 228 tokens per session (7,349 once invoked), scanned A, original, MIT.

A remote-control workflow for running GDScript in a connected Godot editor or game. Godot is a tool for building games, and GDScript is its scripting language.

In plain words
What is it for?
Use it to create or modify scenes, change node properties, run editor operations, and inspect live game state such as physics, frame rate, input, and variables.
Why use it?
It lets an agent inspect or change a live Godot project through a broker connection instead of only editing files. It can target either the editor or the running game, depending on the task.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is rayxuln/hastur-operation-plugin's own configuration. It tells Claude Code how to work on hastur-operation-plugin 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 hastur-operation-plugin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rayxuln/hastur-operation-plugin. 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/rayxuln/hastur-operation-plugin/main/.claude/skills/godot-remote-executor/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rayxuln/hastur-operation-plugin

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-remote-executor

README.md
[![agentmods](https://agentmods.dev/badge/skills/rayxuln/hastur-operation-plugin/godot-remote-executor/github.svg)](https://agentmods.dev/skills/rayxuln/hastur-operation-plugin/godot-remote-executor)
Your own site
<a href="https://agentmods.dev/skills/rayxuln/hastur-operation-plugin/godot-remote-executor"><img src="https://agentmods.dev/badge/skills/rayxuln/hastur-operation-plugin/godot-remote-executor/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.

agentmods 80×15 button for godot-remote-executor

Your own site · 80×15
<a href="https://agentmods.dev/skills/rayxuln/hastur-operation-plugin/godot-remote-executor"><img src="https://agentmods.dev/badge/skills/rayxuln/hastur-operation-plugin/godot-remote-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 228 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00228 $0.07349
Opus 5 $0.00114 $0.03674
Sonnet 5 $0.00046 $0.01470
Haiku 4.5 $0.00023 $0.00735

Measured 9d ago against content hash a02c9332332f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

godot-remote-executor scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -H "Authorization: Bearer HASTUR_AUTH_TOKEN" HASTUR_BASE_URL/api/executors
.claude/skills/godot-remote-executor/SKILL.md · 627 lines

How it starts

The opening of the file, as written. The whole thing — 627 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godot Remote Executor

This skill enables you to execute arbitrary GDScript code on a running Godot editor or game runtime instance through the Hastur broker-server. The broker-server acts as a bridge: you send HTTP requests to it, and it forwards the code to a connected Hastur Executor (editor plugin or game runtime) via TCP.

Executors have a type field: "editor" for the editor plugin, "game" for the GameExecutor autoload running in the game process. Use type: "game" to target the live game runtime — useful for inspecting runtime state, scene tree, physics, FPS, input, and variables during gameplay.

Prerequisites

Before you begin, you need two things from the user:

  1. Auth token — The broker-server requires a Bearer token for authentication. Ask the user for it if not provided. It was printed to stdout when the broker-server started.
  2. Base URL — Defaults to http://localhost:5302. The user may specify a different host/port.

Store these for the duration of the conversation:

  • HASTUR_AUTH_TOKEN — the Bearer token
  • HASTUR_BASE_URL — defaults to http://localhost:5302

Step 0: Read GDScript Syntax Reference (Critical)

Before writing any GDScript code, read the GDScript syntax reference to avoid compilation errors. GDScript has Python-like indentation-based syntax but significant differences in typing, built-in types, and conventions.

Read this file first:

  • references/gdscript-syntax/gdscript_basics.rst.txt — The core language reference (~2900 lines). Covers syntax, types, control flow, functions, classes, signals, exports, and all language constructs.

This is the single most important thing you can do to reduce errors. GDScript has many subtle differences from Python:

  • Uses := for type inference (not :)
  • var x: int for typed variables
  • func not def
  • Indentation matters (tabs, not spaces)
  • @onready, @export, @tool annotations
  • Built-in types: Vector2, Vector3, Color, Dictionary, Array, etc.
  • String formatting with % operator or format() method
  • match instead of switch
  • No list comprehensions (use Array.map() / Array.filter())
  • for x in range(n) or for x in array
  • Signals declared with signal keyword
  • preload() and load() for resources

Read the full file on GitHub · 627 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 627 lines · 228 tokens per session scan A a02c9332332f

Subscribe to this mod's changes

godot-remote-executor is a skill published in the GitHub repository rayxuln/hastur-operation-plugin (239 stars, last pushed 5mo ago), licensed MIT. It adds 228 tokens to every session and 7,349 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.