ship-godot-game

ship-godot-game is a skill for Claude Code, Codex from beremaran/godot-agent-loop. It costs 65 tokens per session (1,027 once invoked), scanned A, original, MIT.

A release-checking guide for preparing a Godot 4 game for export, which turns the project into a playable build for a target platform.

In plain words
What is it for?
Use it to inspect exports, tests, C# or .NET projects, add-ons, imported files, release artifacts, smoke tests, signing, and platform readiness in Godot 4.7 or later.
Why use it?
It checks release requirements and reports missing templates, software, signing credentials, devices, or other blockers instead of treating them as successful.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the godot-agent-loop plugin — 4 skills, 1 MCP server shipped together

Good fit Use it to inspect exports, tests, C# or .NET projects, add-ons, imported files, release artifacts, smoke tests, signing, and platform readiness in Godot 4.7 or later.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/beremaran/godot-agent-loop/ship-godot-game
Install

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.

Any agent
npx skills add beremaran/godot-agent-loop --skill ship-godot-game
Clone the repo
git clone --depth 1 https://github.com/beremaran/godot-agent-loop

Made for: Claude Code, Codex.

Or install godot-agent-loop, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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 ship-godot-game

README.md
[![agentmods](https://agentmods.dev/badge/skills/beremaran/godot-agent-loop/ship-godot-game/github.svg)](https://agentmods.dev/skills/beremaran/godot-agent-loop/ship-godot-game)
Your own site
<a href="https://agentmods.dev/skills/beremaran/godot-agent-loop/ship-godot-game"><img src="https://agentmods.dev/badge/skills/beremaran/godot-agent-loop/ship-godot-game/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 ship-godot-game

Your own site · 80×15
<a href="https://agentmods.dev/skills/beremaran/godot-agent-loop/ship-godot-game"><img src="https://agentmods.dev/badge/skills/beremaran/godot-agent-loop/ship-godot-game.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,027 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00065 $0.01027
Opus 5 $0.00032 $0.00513
Sonnet 5 $0.00013 $0.00205
Haiku 4.5 $0.00006 $0.00103

Measured 11d ago against content hash abe6cb22cf47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ship-godot-game 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 11d 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.

agent-plugin/skills/ship-godot-game/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship a Godot game

Treat shipping as an evidence gate. Preserve the project and release artifacts; never turn an unavailable platform, signing identity, export template, SDK, toolchain, or target device into a passing claim. Support begins at Godot 4.7.

Control contract

  • Validate projectPath, artifact destinations, and local sources against the effective MCP roots and allowed directories before access or mutation.

  • Record whether release verification is watched or unattended. For watched work, call editor_session with ensure and launch enabled; stop if a usable editor cannot be established rather than silently continuing detached. For unattended release work, do not launch an editor; use direct and hidden inspection/runtime tools so readiness checks do not alter project metadata.

  • Keep inspection read-only until the user authorizes a repair, export, signing, addon/import change, or other release mutation. Distinguish persistent project changes, runtime-ephemeral playtest state, process lifecycle, and deliverables.

  • Use canonical core tools directly (compact is only the compatibility alias). Resolve hidden analyze_project_integrity, verify_export_readiness, manage_import_pipeline, verify_dotnet_project, and manage_addon through godot_catalog detail, then invoke them with godot_call; never call a hidden tool directly.

  • The wrapper field is exactly toolName, not name or tool. Use godot_catalog like this:

    { "action": "describe", "toolName": "verify_export_readiness", "detail": "full" }
    

    Then dispatch through godot_call like this:

    { "toolName": "verify_export_readiness", "arguments": { "projectPath": "...", "action": "inspect", "presetName": "Local Eval" } }
    
  • Respect Pause Agent without retry or bypass. While paused, retain inspection, input release, stop, and cleanup; report any blocked effective mutation.

  • Use privileged reflection or evaluation only when already enabled and necessary for a release criterion. Never enable it to manufacture missing evidence.

Read the full file on GitHub · 80 lines

Files

What ships with it

1 file 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. 11d ago First seen · 80 lines · 65 tokens per session scan A abe6cb22cf47

Subscribe to this mod's changes

ship-godot-game is a skill published in the GitHub repository beremaran/godot-agent-loop (5 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,027 once invoked, about $0.0003 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.