Godogen: Skill for Claude Code

.claude/skills/godogen/SKILL.md

godogen is a skill for Claude Code from liangdabiao/Godogen. It costs 45 tokens per session (1,401 once invoked), scanned A, original, MIT.

A workflow for creating or updating complete Godot games from plain-language descriptions. Godot is a game engine, and the workflow covers planning, code, scenes, assets, and visual checks.

In plain words
What is it for?
It helps generate reference images, plan the game structure, create Godot scenes and assets, write GDScript, remove image backgrounds, make animated sprites, and capture screenshots or video for visual review.
Why use it?
It breaks a game request into manageable tasks and provides guidance for the different stages of building and checking the game.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable.

This is liangdabiao/Godogen's own configuration. It tells Claude Code how to work on Godogen 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 Godogen configures →

Reuse

Borrowing it

Nothing to install: this file belongs to liangdabiao/Godogen. 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/liangdabiao/Godogen/main/.claude/skills/godogen/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/liangdabiao/Godogen

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 godogen

README.md
[![agentmods](https://agentmods.dev/badge/skills/liangdabiao/godogen/godogen.svg)](https://agentmods.dev/skills/liangdabiao/godogen/godogen)
Your own site
<a href="https://agentmods.dev/skills/liangdabiao/godogen/godogen"><img src="https://agentmods.dev/badge/skills/liangdabiao/godogen/godogen.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,401 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 $0.00045 $0.01401
Opus 5 $0.00023 $0.00700
Sonnet 5 $0.00009 $0.00280
Haiku 4.5 $0.00005 $0.00140

Measured 8d ago against content hash 35a57fcc4e2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

godogen 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 8d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (tools/asset_gen.py, tools/find_loop_frame.py, tools/grid_slice.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/godogen/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Game Generator — Orchestrator

Generate and update Godot games from natural language.

Capabilities

Read each sub-file from ${CLAUDE_SKILL_DIR}/ when you reach its pipeline stage.

File Purpose When to read
visual-target.md Generate reference image Pipeline start
decomposer.md Decompose into task DAG After visual target
scaffold.md Architecture + skeleton After decomposition
asset-planner.md Budget and plan assets If budget provided
asset-gen.md Asset generation CLI ref When generating assets
rembg.md Background removal Only when an asset needs transparency removed
sprite-gen.md Sprite sheet animation generation When generating animated characters
task-execution.md Task workflow + commands Before first task
quirks.md Godot gotchas Before writing code
(godot-api skill) GDScript syntax ref When unsure about GDScript syntax
scene-generation.md Scene builders Targets include .tscn
test-harness.md Verification scripts Before test harness
capture.md Screenshot/video Before capture
visual-qa.md Visual QA (forked skill) After capture
android-build.md APK export User requests Android

Pipeline

User request
    |
    +- Check if PLAN.md exists (resume check)
    |   +- If yes: read PLAN.md, STRUCTURE.md, MEMORY.md -> skip to task execution
    |   +- If no: continue with fresh pipeline below
    |
    +- Generate visual target -> reference.png + ASSETS.md (art direction only)
    +- Analyze risks + define verification criteria -> PLAN.md
    +- Design architecture -> STRUCTURE.md + project.godot + stubs
    |
    +- If budget provided (and no asset tables in ASSETS.md):
    |   +- Plan and generate assets -> ASSETS.md + updated PLAN.md with asset assignments
    |
    +- Show user a concise plan summary (risk tasks if any, main build scope)
    |
    +- Execute (see Execution below)
    |
    +- If user requested Android app:
    |   +- Read android-build.md, add ETC2/ASTC to project.godot, create export_presets.cfg, export APK
    |
    +- Summary of completed game

Read the full file on GitHub · 118 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. 8d ago First seen · 118 lines · 45 tokens per session scan A 35a57fcc4e2d

Subscribe to this mod's changes

godogen is a skill published in the GitHub repository liangdabiao/Godogen (121 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,401 once invoked, about $0.0002 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 2026-08-30.