What is autonomous-game-pipeline?

A workflow for having an agent build complete games from natural-language descriptions using Godot 4, Bevy, or Babylon.js. It creates code and assets, runs the game, and records a video showing the result.

It helps prototype playable games, create scenes and assets, verify builds with screenshots or runs, and produce gameplay proof videos.

It organizes the many steps of game creation, from planning and asset generation to building and checking the running game. Saved plans and memory help the work continue after interruption.

autonomous-game-pipeline — Skill for Claude Code and Codex by jxoesneo

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 jxoesneon/Ciel --skill autonomous-game-pipeline

Clone the repo

git clone --depth 1 https://github.com/jxoesneon/Ciel

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jxoesneon/ciel/autonomous-game-pipeline/github.svg)](https://agentmods.dev/skills/jxoesneon/ciel/autonomous-game-pipeline)

Your own site

<a href="https://agentmods.dev/skills/jxoesneon/ciel/autonomous-game-pipeline"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/autonomous-game-pipeline/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jxoesneon/ciel/autonomous-game-pipeline"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/autonomous-game-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,209 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.01209
Opus 5	$0.00020	$0.00605
Sonnet 5	$0.00008	$0.00242
Haiku 4.5	$0.00004	$0.00121

Measured 7d ago against content hash c9ff5b41bc15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

autonomous-game-pipeline 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.

skills/autonomous-game-pipeline/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CIEL ADAPTATION: Autonomous Game Generator

Generates complete games from natural language descriptions across Godot 4 (C#/.NET), Bevy (Rust), and Babylon.js (TypeScript). The agent builds the project, generates assets via paid APIs, runs the engine, and proves the result with a recorded gameplay video.

Risk note: Ciel's risk classifier gates autonomous execution as high → Council. Ciel's SANDBOX.md enforces acquisition-time isolation for Tier 3 sources. This skill declares side effects; Ciel's runtime handles execution gating — sandbox requirements are NOT baked into this body.

Pipeline

Resume check: If PLAN.md exists, read PLAN.md + STRUCTURE.md + MEMORY.md → skip to task execution.
Fresh pipeline: Generate visual target → reference.png + ASSETS.md (art direction only).
Risk analysis: Define verification criteria → PLAN.md.
Architecture: Design → STRUCTURE.md + project.godot + stubs.
Asset generation (if budget provided, no asset tables in ASSETS.md): Plan + generate → updated PLAN.md.
Task loop: Pick next task → implement (code/assets/scenes) → verify (build/run/screenshot) → update PLAN.md + MEMORY.md.
Proof: Capture 15–20s gameplay video → visual QA (multimodal review) → deliver.

Engine Guides

Godot 4 (engines/godot.md): C#/.NET, Jolt Physics, build-time scene generation.
Bevy (engines/bevy.md): Rust, ECS, code-first scenes.
Babylon.js (engines/babylon.md): TypeScript/Vite, browser-served.

Read the appropriate guide before writing any engine-specific code.

Asset Generation (Paid APIs — confirm spend before first run)

Gemini: Precise references, characters — 5–15¢/image.
xAI Grok: Textures, simple objects — 2¢/image.
Tripo3D: Image-to-3D GLB — 30–60¢/model; rigged biped +25¢; animation clips 10¢/clip.
Grok Video: Animated sprites — 5¢/second.

Key Principles

Proof over claims: Judge progress from the running game, never a clean build.
Visual QA closes the loop: Capture screenshots; multimodal review catches defects.
Scenes generated at build time: C# SceneTree scripts emit .tscn, not hand-authored.
Silent-failure awareness: Godot serialization drops nodes without errors; validate packs.
Asset manifest: Track every asset with an in-game Size column in README.md.

Read the full file on GitHub · 79 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.

7d ago First seen · 79 lines · 40 tokens per session scan A c9ff5b41bc15

Subscribe to this mod's changes

autonomous-game-pipeline is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,209 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 2026-09-03.

Autonomous Game development agentic-workflows ai asset-generation babylon bevy ciel domain:ai godot harmonized procedural

swallowtail

Use the complete Godot development loop from the swallowtail CLI: discover the live engine API, build and edit in the open editor, run and play the game, observe state, debug failures, fix them in place, and verify the result. Use when the task involves creating or modifying a Godot project, testing game behavior…

regiellis/godot-mcp-go · 0 tokens

balance-check

Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.

striderZA/OpenCodeGameStudios · 61 tokens

autonomous-game-pipeline