A project-starting workflow for game development, whether the folder is empty, partly built, or inherited from another developer.

Use it to create game-project scaffolding, set up a new project, onboard into an existing one, or check the project's current structure.

It helps turn scattered ideas or an unfamiliar game codebase into a clear next step without repeating work already done.

game-start — Skill for Claude Code by AlterLab-IEU/AlterLab

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add AlterLab-IEU/AlterLab_GameForge

Claude Code

/plugin install gameforge

Made for: Claude Code.

Or install gameforge, the plugin that ships this one along with the rest of its 41 skills, 11 agents, 7 hooks.

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/alterlab-ieu/alterlab_gameforge/game-start/github.svg)](https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-start)

Your own site

<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-start"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-start/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/alterlab-ieu/alterlab_gameforge/game-start"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,909 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 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.

Model	Per session	Once invoked
Fable 5.1	$0.00091	$0.05909
Opus 5.5	$0.00036	$0.02364
Sonnet 5.5	$0.00018	$0.01182
Haiku 4.5	$0.00009	$0.00591

Measured today against content hash ed7b2dba07e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

game-start scanned grade C 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 today.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

and rebase, and denies force-push, `reset --hard`, `rm -rf` and reading `.env` or keystores. If a

skills/workflows/game-start/SKILL.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AlterLab GameForge -- Project Setup and Onboarding

This is the front door of a GameForge project. In one pass it finds out where the project stands, wires the plugin into it so the hooks and other skills work, sets up version control the way the engine needs, connects Claude Code to the engine, and leaves a clear next step. It meets the project where it lives: an empty folder, a design doc with no code, or an inherited codebase all start here.

Two jobs, in this order:

Wire the project (always): .gameforge/project.json, production/session-state/active.md, .gitignore entries, a merged CLAUDE.md, Git and Git LFS, agent setup.
Assess the project (scaled to what exists): gaps, structure, and the next three actions.

When NOT to use me

The user wants...	Route to
Something playable tonight, built with an AI agent, minimal setup	`/gameforge:game-vibe-code` (offer the 2-minute wiring below first)
A 48-72 hour jam entry	`/gameforge:game-jam-mode`
A game idea, not a project	`/gameforge:game-brainstorm`
A deep engine choice debate	`/gameforge:game-technical-director` with `${CLAUDE_PLUGIN_ROOT}/docs/engine-comparison.md`
Documentation for code that already exists	`/gameforge:game-reverse-document`
"Which skill do I need?"	`/gameforge:game-help`

Critical Rules

Never overwrite. Existing CLAUDE.md, .gitignore, .gitattributes, .claude/settings.json and .gameforge/project.json are merged, never replaced. Show what you will add before writing.
Detect before prescribing. Read the project first. Do not assume an empty project or a tidy one.
Ask only what you cannot detect. If the engine is detectable, do not ask for it.
Re-runs are updates. If .gameforge/project.json exists, this is a re-run: show the current values, change only what the user asks, and re-check the wiring.
Localhost-only agent tooling. Every MCP server you suggest binds to 127.0.0.1. Tools that execute code (Blender MCP, engine scripting bridges) are arbitrary code execution; say so.
No destructive git. git init and git lfs setup only. Offer the first commit; do not make it without the user's OK.
Scope honesty. If the user describes a 200-hour game and three weekends, say so now, kindly, and route to /gameforge:game-scope-check.

Read the full file on GitHub · 358 lines

Files

What ships with it

3 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.

today Changed · +14 lines · -3 tokens per session scan A → C ed7b2dba07e0
2mo ago First seen · 344 lines · 94 tokens per session scan A 0dba2324889e

Subscribe to this mod's changes

game-start is a skill published in the GitHub repository AlterLab-IEU/AlterLab_GameForge (52 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 5,909 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Game development

game-start next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
game-startAlterLab-IEU/AlterLab_GameForge	Skill	52	yesterday	MIT	C	91	Claude Code
playtest-reportDonchitos/Claude-Code-Game-Studios	Skill	36k	18d ago	MIT	A	20	Claude Code
godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills	Skill	6.9k	9d ago	Apache-2.0	A	95	Claude Code
scenario-unreal-gameplayscenario-labs/skills	Skill	3.2k	yesterday	MIT	A	121	Claude Code
motionOpenDCAI/GameFactory-3A	Skill	1.0k	8d ago	Apache-2.0	A	0	Claude Code, Codex
unity-addressablesBesty0728/Unity-Skills	Skill	1.9k	yesterday	MIT	A	25	Claude Code, Codex
unity-manual-componentBesty0728/Unity-Skills	Skill	1.9k	yesterday	MIT	A	36	Claude Code, Codex

game-start