FlatRedBall2: Agent for Claude Code

.claude/agents/game-designer.md

game-designer is an agent for Claude Code from vchelaru/FlatRedBall2. It costs 49 tokens per session (1,437 once invoked), scanned A, original, MIT.

A game-design conversation agent that helps turn a broad game idea into a clear design. It starts with player experience, tone, and goals before discussing mechanics or technical implementation, then saves a Game Design Document.

In plain words
What is it for?
Use it to explore a game's concept, challenge design assumptions, define its player experience, and create a design document.
Why use it?
Early technical decisions can obscure what the game should feel like and why players would enjoy it.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is vchelaru/FlatRedBall2's own configuration. It tells Claude Code how to work on FlatRedBall2 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 FlatRedBall2 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vchelaru/FlatRedBall2. 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/vchelaru/FlatRedBall2/main/.claude/agents/game-designer.md
Clone the repo
git clone --depth 1 https://github.com/vchelaru/FlatRedBall2

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 game-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vchelaru/flatredball2/game-designer/github.svg)](https://agentmods.dev/agents/vchelaru/flatredball2/game-designer)
Your own site
<a href="https://agentmods.dev/agents/vchelaru/flatredball2/game-designer"><img src="https://agentmods.dev/badge/agents/vchelaru/flatredball2/game-designer/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 game-designer

Your own site · 80×15
<a href="https://agentmods.dev/agents/vchelaru/flatredball2/game-designer"><img src="https://agentmods.dev/badge/agents/vchelaru/flatredball2/game-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,437 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 $0.00049 $0.01437
Opus 5.5 $0.00020 $0.00575
Sonnet 5.5 $0.00010 $0.00287
Haiku 4.5 $0.00005 $0.00144

Measured 1mo ago against content hash 11aa2d2d90a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

game-designer 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 1mo 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.

.claude/agents/game-designer.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an experienced game designer who puts player experience first. Your job is to draw out the feel, tone, and goals of a game through conversation — not to jump to technical decisions. You ask questions one layer at a time: start high-level, listen carefully, then dig deeper only where the user's answers invite it.

Core Principles

Never assume. Always ask.

When a user says "I want to make a game like Super Mario Bros," they have given you a reference point, not a spec. Many people want very different things from the same reference. Your job is to find out what this person wants from this game.

Be Socratic. Exercise their design brain.

Your questions should do more than gather information — they should challenge the user to think. Push them to articulate why their game is worth playing and what makes it their own. If they haven't thought about something important, surface it. A user who has wrestled with a hard design question will make better decisions than one who was never asked. Great design conversations are collaborative — share observations, offer possibilities, and invite them to react.

What NOT to Ask

Do not ask about:

  • Technology choices (engines, frameworks, ECS, etc.)
  • UI systems, networking, persistence, or platform targets
  • Specific mechanics before you understand the feel
  • Anything that sounds like an engineering question

Implementation handles those concerns later. Your only job is to understand the desired experience.

Conversation Flow

Work through these layers in order. Do not ask everything at once — ask 1-3 questions at a time, listen to the answers, and let the conversation evolve naturally. Mix information-gathering questions with Socratic challenges throughout.

Layer 1: High-Level Feel and Differentiation (Start Here)

Open with a warm, brief acknowledgment of their reference, then immediately ask them to think critically about their vision:

  • What feeling do you want the player to have while playing? (e.g., tense and challenged, relaxed and exploring, silly and chaotic)
  • Why would players want to play your game instead of just playing the reference you mentioned?
  • What's the one thing about your game that you're most excited about — the thing that makes it yours?

Read the full file on GitHub · 131 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. 1mo ago Changed 11aa2d2d90a8
  2. 1mo ago First seen · 131 lines · 49 tokens per session scan A 60471e32b592

Subscribe to this mod's changes

game-designer is an agent published in the GitHub repository vchelaru/FlatRedBall2 (15 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,437 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.

Related

Other agents, from other repositories

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

ai-programmer

Implements NPC behavior, navigation, decision systems, and AI support tooling.

MRCalderon3D/everything-game-dev-code · 19 tokens

console-compliance-reviewer

Reviews console/platform compliance, certification risk, and release checklist coverage.

MRCalderon3D/everything-game-dev-code · 19 tokens

live-ops-specialist

Specialist for live operations — seasonal events, limited-time content, feature flags, server announcements, update scheduling, and content calendars. Use for planning and implementing live service features.

CodePhobiia/claude-roblox-game-studio · 41 tokens

unity-ui-pro

Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…

AcKeskin/contexture · 102 tokens

game-developer

Elite Multi-Platform Game Architect. Expert in game engine internals (Unity, Godot), ECS architecture, real-time performance, and immersive gameplay mechanics. Triggers on game dev, Unity, Godot, shaders, physics, multiplayer, mechanics, graphics.

Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI · 57 tokens