FlatRedBall2: Skill for Claude Code

.claude/skills/orchestrator/SKILL.md

orchestrator is a skill for Claude Code from vchelaru/FlatRedBall2. It costs 62 tokens per session (3,287 once invoked), scanned A, original, MIT.

A workflow for designing and building a small retro game in the FlatRedBall2 2D game engine. It delegates the coding work to another agent, builds the game, and reports problems encountered.

In plain words
What is it for?
Use it to create a user-specified or random minigame, have a coding agent implement it, build the result, and identify development friction.
Why use it?
It gives a structured way to test whether the engine's documentation and tools are sufficient for making a game. It also makes the required files and handoff steps explicit.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents.

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/skills/orchestrator/SKILL.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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/vchelaru/flatredball2/orchestrator.svg)](https://agentmods.dev/skills/vchelaru/flatredball2/orchestrator)
Your own site
<a href="https://agentmods.dev/skills/vchelaru/flatredball2/orchestrator"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,287 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 $0.00062 $0.03287
Opus 5 $0.00031 $0.01643
Sonnet 5 $0.00012 $0.00657
Haiku 4.5 $0.00006 $0.00329

Measured yesterday against content hash c57a4c43f117, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

orchestrator 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 yesterday.

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/orchestrator/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Minigame Orchestrator

See content-boundary skill first. Orchestrated games must scaffold placeholder content files (TMX, Gum screens, coefficients JSON) and close with an explicit handoff telling the user which files to open in which tools. Do not hardcode levels, UI composition, or tunable values in C#.

Test the FlatRedBall2 engine's AI-usability by designing and implementing a small retro game, then reporting friction.

Critical constraint: Do NOT read existing samples (samples/), unit tests (tests/), or any game code outside src/ and the current project being built. The only resources available are: engine source code (src/), XML docs, skill files (frb-skills/ for game-dev skills, .claude/skills/ for engine-contributor skills), and templates (.claude/templates/). This applies to you AND to the coder agent you delegate to. The whole point of this evaluation is to test whether the engine's docs and skills are sufficient — looking at other samples defeats the purpose.

Pipeline

Execute these steps in order. Do not skip any step.

Step 1: Pick a Game

Determine which starting condition applies:

A. User provided a game design — Accept it as-is and skip to Step 3. Do not re-design or second-guess it.

B. User specified a game name/title — Use that game and proceed to Step 2.

C. No input — Choose a random game from the Atari 2600 or NES era. Aim for variety — avoid games that are structurally identical to common genres (e.g., don't always pick platformers). Examples: Frogger, Asteroids, Breakout, Galaga, Pac-Man, Donkey Kong, Dig Dug, Missile Command, Centipede, Joust, Balloon Fight, Ice Climber, Excitebike, Burger Time, Q*bert, Spy Hunter, River Raid, Pitfall, Moon Patrol.

Do NOT pick a game that already has a sample in samples/. Check first. (If the user explicitly requested a re-do of an existing game, delete the old project directory first.)

Complexity Levels

Default is Complexity 2 unless the user requests otherwise.

Read the full file on GitHub · 235 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. yesterday First seen · 235 lines · 62 tokens per session scan A c57a4c43f117

Subscribe to this mod's changes

orchestrator is a skill published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 3,287 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 2026-09-04.