FlatRedBall2: Skill for Claude Code

.claude/skills/automation-mode/SKILL.md

automation-mode is a skill for Claude Code from vchelaru/FlatRedBall2. It costs 73 tokens per session (2,119 once invoked), scanned A, original, MIT.

A debug-only control interface for a running FlatRedBall2 game, allowing an external program to send newline-delimited JSON commands. It can step frames, send input, inspect entity state, and force entity values; recorded sessions can use seeded randomness for repeatable runs.

In plain words
What is it for?
It helps automate game tests and debugging by controlling frames and input, reading game entities, changing their public values, and replaying deterministic sessions.
Why use it?
It lets an AI agent or script observe and drive a game through a defined text protocol instead of relying on manual play.

Skill 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/skills/automation-mode/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 automation-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/vchelaru/flatredball2/automation-mode.svg)](https://agentmods.dev/skills/vchelaru/flatredball2/automation-mode)
Your own site
<a href="https://agentmods.dev/skills/vchelaru/flatredball2/automation-mode"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/automation-mode.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,119 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00073 $0.02119
Opus 5 $0.00036 $0.01059
Sonnet 5 $0.00015 $0.00424
Haiku 4.5 $0.00007 $0.00212

Measured 3d ago against content hash 9ef949fcd30b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

automation-mode 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 3d 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/skills/automation-mode/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automation Mode in FlatRedBall2

Automation mode lets an external process control a running game via NDJSON (newline-delimited JSON) over stdin/stdout — one command per line in, one response per line out. The primary use case is AI agents that need to observe and interact with the game the way Playwright interacts with a browser.

Debug builds only. EnableAutomationMode() is a no-op in Release. This is intentional — automation mode exposes internal state and allows arbitrary value forcing.

Setup

// Game.Initialize, after base.Initialize():
FlatRedBallService.Default.EnableAutomationMode();

The call itself does nothing unless --frb-auto is present in the command-line args. Ship the call unconditionally; the flag controls activation.

dotnet run -- --frb-auto

That's the entire required wiring. Entities and their public properties are auto-discovered — no per-property registration.

Deterministic randomness

When automation activates, FlatRedBallService.Random is replaced with a deterministic GameRandom so recorded NDJSON sessions reproduce exactly. Pass an explicit seed to choose which run.

FlatRedBallService.Default.EnableAutomationMode(seed: 1234);
--frb-auto flag seed: param Result
absent (any) time-based — automation off, seed param ignored
present omitted seed 0
present 1234 seed 1234

The seed is only applied when --frb-auto activates automation; without the flag, ship-time seed values have no effect on a normal run.

Game code that constructs its own Random/GameRandom is not seeded by the engine — route gameplay randomness through FlatRedBallService.Random (or derive your own seed from it) if you want it included in the deterministic run.

Command Protocol

Each command is a JSON object terminated by \n. Each response is a JSON object on its own line, always containing ok and frame.

Command JSON
Step N frames {"cmd":"step"} or {"cmd":"step","count":5}
Key down/up {"cmd":"input","type":"key","key":"Space","down":true}
Gamepad button {"cmd":"input","type":"gamepad","player":0,"button":"A","down":true}
Gamepad axis {"cmd":"input","type":"axis","player":0,"axis":"LeftStickX","value":0.8}
Cursor (screen px) {"cmd":"input","type":"cursor","x":120,"y":80,"primary":true}
Cursor (world coords) {"cmd":"input","type":"cursor","x":0,"y":0,"space":"world","primary":true}
Query active screen {"cmd":"query","target":"screen"}
Query all entities {"cmd":"query","target":"entities"}
Query one entity type {"cmd":"query","target":"Player"}
Force a value {"cmd":"set","entity":"Player","prop":"X","value":100.0}
Screenshot next Draw {"cmd":"record_next_screenshot","path":"shot.png"}
Quit {"cmd":"quit"}

Read the full file on GitHub · 134 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. 3d ago First seen · 134 lines · 73 tokens per session scan A 9ef949fcd30b

Subscribe to this mod's changes

automation-mode is a skill published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 2,119 once invoked, about $0.0004 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.