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.
curl -O https://raw.githubusercontent.com/vchelaru/FlatRedBall2/main/.claude/skills/automation-mode/SKILL.mdgit clone --depth 1 https://github.com/vchelaru/FlatRedBall2Wrote 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.
[](https://agentmods.dev/skills/vchelaru/flatredball2/automation-mode)<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>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.02119 |
| Opus 5 | $0.00036 | $0.01059 |
| Sonnet 5 | $0.00015 | $0.00424 |
| Haiku 4.5 | $0.00007 | $0.00212 |
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.
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"} |
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.
- 3d ago First seen · 134 lines · 73 tokens per session scan A 9ef949fcd30b
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.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.