Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/RamonBedin/mcp-game-deckWrote 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/plugins/ramonbedin/mcp-game-deck/plugin)<a href="https://agentmods.dev/plugins/ramonbedin/mcp-game-deck/plugin"><img src="https://agentmods.dev/badge/plugins/ramonbedin/mcp-game-deck/plugin/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.
<a href="https://agentmods.dev/plugins/ramonbedin/mcp-game-deck/plugin"><img src="https://agentmods.dev/badge/plugins/ramonbedin/mcp-game-deck/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-game-deck 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.
What it actually says
{
"name": "mcp-game-deck",
"version": "1.1.0",
"description": "Skills bundled with MCP Game Deck for Unity development workflows.",
"author": {
"name": "Ramon Bedin",
"url": "https://github.com/RamonBedin"
},
"homepage": "https://github.com/RamonBedin/mcp-game-deck",
"repository": "https://github.com/RamonBedin/mcp-game-deck",
"license": "MIT",
"keywords": [
"unity",
"game-development",
"mcp"
]
}What it installs
The manifest is a name and a version. 24 skills, 10 agents travel with it, and installing the plugin installs all of them — 1,004 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill refactor A 17 tokens
- Skill save-plan A 31 tokens
- Skill code-review A 30 tokens
- Skill new-feature A 16 tokens
- Skill create-command A 27 tokens
- Skill asset-audit A 26 tokens
- Skill balance-check A 28 tokens
- Skill bug-report A 24 tokens
- Skill design-review A 23 tokens
- Skill hotfix A 21 tokens
- Skill map-systems A 25 tokens
- Skill perf-profile A 25 tokens
- Skill playtest-report A 20 tokens
- Skill prototype A 24 tokens
- Skill reverse-document A 22 tokens
- Skill sprint-plan A 26 tokens
- Skill tech-debt A 29 tokens
- Skill architecture-decision A 22 tokens
- Skill estimate A 23 tokens
- Skill scope-check A 26 tokens
- Skill changelog A 16 tokens
- Skill new-system A 20 tokens
- Skill plan-execute A 23 tokens
- Skill brainstorm A 25 tokens
- Agent performance-analyst A 39 tokens
- Agent unity-specialist A 48 tokens
- Agent gameplay-programmer A 39 tokens
- Agent qa-lead A 40 tokens
- Agent unity-addressables-specialist A 43 tokens
- Agent unity-dots-specialist A 46 tokens
- Agent unity-shader-specialist A 48 tokens
- Agent unity-ui-specialist A 44 tokens
- Agent systems-designer A 42 tokens
- Agent technical-artist A 46 tokens
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.
- 1mo ago First seen · 17 lines scan A f76179caa18b
mcp-game-deck is a plugin published in the GitHub repository RamonBedin/mcp-game-deck (6 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
game-architecture
Game code architecture: game loops, ECS, event buses, data resources, service locators, scene management, and state stacks.
error-diagnostics
Error tracing, root cause analysis, and smart debugging for production systems.
godot
Develop, test, build, and deploy Godot 4.x games. Includes GdUnit4 testing, PlayGodot automation, web/desktop exports, CI/CD pipelines, and deployment.
bevy-skills
AI agent skills for Bevy 0.19: ECS, rendering, physics, input, assets, audio, accessibility, persistence, testing, profiling, voxels, and migration.
unity-ops
Verification gates and control-surface guardrails for driving Unity 6+ through the Unity CLI. Sits above Unity's first-party unity-cli skill; adds enforcement rather than restating it.
junoclaude
Design, build, program and flight-test craft in Juno: New Origins (SimpleRockets 2). Generates craft XML, compiles Vizzy flight programs, launches the game and reads its log. Use when the topic is Juno New Origins, SimpleRockets, Vizzy, building a rocket or plane, or testing a craft in-game.