A set of add-ons for game artificial intelligence, the systems that control computer-driven characters and decisions. It covers behavior trees, NPC systems, changing difficulty, and intelligent-agent design.

Use it to design behavior trees, NPC personalities, difficulty adjustment, and broader AI system structures.

It gathers several common game-AI design tasks in one toolkit. The provided details do not explain the exact workflow of each included add-on.

ai-systems — Plugin for Claude Code by sponticelli: A set of add-ons for game artificial intelligence, the…

Install

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.

Claude Code

/plugin marketplace add sponticelli/gamedev-claude-plugins

agentmods

npx agentmods add plugins/sponticelli/gamedev-claude-plugins/ai-systems

Clone the repo

git clone --depth 1 https://github.com/sponticelli/gamedev-claude-plugins

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/sponticelli/gamedev-claude-plugins/ai-systems.svg)](https://agentmods.dev/plugins/sponticelli/gamedev-claude-plugins/ai-systems)

Your own site

<a href="https://agentmods.dev/plugins/sponticelli/gamedev-claude-plugins/ai-systems"><img src="https://agentmods.dev/badge/plugins/sponticelli/gamedev-claude-plugins/ai-systems.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 4 commands, 3 agents cost 130 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

ai-systems 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 4d 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.

plugins/ai-systems/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "ai-systems",
  "description": "Game AI - behavior trees, NPC systems, dynamic difficulty, and intelligent agent design",
  "version": "1.2.0",
  "author": {
    "name": "GameDev Plugins"
  },
  "repository": "https://github.com/sponticelli/gamedev-claude-plugins",
  "license": "MIT",
  "agents": [
    "./agents/behavior-architect.md",
    "./agents/difficulty-adapter.md",
    "./agents/npc-personality-designer.md"
  ],
  "commands": [
    "./commands/behavior-tree.md",
    "./commands/npc-spec.md",
    "./commands/difficulty-curve.md",
    "./commands/ai-architecture.md"
  ]
}

Contents

What it installs

The manifest is a name and a version. 4 commands, 3 agents travel with it, and installing the plugin installs all of them — 130 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

4d ago First seen · 22 lines scan A 8a7c5f6f1fb2

Subscribe to this mod's changes

ai-systems is a plugin published in the GitHub repository sponticelli/gamedev-claude-plugins (15 stars, last pushed 7mo 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 2026-08-30.

Game development

godot

Develop, test, build, and deploy Godot 4.x games. Includes GdUnit4 testing, PlayGodot automation, web/desktop exports, CI/CD pipelines, and deployment.

Randroids-Dojo/skills · not measured

bevy-skills

AI agent skills for Bevy 0.19: ECS, rendering, physics, input, assets, audio, accessibility, persistence, testing, profiling, voxels, and migration.

chrisgliddon/bevy-skills · not measured

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.

AlexWortega/junoclaude · not measured

ai-systems