ai-system

ai-system is a skill for Claude Code from bullish0x/GameStudio. It costs 22 tokens per session (4,979 once invoked), scanned A, original, MIT.

A system for programming how game characters and other entities behave. It uses finite-state machines, behavior trees, steering, pathfinding, and decision-making rules; a finite-state machine represents modes such as idle, chasing, and attacking.

In plain words
What is it for?
Use it to build enemy and NPC behavior, autonomous agents, steering and pathfinding, tactical decisions, and behavior updates that run at different frequencies based on importance.
Why use it?
It helps organize complicated game behavior so it stays separate from graphics and physics, remains configurable, and can be inspected when decisions go wrong.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to build enemy and NPC behavior, autonomous agents, steering and pathfinding, tactical decisions, and behavior updates that run at different frequencies based on importance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bullish0x/gamestudio/ai-system
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.

Any agent
npx skills add bullish0x/GameStudio --skill ai-system
Clone the repo
git clone --depth 1 https://github.com/bullish0x/GameStudio

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 ai-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/bullish0x/gamestudio/ai-system/github.svg)](https://agentmods.dev/skills/bullish0x/gamestudio/ai-system)
Your own site
<a href="https://agentmods.dev/skills/bullish0x/gamestudio/ai-system"><img src="https://agentmods.dev/badge/skills/bullish0x/gamestudio/ai-system/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.

agentmods 80×15 button for ai-system

Your own site · 80×15
<a href="https://agentmods.dev/skills/bullish0x/gamestudio/ai-system"><img src="https://agentmods.dev/badge/skills/bullish0x/gamestudio/ai-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,979 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 $0.00022 $0.04979
Opus 5 $0.00011 $0.02490
Sonnet 5 $0.00004 $0.00996
Haiku 4.5 $0.00002 $0.00498

Measured 9d ago against content hash 3890ea04df58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-system 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 9d 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.

.agents/skills/ai-system/SKILL.md · 829 lines

How it starts

The opening of the file, as written. The whole thing — 829 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI System

When to Use

Use this skill when:

  • Creating enemy AI
  • Implementing NPC behavior
  • Building autonomous agents
  • Creating steering and pathfinding
  • Implementing decision-making systems
  • Building tactical AI

Core Principles

  1. Separation of Logic: AI separate from rendering/physics
  2. Hierarchical Behavior: Break complex behaviors into simple tasks
  3. State-Driven: Use FSMs or behavior trees
  4. Performance-Aware: Update frequency based on importance
  5. Debuggable: Visualize AI state and decisions
  6. Data-Driven: Configure AI in data files

AI System Implementation

1. Finite State Machine (FSM)

// ai/StateMachine.ts
export interface State {
  name: string;
  onEnter?: (entity: Entity) => void;
  onUpdate?: (entity: Entity, deltaTime: number) => void;
  onExit?: (entity: Entity) => void;
}

export interface Transition {
  from: string;
  to: string;
  condition: (entity: Entity) => boolean;
}

export class StateMachine {
  private states = new Map<string, State>();
  private transitions: Transition[] = [];
  private currentState: State | null = null;

  addState(state: State): void {
    this.states.set(state.name, state);
  }

  addTransition(transition: Transition): void {
    this.transitions.push(transition);
  }

  start(stateName: string, entity: Entity): void {
    const state = this.states.get(stateName);
    if (!state) {
      console.warn(`State not found: ${stateName}`);
      return;
    }

    if (this.currentState?.onExit) {
      this.currentState.onExit(entity);
    }

    this.currentState = state;

    if (this.currentState.onEnter) {
      this.currentState.onEnter(entity);
    }
  }

  update(entity: Entity, deltaTime: number): void {
    if (!this.currentState) return;

    // Update current state
    if (this.currentState.onUpdate) {
      this.currentState.onUpdate(entity, deltaTime);
    }

    // Check transitions
    for (const transition of this.transitions) {
      if (transition.from === this.currentState.name && transition.condition(entity)) {
        this.start(transition.to, entity);
        break;
      }
    }
  }

  getCurrentStateName(): string | null {
    return this.currentState?.name ?? null;
  }
}

Read the full file on GitHub · 829 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. 9d ago First seen · 829 lines · 22 tokens per session scan A 3890ea04df58

Subscribe to this mod's changes

ai-system is a skill published in the GitHub repository bullish0x/GameStudio (11 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 4,979 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

game-development

Game development with Unity, Unreal Engine, and Godot. Use when building games, implementing game mechanics, physics, AI, or working with game engines.

travisjneuman/.claude · 34 tokens

ar-vr-xr

AR/VR/XR development with Unity XR, WebXR, ARKit, ARCore, Meta Quest SDK, and spatial computing. Use when building augmented reality, virtual reality, mixed reality applications, or spatial experiences.

travisjneuman/.claude · 50 tokens

sdf

SDFormat/SDF model and world authoring, validation, and simulator handoff. Use for .sdf files, SDFormat XML, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh URIs, sensors, lights, physics, plugins, includes, Gazebo, static SDF review, or simulator-specific metadata. Do not use…

earthtojake/text-to-cad · 88 tokens

unity-agent-workflows

Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…

hashgraph-online/awesome-codex-plugins · 146 tokens

using-bgs-archive

Use when the user wants to inspect, list, extract, unpack, or repack Bethesda BA2/BSA archives; determine archive format/version/compression; or build archive assets for an MO2 overlay. Triggers - "unpack BA2", "extract BSA", "pack archive", "inspect archive", "bgs-archive".

hashgraph-online/awesome-codex-plugins · 75 tokens

ai-ml-development

AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.

travisjneuman/.claude · 43 tokens