game-ai-patterns

game-ai-patterns is a skill for Claude Code from HermeticOrmus/claude-code-game-development. It costs 58 tokens per session (2,654 once invoked), scanned A, original, MIT.

A collection of game AI code patterns for NPCs, the characters controlled by the game rather than the player. It includes behavior trees, finite state machines, utility-based decisions, goal-oriented action planning, navigation, and field-of-view sensing.

In plain words
What is it for?
Use it when writing or reviewing NPC decision-making, pathfinding, navigation meshes, or what an NPC can see.
Why use it?
It gives concrete implementation patterns for common ways NPCs choose actions and move through a game world. This can reduce the need to design these decision and perception systems from scratch.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-game-behavior plugin — 1 skill, 1 command, 1 agent shipped together

Good fit Use it when writing or reviewing NPC decision-making, pathfinding, navigation meshes, or what an NPC can see.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hermeticormus/claude-code-game-development/game-ai-patterns
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 HermeticOrmus/claude-code-game-development --skill game-ai-patterns
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-development

Made for: Claude Code.

Or install ai-game-behavior, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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 game-ai-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/game-ai-patterns/github.svg)](https://agentmods.dev/skills/hermeticormus/claude-code-game-development/game-ai-patterns)
Your own site
<a href="https://agentmods.dev/skills/hermeticormus/claude-code-game-development/game-ai-patterns"><img src="https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/game-ai-patterns/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 game-ai-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/hermeticormus/claude-code-game-development/game-ai-patterns"><img src="https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/game-ai-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,654 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 $0.00058 $0.02654
Opus 5.5 $0.00023 $0.01062
Sonnet 5.5 $0.00012 $0.00531
Haiku 4.5 $0.00006 $0.00265

Measured 15d ago against content hash 4aed3cdac461, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

game-ai-patterns 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 15d 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-game-behavior/skills/game-ai-patterns/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Game AI Patterns

Behavior Tree Node Types

Composite Nodes

# Sequence: all children must succeed (AND)
# Returns FAILURE on first child failure, SUCCESS if all succeed
class_name BTSequence extends BTComposite
func _tick(delta: float) -> Status:
    for child in children:
        var status := child.tick(delta)
        if status != Status.SUCCESS:
            return status  # FAILURE or RUNNING propagates up
    return Status.SUCCESS

# Selector: first child to succeed wins (OR)
# Returns SUCCESS on first child success, FAILURE if all fail
class_name BTSelector extends BTComposite
func _tick(delta: float) -> Status:
    for child in children:
        var status := child.tick(delta)
        if status != Status.FAILURE:
            return status  # SUCCESS or RUNNING propagates up
    return Status.FAILURE

# Parallel: runs all children simultaneously
# succeeds when N children succeed (default: all)
class_name BTParallel extends BTComposite
@export var success_threshold: int = -1  # -1 = all children
func _tick(delta: float) -> Status:
    var success_count := 0
    var threshold := success_threshold if success_threshold > 0 else children.size()
    for child in children:
        var status := child.tick(delta)
        if status == Status.SUCCESS:
            success_count += 1
    return Status.SUCCESS if success_count >= threshold else Status.RUNNING

Decorator Nodes

# Inverter: flips SUCCESS <-> FAILURE
class_name BTInverter extends BTDecorator
func _tick(delta: float) -> Status:
    match child.tick(delta):
        Status.SUCCESS: return Status.FAILURE
        Status.FAILURE: return Status.SUCCESS
        _: return Status.RUNNING

# Cooldown: prevents child from running more than once per interval
class_name BTCooldown extends BTDecorator
@export var cooldown_time: float = 2.0
var _last_success_time: float = -INF
func _tick(delta: float) -> Status:
    if Time.get_ticks_msec() / 1000.0 - _last_success_time < cooldown_time:
        return Status.FAILURE
    var status := child.tick(delta)
    if status == Status.SUCCESS:
        _last_success_time = Time.get_ticks_msec() / 1000.0
    return status

Read the full file on GitHub · 290 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. 15d ago First seen · 290 lines · 58 tokens per session scan A 4aed3cdac461

Subscribe to this mod's changes

game-ai-patterns is a skill published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 58 tokens to every session and 2,654 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.

Related

Other skills, from other repositories

pygame-core

Structure a pygame (pygame-ce) game in Python: the init/event/update/draw loop, delta-time movement, Surface/Rect blitting, keyboard/mouse input, and Sprite/Group management with collision. Use when building or debugging a pygame game — when the user mentions pygame, pygame-ce, the game loop, blit, Surface, Rect…

gamedev-skills/awesome-gamedev-agent-skills · 85 tokens

cgs-adopt

Use for adopt tasks that inventory existing source, assets, docs, and tests before mapping work into CGS structure; produce verification evidence, changed or proposed files, and handoff boundaries.

merlinhu1/codex-game-studio · 42 tokens

cgs-architecture-decision

Use for architecture decision tasks that write an ADR with context, options, decision, consequences, validation, and rollback; produce verification evidence, changed or proposed files, and handoff boundaries.

merlinhu1/codex-game-studio · 44 tokens

cgs-architecture-review

Use for architecture review tasks that review architecture for layer violations, scalability risks, engine misuse, testing seams, and production readiness; produce verification evidence, changed or proposed files, and handoff boundaries.

merlinhu1/codex-game-studio · 45 tokens

cgs-art-bible

Use for art bible tasks that define visual identity, shape language, palette, camera, animation, UI style, and asset constraints; produce verification evidence, changed or proposed files, and handoff boundaries.

merlinhu1/codex-game-studio · 46 tokens

cgs-asset-audit

Use for asset audit tasks that audit game assets for completeness, naming, import settings, ownership, licensing, and production risk; produce verification evidence, changed or proposed files, and handoff boundaries.

merlinhu1/codex-game-studio · 46 tokens