behavior-tree

behavior-tree is a command for coding agents from sponticelli/gamedev-claude-plugins. It costs 13 tokens per session (732 once invoked), scanned A, original, MIT.

A command that designs a behavior tree, a branching decision structure used to control game characters or enemies.

In plain words
What is it for?
Use it to plan NPC, companion, or enemy behavior, including combat, patrol, service roles, triggers, and integration requirements.
Why use it?
It turns vague character-AI requirements into an organized set of priorities, conditions, actions, and fallback behaviors.

Command

Part of the ai-systems plugin — 4 commands, 3 agents shipped together

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.

agentmods
npx agentmods add commands/sponticelli/gamedev-claude-plugins/behavior-tree
Clone the repo
git clone --depth 1 https://github.com/sponticelli/gamedev-claude-plugins

Or install ai-systems, the plugin that ships this one along with the rest of its 4 commands, 3 agents.

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 behavior-tree

README.md
[![agentmods](https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/behavior-tree.svg)](https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/behavior-tree)
Your own site
<a href="https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/behavior-tree"><img src="https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/behavior-tree.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.00732
Opus 5 $0.00006 $0.00366
Sonnet 5 $0.00003 $0.00146
Haiku 4.5 $0.00001 $0.00073

Measured 4d ago against content hash a9f6dec7b78f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

behavior-tree 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/commands/behavior-tree.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Behavior Tree Generator

Create a behavior tree design for game AI.

Context Gathering

Before generating the behavior tree, understand the context:

Analyze the NPC

  • What type of entity? (Enemy, companion, neutral NPC)
  • What's their role in gameplay?
  • What actions can they perform?
  • What should they prioritize?

Understand Game Context

  • What game genre and style?
  • What other AI exists for reference?
  • What level of complexity is appropriate?
  • What debugging tools are available?

Check Technical Requirements

  • What behavior tree system is used?
  • What node types are available?
  • Performance constraints?
  • Integration with other systems?

Identify Key Behaviors

  • What must this AI do?
  • What's the highest priority?
  • What's the fallback behavior?
  • What triggers special behaviors?

Use this context to design appropriate behavior tree.

Output Format

# Behavior Tree: [NPC/Enemy Type]

## Overview
**Entity type:** [Enemy/Companion/NPC]
**Complexity:** [Simple/Medium/Complex]
**Priority focus:** [Combat/Patrol/Service/etc.]

## Tree Visualization

[Root: Selector] ├─ [Priority 1: Sequence] │ ├─ [Condition] │ └─ [Action] ├─ [Priority 2: Selector] │ ├─ [Sequence] │ │ ├─ [Condition] │ │ └─ [Action] │ └─ [Fallback] └─ [Default: Action]


## Node Definitions

### Composite Nodes
| Node | Type | Children | Purpose |
|------|------|----------|---------|
| [Name] | [Selector/Sequence/Parallel] | [Names] | [What it does] |

### Condition Nodes
| Node | Check | Success | Failure |
|------|-------|---------|---------|
| [Name] | [What's evaluated] | [When true] | [When false] |

### Action Nodes
| Node | Action | Duration | Exit |
|------|--------|----------|------|
| [Name] | [What it does] | [Time/Condition] | [Success/Fail/Running] |

### Decorator Nodes
| Node | Child | Modification |
|------|-------|--------------|
| [Name] | [Which node] | [How it modifies] |

## Behavior Breakdown

### [High Priority Behavior]
**Trigger:** [What activates this branch]
**Sequence:**
1. [Check condition]
2. [Perform action]
3. [Continue or exit]

### [Medium Priority Behavior]
**Trigger:** [What activates this branch]
**Sequence:**
[Steps]

### [Fallback Behavior]
**When:** [All else fails]
**Action:** [What they do]

## Blackboard Variables
| Variable | Type | Set By | Used By |
|----------|------|--------|---------|
| [Name] | [Type] | [What sets it] | [What reads it] |

## State Transitions
[How the AI moves between major behavioral states]

## Debug Information
**Key breakpoints:** [Where to check behavior]
**Log points:** [What to log]
**Visualization:** [What to show in debug view]

## Edge Cases
| Scenario | Handling |
|----------|----------|
| [Edge case] | [How the tree handles it] |

Read the full file on GitHub · 125 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. 4d ago First seen · 125 lines · 13 tokens per session scan A a9f6dec7b78f

Subscribe to this mod's changes

behavior-tree is a command published in the GitHub repository sponticelli/gamedev-claude-plugins (15 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 732 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 2026-08-30.