npc-spec

npc-spec is a command for Claude Code from sponticelli/gamedev-claude-plugins. It costs 8 tokens per session (863 once invoked), scanned A, original, MIT.

A command that creates a detailed behavior plan for an NPC, meaning a game character controlled by the computer. The plan covers the character's role, setting, personality, interactions, and technical needs.

In plain words
What is it for?
Use it to specify enemies, allies, merchants, guards, companions, and other NPCs, including their identity, appearance, voice, behavior, and game role.
Why use it?
It helps turn an idea for a character into information that designers and programmers can use. It prompts for missing context such as combat, dialogue, animation, and performance limits.

Command for Claude Code

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

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

Good fit Use it to specify enemies, allies, merchants, guards, companions, and other NPCs…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sponticelli/gamedev-claude-plugins/npc-spec
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.

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

Made for: Claude Code.

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 npc-spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/npc-spec.svg)](https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/npc-spec)
Your own site
<a href="https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/npc-spec"><img src="https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/npc-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 863 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 $0.00008 $0.00863
Opus 5 $0.00004 $0.00432
Sonnet 5 $0.00002 $0.00173
Haiku 4.5 $0.00001 $0.00086

Measured 7d ago against content hash 3b2480aa8d10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

npc-spec 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 7d 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/npc-spec.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NPC Specification Generator

Create a comprehensive NPC behavior specification.

Context Gathering

Before generating the NPC spec, understand the character:

Analyze NPC Role

  • What's their function in the game?
  • How does the player interact with them?
  • Are they combat-capable?
  • Do they have dialogue?

Understand Context

  • Where do they appear?
  • What's their narrative role?
  • Are they recurring or one-time?
  • What factions/groups are they part of?

Check Technical Needs

  • What AI system will be used?
  • What animations are available?
  • What's the performance budget?
  • What other NPCs exist for reference?

Identify Personality

  • What's their disposition?
  • What motivates them?
  • What are their quirks?
  • How do they react to the player?

Use this context to create complete NPC specification.

Output Format

# NPC Specification: [NPC Name/Type]

## Overview
**Classification:** [Enemy/Neutral/Ally/Companion]
**Role:** [Merchant/Quest-giver/Guard/etc.]
**Location(s):** [Where they appear]
**Frequency:** [Always/Conditional/Unique]

## Identity

### Basic Info
**Name:** [Name or naming pattern]
**Appearance:** [Visual description]
**Voice:** [Vocal qualities]

### Personality
| Trait | Level | Expression |
|-------|-------|------------|
| [Trait] | [1-10] | [How it shows] |

### Motivation
**Wants:** [Goals]
**Fears:** [Avoids]
**Secret:** [Hidden aspect]

## Behaviors

### Idle State
**Default activity:** [What they do normally]
**Animations:** [Idle animation set]
**Variations:** [Different idle behaviors]
**Schedule:** [Time-based changes, if any]

### Interaction
**Player approach:** [How they react]
**Dialogue trigger:** [How to talk to them]
**Services:** [What they offer]
**Relationship tracking:** [If tracked]

### Combat (if applicable)
**Aggression:** [Passive/Defensive/Aggressive]
**Combat style:** [How they fight]
**Triggers:** [What makes them hostile]
**Allies:** [Who they fight with]
**Flee threshold:** [When they run]

### Reactions
| Trigger | Reaction |
|---------|----------|
| Player approaches | [Response] |
| Attacked | [Response] |
| Ally attacked | [Response] |
| Gift received | [Response] |
| Threat nearby | [Response] |

## Dialogue

### Voice Characteristics
**Style:** [Formal/Casual/Rough/etc.]
**Vocabulary:** [Simple/Complex]
**Quirks:** [Speech patterns]

### Key Lines
**Greeting (first):** "[Line]"
**Greeting (return):** "[Line]"
**Farewell:** "[Line]"
**Busy/dismissive:** "[Line]"
**Combat taunt:** "[Line]"

### Dialogue Trees
[Reference to dialogue content or structure]

## Technical Requirements

### AI Behavior
**System:** [FSM/BT/Other]
**Complexity:** [Simple/Medium/Complex]
**Key states:** [Main behavior states]

### Animation Requirements
| Animation | Priority | Notes |
|-----------|----------|-------|
| [Animation] | [Required/Nice-to-have] | [Details] |

### Audio Requirements
| Audio | Type | Notes |
|-------|------|-------|
| [Sound] | [VO/SFX] | [Details] |

## Spawning

### Placement
**Locations:** [Where they spawn]
**Density:** [How many]
**Conditions:** [Spawn requirements]

### Schedule
[Time-based spawn rules if any]

## Relationships

### With Player
**Starting:** [Neutral/Friendly/Hostile]
**Can change:** [Yes/No]
**Factors:** [What affects it]

### With NPCs
| NPC/Group | Relationship |
|-----------|--------------|
| [NPC] | [Friend/Neutral/Enemy] |

## Implementation Notes
[Technical considerations, dependencies, risks]

Read the full file on GitHub · 159 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. 7d ago First seen · 159 lines · 8 tokens per session scan A 3b2480aa8d10

Subscribe to this mod's changes

npc-spec is a command published in the GitHub repository sponticelli/gamedev-claude-plugins (15 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 863 once invoked, about $0.0000 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.