vbot-mind

vbot-mind is a skill for Claude Code from sandraschi/vbot-mind-mcp. It costs 50 tokens per session (748 once invoked), scanned A, original, MIT.

A runtime for autonomous virtual robots in Godot, Unity3D, or Resonite. It lets game-engine characters perceive their surroundings, reason with a language model, remember events, and act.

In plain words
What is it for?
Creating and controlling V-Bots with personalities, roles, goals, and backstories; sending them observations; running decisions; storing or querying memories; and enabling conversations.
Why use it?
It provides the parts needed for characters that respond to situations and retain past interactions, instead of relying only on fixed scripts.

Skill for Claude Code

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

Part of the vbot-mind-mcp plugin — 1 skill, 1 MCP server shipped together

Good fit Creating and controlling V-Bots with personalities, roles, goals, and backstories; sending them observations; running decisions; storing or querying memories; and enabling conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandraschi/vbot-mind-mcp/vbot-mind
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 sandraschi/vbot-mind-mcp --skill vbot-mind
Clone the repo
git clone --depth 1 https://github.com/sandraschi/vbot-mind-mcp

Made for: Claude Code.

Or install vbot-mind-mcp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 vbot-mind

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandraschi/vbot-mind-mcp/vbot-mind.svg)](https://agentmods.dev/skills/sandraschi/vbot-mind-mcp/vbot-mind)
Your own site
<a href="https://agentmods.dev/skills/sandraschi/vbot-mind-mcp/vbot-mind"><img src="https://agentmods.dev/badge/skills/sandraschi/vbot-mind-mcp/vbot-mind.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 748 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 $0.00050 $0.00748
Opus 5 $0.00025 $0.00374
Sonnet 5 $0.00010 $0.00150
Haiku 4.5 $0.00005 $0.00075

Measured 7d ago against content hash 1d3b13712091, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vbot-mind 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.

skills/vbot-mind/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

V-Bot Mind — Skill

What This Server Does

V-Bot Mind is the fleet's autonomous virtual robot brain runtime. It receives perception data from a game engine (what the bot sees, hears, senses), runs LLM reasoning to decide what to do, maintains episodic memory of past interactions, and outputs motor commands back to the engine.

You use this server when you have V-Bots in Godot, Unity3D, or Resonite that need autonomous behavior — NPCs that think, remember, and act like characters.

Core Workflow

  1. Create a V-Bot with a name, personality, role, and backstory
  2. Perceive — feed the bot observations from the game engine
  3. Think — run LLM reasoning on the current situation
  4. Act — output motor commands back to the engine
  5. Remember — store important events; query past memories
  6. Chat — have a player/NPC talk directly to the V-Bot

Tool Reference

vbot_mind (primary portmanteau)

Operations:

  • status — List all V-Bots or get one by id
  • create — Create a new V-Bot with personality, role, and backstory
  • configure — Update a V-Bot's personality, goals, or role
  • perceive — Feed observations (what the bot sees/hears/senses)
  • think — Run LLM reasoning on the current situation
  • act — Execute a motor command (move, speak, interact, idle)
  • chat — Direct conversation with a V-Bot
  • remember — Store or retrieve episodic memories
  • delete — Remove a V-Bot instance

vbot_agentic_workflow

Runs a multi-step perceive → think → act loop toward a goal. The V-Bot autonomously pursues the goal for up to max_steps cycles.

Personality Design

V-Bot personalities are defined by trait keywords and a backstory:

  • Traits: curiosity, sociability, aggression, patience, humor, diligence, caution, creativity
  • Backstory: A short narrative that shapes the bot's worldview and behavior

The LLM uses the personality + backstory + episodic memory to generate consistent, in-character responses. A "shy, cautious" bot will behave differently from a "bold, aggressive" one in the same situation.

Read the full file on GitHub · 75 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 · 75 lines · 50 tokens per session scan A 1d3b13712091

Subscribe to this mod's changes

vbot-mind is a skill published in the GitHub repository sandraschi/vbot-mind-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 748 once invoked, about $0.0003 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.