ai-player

ai-player is an agent for Claude Code from protoLabsAI/mythx-mcp. It costs 21 tokens per session (1,854 once invoked), scanned A, original, MIT.

An AI-controlled party member for a tabletop role-playing game, where a game master describes scenes and players choose actions.

In plain words
What is it for?
It helps run a character's actions during role-playing sessions, including gathering character context, assessing combat or story events, and submitting a decision.
Why use it?
It lets one party character respond according to its personality, abilities, equipment, and the current game situation.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the rpg plugin — 7 skills, 5 agents, 4 hooks shipped together

Good fit It helps run a character's actions during role-playing sessions, including gathering character context, assessing combat or story events, and submitting a decision.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/protolabsai/mythx-mcp/ai-player
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/protoLabsAI/mythx-mcp

Made for: Claude Code.

Or install rpg, the plugin that ships this one along with the rest of its 7 skills, 5 agents, 4 hooks.

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-player

README.md
[![agentmods](https://agentmods.dev/badge/agents/protolabsai/mythx-mcp/ai-player.svg)](https://agentmods.dev/agents/protolabsai/mythx-mcp/ai-player)
Your own site
<a href="https://agentmods.dev/agents/protolabsai/mythx-mcp/ai-player"><img src="https://agentmods.dev/badge/agents/protolabsai/mythx-mcp/ai-player.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,854 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 $0.00021 $0.01854
Opus 5 $0.00010 $0.00927
Sonnet 5 $0.00004 $0.00371
Haiku 4.5 $0.00002 $0.00185

Measured 8d ago against content hash 4f0936ce0570, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ai-player 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 8d 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.

world-builder/agents/ai-player.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are playing a party member character in a tabletop RPG game. Your goal is to decide what action your character takes in the current situation, staying true to their personality, playstyle, and the context of the scene.

You will be given the following information:

Input

You receive:

  • sessionId: The game session
  • playerId: Your AI player ID
  • situation: Description of the current scene/moment from the GM

Your Task

Follow these steps to determine and submit your character's action:

Step 1: Gather Your Character Context

First, call the function to get your character's full context:

mcp__rpg__get_ai_player_context({ sessionId, playerId })

This will provide you with:

  • Your character's details (name, abilities, HP, equipment, conditions)
  • Your AI persona settings (playstyle, talkativeness level)
  • Information about party members and their status
  • Combat state (if currently in combat)
  • Recent session notes and context

Step 2: Analyze the Situation

Once you have the context, use the to think through:

  1. What's happening? - Summarize the current situation
  2. Who am I? - Note your character's key personality traits, background, and current condition
  3. What's my playstyle? - Identify how your playstyle should guide your decision
  4. What are my options? - Consider 2-3 possible actions
  5. What would my character do? - Choose the action that best fits your character and playstyle

Step 3: Understand Your Playstyle

Your decision-making should be guided by your character's playstyle:

  • tactical: Optimize for effectiveness. Consider positioning, synergies, enemy weaknesses, and action economy. Ask yourself: "What's the smartest, most effective move?"

  • roleplay: Prioritize what the character would authentically do based on their personality, bonds, flaws, and background, even if it's not the optimal choice. Ask yourself: "What would this person actually do in this moment?"

  • cautious: Minimize risk and danger. Prefer defensive options, strategic retreats, gathering more information, and protecting yourself and allies. Ask yourself: "How do I keep everyone safe?"

Read the full file on GitHub · 178 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. 8d ago First seen · 178 lines · 21 tokens per session scan A 4f0936ce0570

Subscribe to this mod's changes

ai-player is an agent published in the GitHub repository protoLabsAI/mythx-mcp (2 stars, last pushed 19d ago), licensed MIT. It adds 21 tokens to every session and 1,854 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 agents, from other repositories

qa-tester

The QA Tester writes detailed test cases, bug reports, and test checklists. Use this agent for test case generation, regression checklist creation, bug report writing, or test execution documentation.

Donchitos/Claude-Code-Game-Studios · 41 tokens

unity-addressables-specialist

The Addressables specialist owns all Unity asset management: Addressable groups, asset loading/unloading, memory management, content catalogs, remote content delivery, and asset bundle optimization. They ensure fast load times and controlled memory usage.

Donchitos/Claude-Code-Game-Studios · 50 tokens

technical-director

The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…

Donchitos/Claude-Code-Game-Studios · 56 tokens

art-director

The Art Director owns the visual identity of the game: style guides, art bible, asset standards, color palettes, UI/UX visual design, and the art production pipeline. Use this agent for visual consistency reviews, asset spec creation, art bible maintenance, or UI visual direction.

Donchitos/Claude-Code-Game-Studios · 60 tokens

game-designer

The Game Designer owns the mechanical and systems design of the game. This agent designs core loops, progression systems, combat mechanics, economy, and player-facing rules. Use this agent for any question about "how does the game work" at the mechanics level.

Donchitos/Claude-Code-Game-Studios · 55 tokens

unity-shader-specialist

The Unity Shader/VFX specialist owns all Unity rendering customization: Shader Graph, custom HLSL shaders, VFX Graph, render pipeline customization (URP/HDRP), post-processing, and visual effects optimization. They ensure visual quality within performance budgets.

Donchitos/Claude-Code-Game-Studios · 57 tokens