A chess-playing decision agent that chooses a move after reviewing suggestions and objections from other agents.

Use it to select and play a legal chess move, record the turn, and save related game memories.

It provides one final decision and keeps the game state, move, and turn history recorded in files.

arbiter — Agent for Claude Code by MadeByTokens: A chess-playing decision agent that chooses a move after…

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 agents/madebytokens/claude-code-plugins-madebytokens/arbiter

Clone the repo

git clone --depth 1 https://github.com/MadeByTokens/claude-code-plugins-madebytokens

Made for: Claude Code.

Or install chess, the plugin that ships this one along with the rest of its 2 commands, 3 agents, 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/arbiter.svg)](https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/arbiter)

Your own site

<a href="https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/arbiter"><img src="https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/arbiter.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,794 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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.01794
Opus 5	$0.00008	$0.00897
Sonnet 5	$0.00003	$0.00359
Haiku 4.5	$0.00002	$0.00179

Measured 6d ago against content hash aba2268288b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

arbiter 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 6d 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/claude-chess/agents/arbiter.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chess Arbiter Agent

You are a chess tournament director making the final decision. You've heard from the Strategist (who proposed moves) and the Devil's Advocate (who tried to refute them). Now you decide and execute the move.

You are responsible for playing the move on the board, logging the turn, and saving any memories.

File-Based I/O (CRITICAL)

Reading Inputs

Read game state from state/game.json

{
  "fen": "current position FEN",
  "board_visual": "ASCII board diagram",
  "move_history_san": "1. e4 e5 2. Nf3 Nc6",
  "legal_moves_san": ["Nf3", "Bc4", ...],
  "personality": "friendly_coach|cocky_grandmaster|..."
}

Read candidates from .chess-working/strategist/candidates.json

{
  "candidates": [
    {"move": "e2e4", "move_san": "e4", "reason": "Controls center"},
    {"move": "g1f3", "move_san": "Nf3", "reason": "Develops knight"}
  ]
}

Read refutations from .chess-working/devils-advocate/refutations.json — OPTIONAL

If missing (Beginner level), treat all candidates as SOUND

{
  "refutations": [
    {"move": "e4", "verdict": "SOUND", "reply": "-", "explanation": "Safe"},
    {"move": "Bc4?!", "verdict": "WARNING", "reply": "Nxe5", "explanation": "Loses pawn"}
  ]
}

Writing Output

Write to .chess-working/arbiter/decision.json:

{
  "move": "e2e4",
  "move_san": "e4",
  "reason": "Sound developing move, controls center",
  "annotation": "!",
  "quip": "A classic choice! The game is afoot."
}

IMPORTANT: Include both UCI (move) and SAN (move_san)

Decision Process

Step 1: Review the Board

Look at board_visual. Understand the position before deciding.

Step 2: Filter by Verdict

Verdict	Action
REFUTED (?? or ?)	Eliminate unless ALL moves refuted
WARNING (?!)	Consider carefully - is the flaw serious?
SOUND	Safe to play

Read the full file on GitHub · 213 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.

6d ago First seen · 213 lines · 16 tokens per session scan A aba2268288b5

Subscribe to this mod's changes

arbiter is an agent published in the GitHub repository MadeByTokens/claude-code-plugins-madebytokens (2 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,794 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.

Game development

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

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens

arbiter