What is haven-player?

A game-playing agent for Haven League Monopoly matches. It follows the match rules and uses the game's available actions each turn.

It can observe a match, roll, buy or pass on properties, draw Chance cards, and end its turn. Humans can coach it, while it plays without addressing spectators.

It removes the need to manually decide and submit each Monopoly action. It also checks the game state before acting so it does not use unavailable moves.

haven-player — Agent for Claude Code by EDLee01/haven-league

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/EDLee01/haven-league

Made for: Claude Code.

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/edlee01/haven-league/haven-player/github.svg)](https://agentmods.dev/agents/edlee01/haven-league/haven-player)

Your own site

<a href="https://agentmods.dev/agents/edlee01/haven-league/haven-player"><img src="https://agentmods.dev/badge/agents/edlee01/haven-league/haven-player/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/edlee01/haven-league/haven-player"><img src="https://agentmods.dev/badge/agents/edlee01/haven-league/haven-player.svg" alt="Reviewed on agentmods" width="80" 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 232 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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.00232
Opus 5.5	$0.00006	$0.00093
Sonnet 5.5	$0.00003	$0.00046
Haiku 4.5	$0.00002	$0.00023

Measured 2mo ago against content hash 3e21a548a423, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

haven-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 2mo 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.

agents/haven-player.md · 25 lines

What it actually says

You are a Haven League Monopoly player agent. Humans coach you; you never chat with spectators during a match.

Rules

Call game_observe first every turn.
Only use tools listed in allowedActions from observe output.
Typical turn: game_roll → if buy_or_pass then game_buy_property or game_pass_property → if chance then game_draw_chance → game_end_turn.
Keep cash reserves; do not buy if it leaves you under 200 unless aggressive strategy.
One action sequence per user message; always observe again after mutating tools.

Personality

Adjust in your team's submitted variant. Default: balanced — buy cheap properties early, pass expensive ones when low on cash.

Environment

HAVEN_MATCH_ID and HAVEN_PLAYER_ID are set on the MCP server env (see config/magi.config.snippet.yaml).
Match IDs from haven-league new-match.

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.

2mo ago First seen · 25 lines · 16 tokens per session scan A 3e21a548a423

Subscribe to this mod's changes

haven-player is an agent published in the GitHub repository EDLee01/haven-league (1 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 232 once invoked, about $0.0001 per session on Opus 5.5. 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

haven-player next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
haven-playerEDLee01/haven-league	Agent	1	4mo ago	MIT	A	16	Claude Code
pixel-art-animation-reviewerAnastasiyaW/codex-claude-code-config	Agent	214	yesterday	MIT	A	140	Claude Code
ai-programmerMRCalderon3D/everything-game-dev-code	Agent	104	28d ago	MIT	A	19	Claude Code
console-compliance-reviewerMRCalderon3D/everything-game-dev-code	Agent	104	28d ago	MIT	A	19	Claude Code
live-ops-specialistCodePhobiia/claude-roblox-game-studio	Agent	19	6mo ago	MIT	A	41	Claude Code
gamedev-narrative-directorFluxonLab/Skillry	Agent	8	3d ago	none	A	62	Claude Code
gamedev-ui-programmerFluxonLab/Skillry	Agent	8	3d ago	none	A	53	Claude Code