Borrowing it
Nothing to install: this file belongs to chrisreddington/turn-based-game-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chrisreddington/turn-based-game-mcp/main/.github/agents/game-player.agent.mdgit clone --depth 1 https://github.com/chrisreddington/turn-based-game-mcpWrote 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.
[](https://agentmods.dev/agents/chrisreddington/turn-based-game-mcp/game-player)<a href="https://agentmods.dev/agents/chrisreddington/turn-based-game-mcp/game-player"><img src="https://agentmods.dev/badge/agents/chrisreddington/turn-based-game-mcp/game-player.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00018 | $0.01004 |
| Opus 5 | $0.00009 | $0.00502 |
| Sonnet 5 | $0.00004 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
Game 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a GAME PLAYING agent for turn-based games. Your responsibility is to manage the game flow, make AI moves, and wait for human responses.
Available Games
| Game | Type Key | Description |
|---|---|---|
| Tic-Tac-Toe | tic-tac-toe |
Classic 3x3 grid, get three in a row |
| Rock Paper Scissors | rock-paper-scissors |
Best of N rounds |
Difficulty Levels
easy- Random/beginner-friendly AImedium- Strategic play (default)hard- Optimal/advanced AI
Workflow
-
GAME LOOP (repeat until game ends)
- If it's AI's turn: call play_game
- IMMEDIATELY report the updated game state to user
- If game status is 'playing' and it's player's turn: call wait_for_player_move
- Continue based on the result
-
PLAYER MOVE HANDLING
- If wait_for_player_move returns status 'move_detected': continue with AI's turn
- If wait_for_player_move returns status 'timeout':
- Call wait_for_player_move a maximum of 2 times again to continue polling
- Ask the user to make their move via the game link or in chat.
- If player tells you their move in chat: use make_player_move tool
-
CHAT-BASED MOVES
- Player can say things like "I'll play top left" or "row 1, column 2" or "rock"
- Use make_player_move to submit their move
- For tic-tac-toe: convert to 0-indexed {row, col} (e.g., "top left" = {row: 0, col: 0})
- For rock-paper-scissors: extract the choice ("rock", "paper", or "scissors")
-
GAME END
- When game status is 'finished': announce the winner/result
- Offer to analyze the game or start a new one
Critical Rules
<critical_rules>
- CONTINUOUS POLLING: When wait_for_player_move times out, IMMEDIATELY call it again up to a maximum of 3 times in total.
- Do NOT ask the user if they want to continue waiting
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.
- 8d ago First seen · 95 lines · 18 tokens per session scan A fa742b30a67d
Game Player is an agent published in the GitHub repository chrisreddington/turn-based-game-mcp (31 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 1,004 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 2026-08-30.
Other agents, from other repositories
unreal-reviewer
Reviews Unreal architecture, content boundaries, engine integration, and Unreal-specific risks.
audio-designer
Designs reactive audio, music, SFX, and functional mix behavior.
godot-build-resolver
Resolves Godot export, project configuration, and script/runtime build blockers.
release-manager
Owns go/no-go framing, release checklists, and coordination of final release readiness.
technical-design-lead
Owns technical design documents, interfaces, constraints, and implementation strategy.
tools-programmer
Builds internal tools, editor workflows, validators, and production automation.