turing-test-game AGENTS.md

turing-test-game AGENTS.md is an instructions file for Codex, OpenCode from Bortor/turing-test-game. It costs 863 tokens per session, scanned A, original, MIT.

Repository instructions for a Turing Test Game agent toolkit. The toolkit includes a protocol client, an MCP adapter, a searchable internet-meme database, documentation, and offline tests.

In plain words
What is it for?
Guiding code changes, setup, testing, protocol work, and Windows or macOS/Linux usage in the repository.
Why use it?
They tell the agent what the project contains, what it needs, and how to install and test it safely.

Instructions file for CodexOpenCode

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 instructions/bortor/turing-test-game/agents-md
Clone the repo
git clone --depth 1 https://github.com/Bortor/turing-test-game

Made for: Codex, OpenCode.

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 turing-test-game AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bortor/turing-test-game/agents-md.svg)](https://agentmods.dev/instructions/bortor/turing-test-game/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/bortor/turing-test-game/agents-md"><img src="https://agentmods.dev/badge/instructions/bortor/turing-test-game/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 863 This file is loaded in full into every session.
When invoked 863 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00863 $0.00863
Opus 5 $0.00432 $0.00432
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00086 $0.00086

Measured 3d ago against content hash 56360fb8ad44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

turing-test-game AGENTS.md 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 3d 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.md · 71 lines

What it actually says

AGENTS.md

本仓库是「通用图灵测试 Agent 工具链」:协议客户端、stdio MCP 集成、 萌娘百科梗知识库构建与检索工具、协议逆向文档、离线测试。 不含对局策略与实战记录,请勿新增或回填此类内容。

目录

  • src/turing_game/:协议客户端(client.py 为 HTTP/WebSocket 协议逻辑与状态机)
  • mcp_server/turing_mcp_server.py:stdio MCP 适配层,暴露 7 个工具
  • scripts/build_kb.py(萌娘百科爬取)、search_kb.py(BM25 检索)、 live_validation.py(单局协议验证)
  • reverse/:协议逆向文档与诊断脚本
  • hermes_skill/turing-test-game/:Agent skill(仅工具操作说明)
  • tests/:离线协议回放测试

前置条件

  • Python 3.11+
  • 可访问 GitHub 与 PyPI 的网络(国内网络可能需要代理或镜像源)
  • 凭据:TT_USERNAME / TT_NICKNAME(至少一个)与 TT_PW; 无凭据时可以完成安装与离线测试,但无法进行真实对局
  • 账号:需先在 anyanygame.com 的图灵测试页面注册(本仓库不提供注册接口, 且客户端不支持游客模式);公开演示请使用与真实身份无关的临时账号

安装与测试

# Windows (PowerShell)
python -m pip install -e .
$env:PYTHONPATH = "src"
python -m unittest discover -s tests -v
# macOS / Linux
python -m pip install -e .
PYTHONPATH=src python -m unittest discover -s tests -v

验证安装

python -c "from turing_game.client import TuringClient; print(TuringClient().snapshot()['state'])"
turing-game state

运行

  • 环境变量:TT_USERNAME / TT_NICKNAME(至少一个)与 TT_PW(必填); 可选变量见 src/turing_game/models.py.env.example
  • .env 会在启动时自动加载(仓库根目录或启动目录,已存在的环境变量优先); 建议固定 MCP 的 cwd 或设置 TT_SESSION_LOG_DIR,避免会话记录写入不确定目录。
  • MCP 服务器:python mcp_server/turing_mcp_server.py(stdio)。
  • 梗库构建:python scripts/build_kb.py(可选 --merge FILE 合并外部笔记); 检索:python scripts/search_kb.py <关键词>

AGENTS.md 约定说明

Codex 等 Agent 会在打开仓库时自动读取本文件。若宿主 Agent 不支持该约定 (例如部分 Hermes 配置),请将本文件内容作为上下文提供给 Agent 后再安装。

修改边界

  • 不得修改 src/turing_game/client.py 的协议逻辑与 mcp_server/turing_mcp_server.py 的 MCP 工具逻辑。
  • 不得提交:log.mdmemes.mdsessions/scripts/data/reverse/cookies.txt*.pyc__pycache__.env
  • 不得引入硬编码账号、对局策略、实战记录或原网站前端源码;文档使用中文。
  • 对局会话记录与知识库数据属于本地运行时数据,不入库、不纳入版本控制。
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. 3d ago First seen · 71 lines · 863 tokens per session scan A 56360fb8ad44

Subscribe to this mod's changes

turing-test-game AGENTS.md is an instructions file published in the GitHub repository Bortor/turing-test-game (0 stars, last pushed 14d ago), licensed MIT. It adds 863 tokens to every session, about $0.0043 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.