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.
npx agentmods add instructions/bortor/turing-test-game/agents-mdgit clone --depth 1 https://github.com/Bortor/turing-test-gameWrote 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/instructions/bortor/turing-test-game/agents-md)<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>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 | $0.00863 | $0.00863 |
| Opus 5 | $0.00432 | $0.00432 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00086 | $0.00086 |
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.
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与.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.md、memes.md、sessions/、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。
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.
- 3d ago First seen · 71 lines · 863 tokens per session scan A 56360fb8ad44
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.
Other instructions, from other repositories
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
slivingdoc AGENTS.md
AGENTS.md instructions for baalimago/slivingdoc, covering agents.md — slivingdoc, architecture, package map, event flow and startup wiring (main.go).