Borrowing it
Nothing to install: this file belongs to sumo1/AI-GAME-COOL. 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/sumo1/AI-GAME-COOL/main/CLAUDE.mdgit clone --depth 1 https://github.com/sumo1/AI-GAME-COOLWrote 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/sumo1/ai-game-cool/claude-md)<a href="https://agentmods.dev/instructions/sumo1/ai-game-cool/claude-md"><img src="https://agentmods.dev/badge/instructions/sumo1/ai-game-cool/claude-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 5.1 | $0.04630 | $0.04630 |
| Opus 5 | $0.02315 | $0.02315 |
| Sonnet 5 | $0.00926 | $0.00926 |
| Haiku 4.5 | $0.00463 | $0.00463 |
Grade A, and why
AI-GAME-COOL CLAUDE.md scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:9200/_cluster/health How it starts
The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
实现前必读
在修改代码或编写新功能之前，按需读取：
docs/engineering/conventions.md— 工程规范（包结构、命名、Tool/Skill 设计、错误处理、AgentLoop 边界、评估系统规范）docs/review/code-check.md— 工程审查标准docs/knowledge/principles/agent-system-philosophy.md— Agent 系统设计哲学（双 SSOT + 三时间方向）- 当前活跃任务目录（
docs/task/下按时间戳倒序，取最新的）：memory/— 决策备忘录（优先级高于早期 plan）progress.md— 当前进展和待办plan/— 子任务设计与契约
Agent 体系
本仓库使用 7 个独立工种协作完成开发（流程 SSOT 在 agents/，平台薄引用在 .claude/agents/）：
| Agent | 角色 | 触发 |
|---|---|---|
task-designer |
把需求拆为带双契约的可执行计划 | 收到新需求时 |
coder |
按契约精准施工 | 子任务 plan 就绪后 |
evaluator |
独立复跑命令、机器化验收 | coder 交付后 |
code-reviewer |
工程标准 + 任务专项审查 | 提交前 |
doc-refresher |
业务知识 SSOT 反漂移哨兵 | 每次提交 |
dreamer |
蒸馏 memory 上浮 knowledge | 阶段收尾 / memory ≥ 10 条 |
ci-pre-checker (git-push) |
提交流水线守门 | 用户说"提交"/"push" |
主会话职责（项目经理而非程序员）
主会话是项目经理，不是干活的人。核心职责：
- 管理进度表——
TaskCreate / TaskList / TaskUpdate跟踪所有子任务，每完成一步立即更新 - 识别任务——把用户需求拆成符合 agents 体系的子任务（task-designer 流程或自己拆）
- 分发子任务——能并行就并行，文件范围不重叠的活同时 spawn
- 监督子任务运行状态——子任务很容易僵死。主会话定时检查：
- 简单任务（≤ 3 分钟）：等返回即可，不主动检查
- 中等任务（3-10 分钟）：每 3 分钟用
BashOutput/ 任务输出文件 检查一次 - 长任务（> 10 分钟）：每 5 分钟检查一次；超过预期 2x 时间立即
TaskStop并诊断
- 不每步问用户——除非有真歧义，自己判断下一步该做什么；用户只想看到最终结果
- 真歧义才打断用户——比如用户没拍板的方案选择、风险高的破坏性操作。结构化清晰、不堆问题
反模式：
- 每完成一个 step 就问"要继续吗"
- 不更新 TaskList，让用户搞不清进度
- spawn subagent 后忘记看它有没有挂死
- 把用户当审稿人，每个小事都要确认
Git 提交
使用 git-push skill 触发完整提交流程。直接说"push"或"提交"即可。
内容分层
| 层 | 位置 | 说明 |
|---|---|---|
| 工程标准 | docs/engineering/ + docs/review/ |
跨任务长期有效 |
| Agent 流程 | agents/ |
skill 和 subagent 的流程 SSOT |
| 平台配置 | .claude/ |
Claude Code 薄引用，指向 agents/ |
| 任务文档 | docs/task/{YYMMDD}-{name}/ |
架构、进度、决策、审查历史 |
| 跨任务知识 | docs/knowledge/ |
由 dreamer 上浮维护 |
数据持久化
- 会话与游戏存储在 SQLite（
./game-agent-backend/data/game-agent.db），由infra/db/*模块管理 - 老的
saved-games/目录保留向后兼容（@Deprecated） - 详见
docs/engineering/conventions.md § 12 - 重置：
rm -f ./game-agent-backend/data/game-agent.db*后重启应用自动重建 schema
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.
- 7d ago First seen · 448 lines · 4,630 tokens per session scan A 965d330f82c5
AI-GAME-COOL CLAUDE.md is an instructions file published in the GitHub repository sumo1/AI-GAME-COOL (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 4,630 tokens to every session, about $0.0231 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.