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/amanidawn/dgame/claude-mdgit clone --depth 1 https://github.com/AmaniDawn/DGameWrote 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/amanidawn/dgame/claude-md)<a href="https://agentmods.dev/instructions/amanidawn/dgame/claude-md"><img src="https://agentmods.dev/badge/instructions/amanidawn/dgame/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 | $0.02363 | $0.02363 |
| Opus 5 | $0.01182 | $0.01182 |
| Sonnet 5 | $0.00473 | $0.00473 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade A, and why
DGame CLAUDE.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 5d 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.
This is a copy
95% identical to DGame AGENTS.md — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
请使用中文写提案和回答。 这个文件为 Claude Code (claude.ai/code) 提供指导，用于处理此代码库中的代码。
主启动场景位于 GameUnity/Assets/Scenes/GameStart/GameStart.unity。
⚡ 强制工作流
第零步：判断任务等级
| 等级 | 判断标准 | 知识查询策略 |
|---|---|---|
| L1 简单 | typo、注释、日志文案、单行变量改名；前提是不涉及框架 API、UI 节点前缀、事件定义、资源路径、Luban 配置 | 可跳过 skill，直接处理 |
| L2 调用 | 调用已知 API、单模块局部修改 | 使用 dgame-dev skill 查询对应主题 |
| L3 功能 | 新功能、跨文件修改、新增 UI / 资源 / 事件 / 模块逻辑 | 使用 dgame-dev 查询全量相关主题；涉及配置先用 luban-dev |
| L4 架构 | 模块设计、系统重构、多模块协作、架构决策 | 使用 dgame-dev 并按需并行查询多个 reference；配置链路同时使用 luban-dev |
不确定时上调一级。凡涉及 DGame API 名称、程序集边界、资源地址、UI 节点前缀、事件接口、热更流程、Luban 表结构，都不要按 L1 处理。
第一步：按主题获取规范
同一会话中已查过的主题可复用摘要；只有涉及新主题或发现文档与源码冲突时才重新查询。配置表相关任务优先 luban-dev，业务落位和运行时代码再补 dgame-dev。
| 场景 | 必须查询主题 |
|---|---|
| 文件落位 / 程序集边界 | architecture.md |
| UI 生命周期 / 窗口 / Widget / IUIController | ui-lifecycle.md、ui-patterns.md |
| 资源加载 / 释放 / 场景切换资源整理 | resource-api.md、resource-patterns.md |
| 热更资源包 / YooAsset 下载链路 | hotpatch-workflow.md |
| 整包 / AB 打包 / Jenkins 自动化 / ReleaseTools | build-pipeline.md |
| 热更代码 / HybridCLR / AOT 泛型 | hotfix-workflow.md |
| 模块 API / DataCenterModule / MemoryPool / Audio / Fsm | modules.md |
| 事件系统 / EventCenter / 事件反模式 | event-system.md、event-antipatterns.md |
| Luban 配置消费 | luban-config.md；编辑配置表时使用 luban-dev |
| 红点系统 | reddot-system.md |
| 命名 / UI 节点前缀 / 代码规范 | naming-rules.md |
| MCP 工具链 | mcp-tools.md、mcp-visual.md |
| 排障 | troubleshooting.md |
第二步：输出代码或方案
基于已查询规范实现。若 reference 与源码冲突：
- 用
rg搜索实际签名和调用点。 - 优先信任当前源码。
- 在回复中标注冲突点；如果任务本身是维护 skill，直接修正
.claude/skills/dgame-dev/references/对应文档。
DGame 开发指导
处理 DGame 代码时优先使用 dgame-dev skill。它参考 TEngine 的 tengine-dev 组织方式，但内容按 DGame 当前项目结构、API 和封装编写。
知识源：.claude/skills/dgame-dev/references/
使用方式
使用 skill = "dgame-dev"
描述需要查询的技术问题或功能点
专用 skill 优先级
- Luban 配置表、Excel、
__tables__.xlsx/__beans__.xlsx/__enums__.xlsx、导表脚本、GameConfig/数据：优先使用luban-dev。 - 代码落位、程序集边界、HotFix/Runtime/AOT 分层、资源模块生命周期、UI/事件/模块架构：使用
dgame-dev。 - 同时涉及配置和业务代码时，先用
luban-dev处理配置链路，再用dgame-dev处理业务落位与调用方式。
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.
- 5d ago First seen · 208 lines · 2,363 tokens per session scan A 65adfb5f5290
DGame CLAUDE.md is an instructions file published in the GitHub repository AmaniDawn/DGame (152 stars, last pushed 2d ago), licensed MIT. It adds 2,363 tokens to every session, about $0.0118 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to DGame AGENTS.md, differing in 18 lines, and is treated as a copy.
Other instructions, from other repositories
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.