Borrowing it
Nothing to install: this file belongs to AmaniDawn/DGame. 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/AmaniDawn/DGame/main/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/amanidawn/dgame/agents-md"><img src="https://agentmods.dev/badge/instructions/amanidawn/dgame/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/amanidawn/dgame/agents-md"><img src="https://agentmods.dev/badge/instructions/amanidawn/dgame/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01901 | $0.01901 |
| Opus 5.5 | $0.00760 | $0.00760 |
| Sonnet 5.5 | $0.00380 | $0.00380 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
DGame 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- DGame CLAUDE.md — 95% identical, 88 lines differ
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
请使用中文写提案和回答。
本文件是 DGame 仓库级规则。处理 GameUnity/** 下的文件时，还必须读取并遵守 GameUnity/AGENTS.md；子目录规则用于补充工程细节，和本文件冲突时以距离目标文件更近的规则为准。
适用范围与规范源
- 仓库级配置和工具位于
GameConfig/、GameRelease/和Tools/。 - Unity 工程位于
GameUnity/，其工程级规则见 GameUnity/AGENTS.md。 - Claude Code 与 Codex 共用
.agents/skills/下的 Agent Skills；技能和 Workflow 不再维护第二套入口。 - 不回滚用户已有改动，不删除与当前任务无关的文件。
工作方式
- 先阅读相关实现和
git status，确认已有改动边界。 - 按任务影响范围选择验证方式；跨模块、高风险或多阶段任务先明确目标和验收条件。
- 读取对应 skill 的
SKILL.md及必要的 reference。配置表、Excel、导表脚本和GameConfig/数据优先使用.agents/skills/luban-dev/。 - 源码用代码编辑工具修改；Unity 操作使用 Unity CLI 原生 MCP 工具或
unity command，入口选择和工程核对见unity-cli技能。Workflow 按需用于组合验证、CI 和配置导表。完成后执行与变更匹配的检查，并报告实际结果、限制和剩余风险。 - 当 reference 与源码冲突时，使用
rg核对实际签名和调用点，优先信任当前源码，并记录冲突位置。
授权边界
- 普通源码、文档和只读检查可按用户任务直接执行。
- 删除文件、覆盖已有配置或资源、修改包依赖、修改 ProjectSettings、切换平台、真实构建、导表写入生产目录、发布、提交或推送前，必须明确目标和范围；已有计划或预览不等于已授权执行。
- Unity 写入先明确本工程内的目标、输入和影响范围；支持
dry_run时使用原生命令预览。普通对象、组件及资源操作按用户任务和已有授权直接通过 MCP 或 CLI 执行；删除、覆盖、设置、依赖、平台和真实构建遵守上一条授权要求。使用 Workflow 时才执行其 preview、approve、apply 流程；命令超时后先查询真实状态，不自动重放。 - Luban 生产导表使用
python .agents/scripts/workflow.py luban preview、approve、apply；validate和隔离回归不会写入生产目录。 - 无法连接当前 DGame Editor、缺少工具或测试没有可运行用例时，记录 blocked 和原因，不使用其他工程或旧结果替代。
- Workflow 不自动安装或升级工具，不修改用户级技能、Codex 配置或其他用户级设置。
- 不自动提交、推送、上传、签名或发布；CLI 的
confirm参数和本地审批记录不能替代用户授权。 - 不使用已停用的旧工作流、旧 Unity MCP 或其他项目的验证结果替代当前 DGame 证据。
同一会话中已经核对过的主题可以复用摘要；只有涉及新主题或发现文档与源码冲突时才重新查询。
工作流、环境版本和验证矩阵见 .agents/README.md，Unity 命令以当前 MCP 工具描述、CLI 帮助和注册命令为准，Workflow 命令以 .agents/scripts/workflow.py --help 为准。L4、跨模块、配置导表、Unity 写入、构建和发布类任务必须使用 .agents/templates/task.md 记录目标、授权、决策、验证证据和剩余风险；L1/L2 小改可不创建任务文件。
AGENTS.md 是 Claude Code 与 Codex 都会读取的仓库级入口。匹配任务后，两个工具都应按这里的路由读取 .agents/skills/<skill>/SKILL.md；技能目录遵循 Agent Skills 的 SKILL.md、references/、scripts/ 和可选 agents/openai.yaml 结构。
设计与实现原则
- 精简界面（适用于界面和交互任务）：删除多余的标语、说明文字和次要标签。删除后若界面难以理解，应先重新设计布局或信息结构，不用文字堆叠弥补结构问题。
- 兼顾三类体验：每次修改都要检查以下三项，并在提案、任务记录或评审说明中用 1/2/3 编号呈现；按任务规模决定说明深度。除非任务明确要求，不得破坏当前需求和已有功能：
- 用户体验：信息清楚、操作顺畅、反馈及时。
- 开发体验：结构清晰、改动易维护、验证路径明确。
- AI Agent 使用体验：规则和接口易发现、描述无歧义、执行步骤可验证。
- 精简技能文档：技能描述使用简洁、易懂的文字，删除重复和次要内容。删减后若无法理解，应重写信息结构和说明，而不是继续堆叠文字。
- 保持代码简洁：优先用清晰、简单、可维护的实现完成需求。先确认底层是否已有容错处理，再决定是否补充；避免无意义的
try/catch、if/return和其他冗余代码。 - 确认开发阶段：修改或重构前，依据项目文档、任务要求或负责人确认判断项目是否处于开发阶段。开发阶段可按新方案移除仅服务于旧版本的代码、历史数据和兼容分支，并使用新数据验证；当前需求功能仍需通过验收。非开发阶段则先评估兼容性，再决定迁移或保留策略。
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.
- 2d ago Changed · +11 lines · +399 tokens per session 9b1fa9261ca1
- 18d ago Changed · +128 tokens per session 39072ea21e4f
- 23d ago Changed · +22 tokens per session 20452956f1ad
- 1mo ago Changed · -131 lines · -1,012 tokens per session 464bd227a8eb
- 2mo ago First seen · 208 lines · 2,364 tokens per session scan A abe6186b0d3e
DGame AGENTS.md is an instructions file published in the GitHub repository AmaniDawn/DGame (177 stars, last pushed 3d ago), licensed MIT. It adds 1,901 tokens to every session, about $0.0076 per session on Opus 5.5. 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 instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.