Borrowing it
Nothing to install: this file belongs to PiscesGameDev/UniAI. 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/PiscesGameDev/UniAI/main/CLAUDE.mdgit clone --depth 1 https://github.com/PiscesGameDev/UniAIWrote 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/piscesgamedev/uniai/claude-md)<a href="https://agentmods.dev/instructions/piscesgamedev/uniai/claude-md"><img src="https://agentmods.dev/badge/instructions/piscesgamedev/uniai/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 | $0.04404 | $0.04404 |
| Opus 5 | $0.02202 | $0.02202 |
| Sonnet 5 | $0.00881 | $0.00881 |
| Haiku 4.5 | $0.00440 | $0.00440 |
Grade A, and why
UniAI 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UniAI - AI Assistant Guide
本文档面向参与 UniAI 开发的 AI 助手。它不是用户手册,面向用户的说明见
README.md。修改框架前请先读本文件,避免把模型差异、Editor 行为或生成式路由重新写回错误层级。
包名: com.uniai.core
版本: 0.0.1
Unity: 2022.3+
许可证: Apache 2.0
1. 框架定位
UniAI 是 Unity 与 AI Provider 之间的运行时框架,同时提供 Editor 助手能力。核心目标是让 Unity 项目可以通过统一 C# API 使用 Chat、Agent、Tool、MCP、多模态输入、上下文窗口和生成式资产。
当前架构重点:
- 统一请求模型: 上层只接触
AIRequest、AIResponse、AIStreamChunk、AIMessage、AIContent。 - 多协议 Provider: 内置 Claude Messages API 与 OpenAI Chat Completions 兼容协议。
- 模型元数据驱动:
ModelEntry描述能力、端点、上下文窗口、AdapterId、行为标志和行为参数。 - Adapter/Dialect 扩展: Provider 主流程保持通用,模型或厂商差异放进 adapter/dialect。
- Agent Tool Loop:
AIAgentRunner是门面,实际 loop、工具执行和 tool-call history 构造已拆分。 - 生成式路由: 生成图片等资产由
GenerativeProviderRouter按模型元数据、渠道和 adapter 决定 provider。 - Runtime/Editor 分层: Runtime 不依赖
UnityEditor;Editor 只负责 UI、配置管理和 Unity 上下文采集。
不要把 UniAI 当成单一聊天窗口项目。Runtime API 和 Editor Chat 都是一等使用场景。
2. 当前目录职责
Runtime/
├── Core/
│ ├── AIClient / AIConfig / ChannelEntry / UniAISettings
│ ├── ChannelManager / ChannelRouteSelector / ProviderCache
│ ├── ModelRegistry / ModelEntry / ModelCapability
│ ├── Presets/ # 内置渠道与模型预设
│ ├── Adapters/ # AdapterAttribute / Catalog / Registry / Discovery
│ ├── ChatOrchestrator # 对话生命周期编排
│ ├── ConversationRuntimeFactory # Client、Runner、ContextPipeline 生命周期
│ ├── ConversationContextPreparer # ChatSession -> AIMessage + 上下文注入
│ ├── McpConversationInitializer # Agent MCP 初始化与 Resource 注入
│ ├── AgentEventSessionApplier # AgentEvent -> ChatSession
│ └── ChatSessionPolicies # 保存和标题策略
├── Models/ # 统一请求、响应、消息、工具、流式块
├── Providers/
│ ├── IAIProvider / IAIProviderFactory
│ ├── JsonSseProviderBase
│ ├── Claude/
│ └── OpenAI/
│ └── Chat/ # OpenAI Chat dialect 和 request converter
├── Agent/
│ ├── AIAgentRunner # Agent 门面
│ ├── AgentLoop # stream/non-stream tool loop
│ ├── AgentToolExecutor # 本地 Tool + MCP Tool 执行
│ ├── AgentMessageFactory # assistant tool-call history
│ └── UniAIToolRegistry / ToolSchemaGenerator / ToolResponse
├── Chat/ # ChatSession、历史管理和文件存储
├── Context/ # ContextPipeline、TokenEstimator、摘要、IContextProvider
├── MCP/ # MCP Client、Transport、Resource Provider
├── Generative/
│ ├── GenerativeProviderRouter
│ ├── IGenerativeProviderFactory
│ ├── IGenerativeAssetProvider
│ └── Providers/OpenAI/Images/ # OpenAI Images provider + image dialect
├── Tools/ # Runtime 可用 [UniAITool]
└── Http/ # AIHttpClient、SSEDownloadHandler、SSEParser
Editor/
├── Setting/ # Manager 窗口、配置 Tab、AIConfigManager
├── Chat/ # AIChatWindow、StreamingController、ContextCollector
├── Agent/ # Agent 资产扫描、Inspector、EditorAgentGuard
├── MCP/ # MCP 配置 UI
└── Tools/ # Editor 专用 [UniAITool]
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.
- 8d ago First seen · 397 lines · 4,404 tokens per session scan A f73d9f0617a1
UniAI CLAUDE.md is an instructions file published in the GitHub repository PiscesGameDev/UniAI (30 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 4,404 tokens to every session, about $0.0220 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 2026-08-30.
Other instructions, from other repositories
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.
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).
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).
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.
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.