oryxos: Instructions file for Claude Code

CLAUDE.md

oryxos CLAUDE.md is an instructions file for Claude Code from oryx-labs/oryxos. It costs 6,966 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for OryxOS, a Java application platform for running multiple business-focused AI agents on an organization’s own servers or Kubernetes cluster. They describe its technology choices, modules, and non-negotiable design principles.

In plain words
What is it for?
Use them when modifying agent loops, model providers, memory, tools, HTTP services, persistence, or other Maven modules.
Why use it?
They help an AI coding assistant understand the platform’s architecture and keep changes consistent across its modules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is oryx-labs/oryxos's own configuration. It tells Claude Code how to work on oryxos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oryxos configures →

Reuse

Borrowing it

Nothing to install: this file belongs to oryx-labs/oryxos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/oryx-labs/oryxos/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/oryx-labs/oryxos

Made for: Claude Code.

Wrote 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.

agentmods badge for oryxos CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oryx-labs/oryxos/claude-md.svg)](https://agentmods.dev/instructions/oryx-labs/oryxos/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/oryx-labs/oryxos/claude-md"><img src="https://agentmods.dev/badge/instructions/oryx-labs/oryxos/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,966 This file is loaded in full into every session.
When invoked 6,966 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06966 $0.06966
Opus 5 $0.03483 $0.03483
Sonnet 5 $0.01393 $0.01393
Haiku 4.5 $0.00697 $0.00697

Measured today against content hash 33460f103a94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

oryxos 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 today.

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.

CLAUDE.md · 445 lines

How it starts

The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OryxOS — Claude Code 项目指南

OryxOS 是用 Java 实现的面向企业场景的 Distributed AI Agent OS。装在企业自己的 K8s 或服务器上,作为统一底座运行多个业务 Agent,共享渠道接入、模型路由、工具调用、记忆系统、沙箱执行能力。数据完全留在企业自己的基础设施,不锁任何云生态。

长期目标:走进 Apache 基金会,成为 Apache 顶级项目。

详细背景:docs/DemandAnalysis.md(需求)、docs/TechnicalSolution.md(技术方案)、docs/IndustryResearch.md(业界调研)、docs/AiProgrammingGuide.md(AI 编程指南)、docs/oryxos.md(项目定位)


技术栈

组件 选型
语言 / 运行时 Java 21(必须,virtual thread 处理并发)
框架 Spring Boot 3.x
LLM 调用 Spring AI Alibaba(仅用协议转换 + @Tool schema 生成)
HTTP 服务 Spring MVC + Java 21 Virtual Thread
命令行 Picocli
YAML 解析 SnakeYAML
持久化 SQLite(默认零配置)/ PostgreSQL 14+(部署选项,url 自动识别)+ Spring Data JPA;表结构由 Flyway 管理(db/migration/{vendor}/
日志 Logback + SLF4J(结构化 JSON)
构建 Maven 多模块

模块结构(14 个)

oryxos/
├── oryxos-core          # 核心抽象:OryxTool 接口、Session、Profile、ContextLoader、
│                        #   ReActLoop、PromptBuilder、ToolExecutor、AgentService
├── oryxos-persona       # 025 人格库(copy-in 模板库):PersonaPresetCatalog(内置 12 只读、
│                        #   classpath)、PersonaStore/PersonaService(.oryxos/personas/ 自定义 CRUD)
├── oryxos-provider      # 能力一:ProviderService、Function Calling 适配、
│                        #   多 Provider 显式映射
├── oryxos-memory        # 能力三:MemoryService 门面、LongTermMemory 三档后端、
│                        #   MemoryRecallEngine 三路召回 + MemoryVectorIndex(015)、
│                        #   MemoryTools(save/recall)
├── oryxos-knowledge     # 知识库(014):LocalKnowledgeBackend(契约第一个插件)、
│                        #   解析/切分/向量化索引流水线、双路召回+RRF 检索、
│                        #   ChunkStore 可插拔存储、KnowledgeTools(retrieve_knowledge)
│                        #   (契约与绑定服务在 oryxos-core/knowledge/,依赖倒置)
├── oryxos-tool          # 能力四:内置 Tool(文件/Shell/HTTP)、MCP Client、
│                        #   ToolRegistry、SandboxChecker
├── oryxos-channel-cli   # CLI Channel:oryxos chat 实现
├── oryxos-channel-feishu # 飞书 IM 入站渠道(017):oapi-sdk 长连接收 im.message.receive_v1、
│                        #   FeishuEventNormalizer(@ 判定/剥离)、FeishuMessageSender(分段+沙箱)
│                        #   (入站渠道契约与共享编排在 oryxos-core/channel/,依赖倒置)
├── oryxos-channel-wecom  # 企微智能机器人入站渠道(对称飞书):长连接收消息、免公网回调,
│                        #   WeComEventNormalizer(@ 判定/剥离)、WeComMessageSender(分段+沙箱)
│                        #   (入站渠道契约与共享编排在 oryxos-core/channel/,依赖倒置)
├── oryxos-channel-dingtalk # 钉钉机器人入站渠道(对称飞书/企微):Stream 长连接收消息、
│                        #   DingTalkEventNormalizer(@ 判定/剥离)、DingTalkMessageSender(分段+沙箱)、
│                        #   断线自动重连(对齐企微)
│                        #   (入站渠道契约与共享编排在 oryxos-core/channel/,依赖倒置)
├── oryxos-web           # 能力五:WebServer、ApiController、GlobalExceptionHandler、
│                        #   OpenAPI
├── oryxos-storage       # 持久化:SQLite、SessionRepository、
│                        #   ToolInvocationRepository、LlmCallRepository
├── oryxos-cli           # 命令行入口:Picocli 主入口、13 个子命令、ConfigLoader(025:agent import)
└── oryxos-boot          # Spring Boot 启动模块:主类、自动配置、依赖聚合

Read the full file on GitHub · 445 lines

Changes

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.

  1. today Changed · +50 tokens per session 33460f103a94
  2. 3d ago Changed · +30 lines · +1,266 tokens per session 9134cf05da24
  3. 7d ago First seen · 415 lines · 5,650 tokens per session scan A eeac541a71df

Subscribe to this mod's changes

oryxos CLAUDE.md is an instructions file published in the GitHub repository oryx-labs/oryxos (155 stars, last pushed today), licensed Apache-2.0. It adds 6,966 tokens to every session, about $0.0348 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens