Borrowing it
Nothing to install: this file belongs to fengzhizi715/OpenVitamin. 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/fengzhizi715/OpenVitamin/main/AGENTS.mdgit clone --depth 1 https://github.com/fengzhizi715/OpenVitaminWrote 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/fengzhizi715/openvitamin/agents-md)<a href="https://agentmods.dev/instructions/fengzhizi715/openvitamin/agents-md"><img src="https://agentmods.dev/badge/instructions/fengzhizi715/openvitamin/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/fengzhizi715/openvitamin/agents-md"><img src="https://agentmods.dev/badge/instructions/fengzhizi715/openvitamin/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 | $0.01520 | $0.01520 |
| Opus 5 | $0.00760 | $0.00760 |
| Sonnet 5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
OpenVitamin 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 9d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Inference Gateway & Plugin Governance
本文件是本项目中 优先级最高的行为与架构约束文档之一。
所有 Agent / Plugin / 推理适配层的设计与实现，必须遵循本规范。
1. 项目与技术栈对齐说明
本项目是一个 Web 形态的本地 AI 推理平台，整体架构为：
-
前端（UI 层）：Vue 3 + Vite + Tailwind CSS + shadcn-vue
-
后端（核心中枢）：Python + FastAPI
-
角色定位：
- Web UI 只是“控制台”
- FastAPI 推理网关是“大脑”
- Agent / Plugin 是“能力模块”
-
后端的程序，都要在虚拟环境 conda 中运行。
本文件定义的 Agent，并不等同于“自主智能体”，而是指：
- 推理网关中的系统模块
- 推理后端的统一封装代理
- 以插件形式加载的能力增强模块
2. 核心设计原则（Core Principles）
所有 Agent / Plugin 必须遵循 以下原则：
2.1 User-in-Control（用户始终掌控）
- Agent 不得擅自改变用户意图
- 默认不启用任何“自动决策”或“隐式代理”行为
2.2 Gateway-Centric（以推理网关为中心）
- 所有模型调用必须经过 FastAPI 推理网关
- 前端不得直连模型、推理引擎或工具
2.3 Determinism over Magic（确定性优于魔法）
- 禁止隐藏 Prompt
- 禁止隐式参数注入
- 行为必须可预测、可复现
2.4 Plugin-first（插件优先）
- 新能力优先设计为插件
- 插件必须可独立启停、替换、升级
2.5 Local-first & Privacy-first（本地与隐私优先）
- 默认假设系统运行在 无外网环境
- 不得未经授权进行任何数据外传
3. Agent 分类（Agent Taxonomy）
3.1 Gateway System Agents（系统代理）
位置：FastAPI 推理网关核心层
职责：
- 请求规范化（Request Normalization）
- 模型路由与选择
- 流式响应协调（SSE / Streaming）
- 错误捕获与恢复
约束：
- ❌ 不得包含业务逻辑
- ❌ 不得访问外部网络或文件系统
3.2 Model Agents（模型代理 / 推理适配层）
对不同推理后端的统一封装。
示例：
- OpenAI / API Agent
- Ollama Agent
- vLLM Agent
- llama.cpp Agent
职责：
- 将统一请求转换为后端调用
- 统一流式输出格式
- 明确暴露模型能力边界
约束：
- ❌ 不得修改用户输入语义
- ❌ 不得注入隐藏 Prompt 或系统提示
3.3 Capability Agents（能力插件）
以 插件形式 挂载在推理流程中的增强模块。
示例：
- RAG Agent（本地知识库）
- Tool Calling Agent
- Memory / History Agent
- Workflow / Agent Agent
职责：
- 明确声明权限与依赖
- 对输入输出负责
约束：
- 必须可被禁用
- 必须可观测、可审计
4. Agent / Plugin 生命周期
所有 Agent / Plugin 必须遵循以下生命周期：
load → initialize → ready → execute → teardown
规则：
- Agent 应尽量无状态
- 必须支持优雅失败（graceful failure）
5. Agent / Plugin 接口规范
每个 Agent / Plugin 必须声明：
- name（名称）
- type（system / model / capability）
- version（版本）
- stage（pre / post / tool / router）
- input schema
- output schema
- required permissions
可选声明：
- configuration schema
- 前端 UI Hint（供 Web UI 自动渲染配置面板）
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.
- 9d ago First seen · 245 lines · 1,520 tokens per session scan A 9e6be5810a20
OpenVitamin AGENTS.md is an instructions file published in the GitHub repository fengzhizi715/OpenVitamin (76 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,520 tokens to every session, about $0.0076 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.