What is Aurevoy AGENTS.md?

A project guide for Aurevoy, a desktop app in which users give an AI agent goals and the agent plans, uses tools, and carries out the work.

Use it when changing Aurevoy’s desktop, web, agent, shared-type, API, documentation, or build-related code.

It gives contributors a shared map of the product, architecture, documentation, build commands, and collaboration rules.

How nullskymc/Aurevoy configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to nullskymc/Aurevoy. 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/nullskymc/Aurevoy/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/nullskymc/Aurevoy

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nullskymc/aurevoy/agents-md/github.svg)](https://agentmods.dev/instructions/nullskymc/aurevoy/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nullskymc/aurevoy/agents-md"><img src="https://agentmods.dev/badge/instructions/nullskymc/aurevoy/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nullskymc/aurevoy/agents-md"><img src="https://agentmods.dev/badge/instructions/nullskymc/aurevoy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,398 This file is loaded in full into every session.

When invoked 1,398 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.

Model	Per session	Once invoked
Fable 5.1	$0.01398	$0.01398
Opus 5.5	$0.00559	$0.00559
Sonnet 5.5	$0.00280	$0.00280
Haiku 4.5	$0.00140	$0.00140

Measured 2mo ago against content hash cd929b3acef0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Aurevoy 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 2mo 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.

AGENTS.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Aurevoy 协作入口

参与本仓库的智能体/人类先读本文，再按需下钻 docs/。

产品

Aurevoy 是本地个人 AI Agent 桌面应用：用户用自然语言给目标，引擎规划、调工具、持续执行直至完成。

版本：v0.6.8（已发布 tag v0.6.8；上一版 v0.6.7）
形态：支持 macOS、Windows 和 Linux 桌面端；各平台通过 Tauri 构建对应安装包与更新产物
原则：真实链路、可恢复、可审计；禁止 Mock / 假能力

架构（30 秒）

apps/desktop (Tauri) + packages/web-ui (React)
              │  HTTP + SSE (127.0.0.1:8787)
              ▼
         apps/agent (Node + Fastify + Pi AgentHarness)
              ├── LLM (多协议)  ·  Tools (Effect + MCP)
              └── SQLite (任务 / 轨迹 / 记忆 / KB)
packages/shared  ← 跨进程类型唯一来源

主循环固定走 Pi runtime；LLM 等产品配置走设置页 / SQLite，env 仅运维面。详见 ARCHITECTURE。

文档地图

文档	用途
本文	入口、规则、命令
ARCHITECTURE	模块与数据流
API	HTTP + SSE 契约说明
UI_DESIGN	交互与界面边界
CONVENTIONS	代码与扩展约定
TECH_STACK	选型理由
ROADMAP	已完成能力 + 未竟项
文档站	用户文档：`docs/guide/`（quickstart / prompting / best-practices…）；开发者：`docs/dev/` + 下文协作页 → aurevoy.nullskymc.site

类型真相在 packages/shared/src/，API 细节以代码为准。用户可见行为变化时优先改 docs/guide/（可操作步骤 + 示例 + 反例）；契约/架构变化再改协作参考页。

文档站：npm run docs:dev / docs:build / docs:preview。推送 docs/** 到 main/dev 时由 .github/workflows/docs.yml 部署 Pages。

硬性规则

跨进程数据结构只定义在 packages/shared；涉及 shared 改动的单个任务完成时必执行 npm run build:shared。
新工具放 apps/agent/src/tool/tools/，经 framework/registry 注册；不写进 Agent loop。
新 Provider 扩展 Pi 映射，不恢复第二套 ReAct 后端。
后端不绑 macOS 路径/命令；前端不假设非 Tauri 环境。
外部能力缺失时明确失败/降级，不假成功。
验证分层：单个任务完成时至少 npm run typecheck；行为/安全/存储改动补定向回归或可复现轨迹。提交前按改动影响面跑相关回归即可（见下方命令表），不必每次全套 m3–m8；完整回归仅在发布/合并前统一执行。
密钥只走环境变量 / 设置存储，禁止提交。
新能力同步考虑：日志、审批、权限、失败恢复、用户可解释性。

命令

npm install              # workspace 依赖（Node >= 22.19.0）
npm run dev              # 引擎 + 桌面
npm run dev:agent        # 仅引擎热重载
npm run typecheck        # 全仓类型检查
npm run build            # shared → agent → desktop
npm run build:shared     # 改 shared 后必做
npm run regression:m3    # 文件工具/工作区（工具改动 → m3+m7）
npm run regression:m4    # 多轮对话/历史（LLM/对话改动 → m4+m7）
npm run regression:m5    # 项目工作区切换
npm run regression:m6    # 记忆/Session Tree（记忆改动 → m6+m8）
npm run regression:m7    # agent 循环/工具 schema/MCP/审批（通用联动）
npm run regression:m8    # 知识库/向量检索（KB 改动 → m6+m8）
npm run regression:*     # 提交前按影响面选跑；全套留给发布/合并前
npm run docs:dev         # 文档站本地预览

Read the full file on GitHub · 87 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.

2mo ago First seen · 87 lines · 1,398 tokens per session scan A cd929b3acef0

Subscribe to this mod's changes

Aurevoy AGENTS.md is an instructions file published in the GitHub repository nullskymc/Aurevoy (9 stars, last pushed 3mo ago), licensed MIT. It adds 1,398 tokens to every session, about $0.0056 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 2026-08-31.

LLM agent agent-loops ai-agent workflow

Aurevoy AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Aurevoy AGENTS.mdnullskymc/Aurevoy	Instructions file	9	3mo ago	MIT	A	1,398	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Aurevoy: Instructions file for Codex