Borrowing it
Nothing to install: this file belongs to ZuiTiti/Zuiti-Desktop. 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/ZuiTiti/Zuiti-Desktop/main/AGENTS.mdgit clone --depth 1 https://github.com/ZuiTiti/Zuiti-DesktopWrote 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/zuititi/zuiti-desktop/agents-md)<a href="https://agentmods.dev/instructions/zuititi/zuiti-desktop/agents-md"><img src="https://agentmods.dev/badge/instructions/zuititi/zuiti-desktop/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/zuititi/zuiti-desktop/agents-md"><img src="https://agentmods.dev/badge/instructions/zuititi/zuiti-desktop/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 | $0.02083 | $0.02083 |
| Opus 5 | $0.01042 | $0.01042 |
| Sonnet 5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
Zuiti-Desktop 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件给后续在本仓库工作的 AI 编码代理使用。目标是让改动贴合 Zuiti 的架构、隐私边界和本地优先状态策略。
项目概览
Zuiti 是一个 Electron + React + TypeScript 桌面宠物应用。渲染进程负责透明悬浮 UI、已校验宠物包渲染、数据驱动 motion 执行和锚点道具叠加;主进程负责系统能力、LLM 调用、上下文快照、active pet package 加载校验、vision、memory、behavior、motion plan 校验和 SVG prop skills。
核心数据流:
- 用户输入、周期触发或窗口切换进入主进程行为决策。
- 主进程从
ENABLED_PET指定的pet_resources/pets/<pet_id>/读取 active pet 包,并把visionSummary、memoryText、skillIndex、motion tool prompt 和短期对话窗口放入稳定快照。 textAgent基于稳定快照输出dialogue、mood_tag、可选motion_plan和可选prop_intent。- 主进程按 active pet manifest 校验 motion plan;skills 模块从 active pet 的 enabled 道具 skill 中选择,或生成、校验、审核新的 SVG prop skill。
- 主进程通过 IPC 把只读宠物渲染包、mood、对白和 activity 发给 renderer。
主回复 prompt 的稳定顺序是:
SOUL -> motion tool prompt -> memory -> skill index -> recent window -> current event
目录地图
src/main/:Electron 主进程、LLM provider、vision、memory、skills、behavior、IPC 注册。src/preload/:安全暴露给 renderer 的window.zuitiAPI。src/renderer/src/:React UI、Zustand store、IPC wiring、桌宠和气泡组件。src/shared/types.ts:跨进程共享类型与 IPC channel 常量。pet_resources/:主进程加载的宠物包根目录,存放内置宠物骨架、部件 SVG、表情、motion tools、prompt、memory、skills 和PET_SKELETON_STANDARD.md。resources/:Electron 图标和构建资源,不放宠物骨架资源。docs/:架构与模块文档。改动模块行为时同步更新对应文档。tests/:Node test runner 单元测试,使用scripts/register-ts.cjs注册 TS 源码。pet_resources/pets/default-cat/memory/SOUL.md:默认猫人格源文件,应纳入版本控制。pet_resources/pets/default-cat/memory/memory.example.md:长期记忆示例。pet_resources/pets/default-cat/skills/example-soft-wave/:可提交的示例 skill 包。
运行命令
常用命令:
npm install
npm run dev
npm run test:unit
npm run typecheck
npm run lint
npm run build
提交前优先运行:
npm run test:unit
npm run typecheck
npm run lint
涉及打包、Electron 配置或跨进程入口时,再运行:
npm run build
开发环境要求见 docs/modules/development.md。ENABLED_PET=default-cat 选择 active pet 包;LLM_PROVIDER=mock 可离线启动基础流程;接入真实模型时需要配置 .env,但不要提交 .env。
编码约定
- 使用 TypeScript,遵守现有 ESLint、Prettier 和 electron-vite 结构。
- 优先复用本仓库已有模块边界,不要把主进程职责塞进 renderer。
- 跨进程协议统一从
src/shared/types.ts扩展;新增 IPC channel 时同步更新 preload API 和 renderer 类型。 - renderer 只通过
window.zuiti与主进程交互,不直接使用 Node/Electron 主进程能力。 - 新增 UI 状态优先放在现有 renderer store / hook 结构中,保持
PetView、BubbleLayer、SettingPanel职责清晰。 - 宠物包资源放在
pet_resources/pets/<pet_id>/,并遵守pet_resources/PET_SKELETON_STANDARD.md;不要把骨架资源放进 Electron 的resources/。 - renderer 不把整个
pet_resources/作为 publicDir;memory 和 runtime skills 只由主进程读写,renderer 只能通过window.zuiti.petPackageGet()获取校验后的只读渲染包。 - 骨架动作只暴露 active pet manifest 里的受限语义 motion tool;新增 tool 时更新该 pet 的 manifest、prompt、mood fallback 和测试,不要在系统代码里硬编码 tool 名称。
- 主进程后台任务应避免阻塞用户输入路径;文本回复优先使用最近完成的稳定快照。
- 注释保持简短,只解释不明显的安全、隐私或异步时序原因。
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 · 141 lines · 2,083 tokens per session scan A 11a09a8f2710
Zuiti-Desktop AGENTS.md is an instructions file published in the GitHub repository ZuiTiti/Zuiti-Desktop (5 stars, last pushed 4mo ago), licensed MIT. It adds 2,083 tokens to every session, about $0.0104 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 2026-08-31.
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.
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.