Borrowing it
Nothing to install: this file belongs to shuxueshuxue/gugu-docs. 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/shuxueshuxue/gugu-docs/main/AGENTS.mdgit clone --depth 1 https://github.com/shuxueshuxue/gugu-docsWrote 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/shuxueshuxue/gugu-docs/agents-md)<a href="https://agentmods.dev/instructions/shuxueshuxue/gugu-docs/agents-md"><img src="https://agentmods.dev/badge/instructions/shuxueshuxue/gugu-docs/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/shuxueshuxue/gugu-docs/agents-md"><img src="https://agentmods.dev/badge/instructions/shuxueshuxue/gugu-docs/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 | $0.00775 | $0.00775 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
gugu-docs 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 10d 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.
What it actually says
给写这份文档的 agent
产品是什么
咕咕（Gugu）是一个聊天客户端，通讯录里除了人还有 AI agent。用户给 agent 发消息派活，agent 在用户指定的某台机器、某个目录里干活，边干边回消息。桌面版 macOS + Windows，手机版 Android。
它不是 SaaS 内容平台，没有 dashboard，没有 tags/collections，没有公开 REST API，没有 API key，没有密码登录，也没有第三方账号登录。
已知真实的域名只有这几个：
- 官网
https://gugu.nextmind.space - 下载
https://download.gugu.nextmind.space/releases/{mac,windows,android}/latest/... - 产品仓库
nmhjklnm/gugu（私有）
gugu.app 及其任何子域都不是咕咕的域名。写进文档前先解析一遍。
事实从哪里取
按可信度排序：
- 产品仓库的 spec 树（
.spec/project/...，一百多个节点）。每个节点的spec.md写的是当前意图和不变量，code:/related:指向它治理的源文件。这是第一手来源。 - 源码里用户看得见的字符串。UI 上的档位名、徽标提示、toast 文案，以代码为准——spec 正文里的叫法可能是旧的。写倾听模式时 spec 说「随时/被叫/沉默」，界面上其实是「被动/自适应/主动」。
- 运行中的产品。截图、实际点一遍。
- 官网和 README。它们是宣传文案，句子可能领先于实现，只能当线索，不能当出处。
不能写的东西
- 没有出处的功能。 找不到出处就不写。一句都不要编。
- 禁用占位当成功能。 agent 设置里的「AI 模型、权限、密钥、技能、记忆、财务」标着「即将开放」，后端没接。类似的占位随时会有新的，写之前确认那个面板是不是真的能用。
- 内部术语。 读者是科研工作者，不是咕咕的开发者。ACP、provision、RLS、投影、落地页、harness 这些不要出现在正文里。
- 内部设计沿革。 「不是只帮你填个群名」这种对照的是一个读者从没见过的旧实现，删掉。
文风
用 deslop 审。写完跑：
python3 ~/.claude/skills/deslop/scan.py --strip *.mdx
三个数：词表命中、对偶反转、破折号。当前基线是 4 / 0 / 0，破折号必须是 0——中文列表项用冒号，不用 ——。
其余按 deslop 的规矩：物理动词作用在抽象对象上要换成字面动作；标题命名内容，不叙述阅读路径；每句过一遍「删掉会不会丢信息」。
Mintlify
页面是带 YAML frontmatter 的 MDX，导航在 docs.json。新增页面要同时加进 docs.json 的 navigation.groups，否则站点上打不开。本地预览 mint dev。
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.
- 10d ago First seen · 48 lines · 775 tokens per session scan A 833e277e19e8
gugu-docs AGENTS.md is an instructions file published in the GitHub repository shuxueshuxue/gugu-docs (2 stars, last pushed 17d ago), licensed MIT. It adds 775 tokens to every session, about $0.0039 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).
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.
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.