Borrowing it
Nothing to install: this file belongs to RandyChen1985/nanzi-ai-agent-platform. 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/RandyChen1985/nanzi-ai-agent-platform/main/AGENTS.mdgit clone --depth 1 https://github.com/RandyChen1985/nanzi-ai-agent-platformWrote 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/randychen1985/nanzi-ai-agent-platform/agents-md)<a href="https://agentmods.dev/instructions/randychen1985/nanzi-ai-agent-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/randychen1985/nanzi-ai-agent-platform/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/randychen1985/nanzi-ai-agent-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/randychen1985/nanzi-ai-agent-platform/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 | $0.01293 | $0.01293 |
| Opus 5.5 | $0.00517 | $0.00517 |
| Sonnet 5.5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
nanzi-ai-agent-platform 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 3d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
交流语言
- 始终使用中文交流，包括中间过程中的推理与思考，以及所有回复、汇报与文档说明。所有说明请优先用中文。与用户沟通、解释、总结时一律使用中文。
项目技术栈与关键边界
- 运行时：Python 3.11；Docker 基础镜像为
python:3.11-slim。禁止使用仅 Python 3.12+ 支持的语法。 - 后端：FastAPI + Uvicorn + SQLAlchemy 2.x 异步 ORM + Pydantic 2。
- 前端：Vue 3 + TypeScript + Vite 7 + Tailwind CSS 3，按现有 Vue 工程实现，不引入 React 方向的方案。
- AI 编排：AgentScope 2.x 是主运行时；OpenClaw、RAGFlow、MCP 是独立集成边界。修改路由或执行链前，先追踪 router、dispatcher、runner、tool 和权限预检。
- 数据库：平台主库默认 MySQL，也支持 PostgreSQL。MySQL 使用
db-prod/，PostgreSQL 使用db-prod-pg/，两套迁移不可混用；平台主库与外部数据源支持必须分开处理。 - Redis：Redis Stack/RediSearch 是平台运行依赖。
- 权限：
menu:*控制菜单显示，element:*控制具体功能。平台技能管理和待审核使用element:skills:admin。 - 测试：后端使用 pytest；纯前端契约测试使用
pytest --confcutdir=tests/frontend，前端类型检查使用vue-tsc --noEmit。 - 数据库变更：只新增对应版本的迁移 SQL，不直接修改本地或线上数据库。
- 执行边界：Agent 不主动执行
./dev.sh、部署脚本或生产数据库操作；服务启停和部署由用户在控制台执行。
原型（prototypes/）
用户说「先给我看看效果」「出个 mock」「做个原型」时，按这套流程走：
- 位置：所有原型 HTML 只能放
prototypes/。禁止放html/、docs/、frontend/public/或仓库根目录。 - 命名：
YYYY-MM-DD-<topic>.html，日期是首次创建日，topic 用小写英文连字符（如2026-11-02-knowledge-doc-workspace.html）。一个需求一个文件，多方案做在同一个文件里（tab / 并排），不拆成多个。 - 登记：写完或改名后必须跑
python prototypes/build_index.py，它会重写总览页prototypes/index.html（该页是生成物，不要手工改）。 - 自包含：CSS/JS 内联，不引外部资源，双击即可打开；
<title>写成「功能 · 做了什么」。 - 顺序：先出原型让用户确认，确认后再改实现代码——不要跳过原型直接写实现。
- 完整规范见
prototypes/prototypes.md。
Git 协作：用户说「代码已合」
用户表示 PR/代码已合并后，必须立即执行本地 git 同步，不要只口头确认：
git fetch origin- 切回开发分支：
git checkout dev-agentscope-mcp2.x—— 这是当前唯一的开发分支，日常开发都在它上面。dev-agentscope已废弃，不要再切过去。 - 把刚合并的结果快进回来：
git merge --ff-only origin/main—— PR 固定从dev-agentscope-mcp2.x提到main，合并结果落在origin/main上。 - 汇报：主工作分支最新 commit、与远程是否一致
- 提醒用户自行在控制台执行
./dev.sh（Agent 不代跑）
不要做的事：不 rebase、不对共享分支 push --force（PR 合并已产生 merge commit，改写历史会让远程记录与 PR 对不上）。合并后一律用 --ff-only 快进；出现冲突先汇报再问，不要自行 resolve。
不要在用户未要求时擅自创建 PR 或 force push。
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.
- 3d ago Changed · +11 lines · +286 tokens per session 1d63ba026533
- 7d ago Changed · +5 lines · +176 tokens per session 012c47dbcadc
- 2mo ago Changed · +7 tokens per session 46261821c934
- 2mo ago First seen · 38 lines · 824 tokens per session scan A 2ca55a5b9274
nanzi-ai-agent-platform AGENTS.md is an instructions file published in the GitHub repository RandyChen1985/nanzi-ai-agent-platform (228 stars, last pushed yesterday), licensed MIT. It adds 1,293 tokens to every session, about $0.0052 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 2026-08-30.
nanzi-ai-agent-platform AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nanzi-ai-agent-platform AGENTS.mdRandyChen1985/nanzi-ai-agent-platform | Instructions file | 228 | yesterday | MIT | A | 1,293 | 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 | today | 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 |