Borrowing it
Nothing to install: this file belongs to vien-meng/vien-skills. 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/vien-meng/vien-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/vien-meng/vien-skillsWrote 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/vien-meng/vien-skills/agents-md)<a href="https://agentmods.dev/instructions/vien-meng/vien-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vien-meng/vien-skills/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/vien-meng/vien-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vien-meng/vien-skills/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 | $0.01008 | $0.01008 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
vien-skills 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.
What it actually says
通用项目开发 SOP（generic-dev-sop）
本文件是 vien-skills 的通用适配器：Codex、OpenCode、Gemini、Kimi 等读 AGENTS.md 的平台均可使用。完整模板见
skills/generic-dev-sop/references/，skill 主文件为skills/generic-dev-sop/SKILL.md。
把项目从零到交付作为可追踪闭环：搭建底座 → 规划任务 → 单功能闭环 × N → 完整交付。每项功能把「计划、契约、UI、实现、测试、证据」同步交付，禁止只做底层逻辑、接口或 UI Mock 后宣称完成。纯文案/无行为变化的单行修改可跳过步骤；无 UI 的后端功能可跳过设计稿，但必须说明原因。
适用：从零搭建新项目，或对已有项目继续迭代（复用架构与质量底座，每个新需求仍按「需求分析 → UI 设计稿 → 任务计划 → 开发 → 验收」闭环）。纯文案/单行修改、一次性脚本或原型不走完整流程；小型项目可跳过灰度/合规等交付门禁。
状态仅使用：未开始、分析中、设计确认、开发中、审查测试中、已完成、阻塞。
生命周期
- 项目搭建：确认工程边界 → 确认技术栈 → 输出架构决策 → 输出任务计划 → 搭质量底座 → 建开发记录机制。
- 详细任务计划：执行原则、交付定义（真实闭环，不是「页面都能点」）、范围/估算/关键路径、阶段总览、详细任务（每条含验收条件）、功能矩阵（P0/P1/P2）、质量门禁、团队边界、第一批执行顺序。
- 单功能开发闭环（每个功能循环）：确认计划进度 → 需求分析 → 最小方案 → 写开发记录 → 设计稿（有 UI 先出默认/加载/空/错误/禁用/无权限/离线状态）→ 数据结构（先定模型/校验/迁移）→ 开发（复用现有模式）→ 审查测试（按审查清单 + 留最小可运行检查）→ 回写进度（证据一致才标记完成）。
- 完整交付：发布候选门禁 → 灰度与回滚 → 文档同步 → 项目交付检查（P0 功能矩阵全绿，无「页面有数据假」「接口有客户端不可达」）。
技术栈确认
启动前先与用户确认技术栈：用户指定则以用户为准；未指定或直接回车 = 同意使用默认。默认组合（已验证）：Web/桌面 = Electron + React + Vite + MobX + Ant Design + i18next（单构建同时出 Web 与桌面）；跨端移动 = Flutter + Riverpod + GoRouter + Dio + just_audio；服务端 = NestJS + PostgreSQL/PostGIS + TypeORM + Redis + Swagger + JWT/RBAC + Winston。
核心规则
- 单一业务真相：主库是唯一事实来源，缓存/实时事件可丢失且可恢复。
- 有 UI 先出覆盖各状态的静态稿再写代码；无 UI 要说明依据。
- 非平凡逻辑留一个最小可运行检查；日常跑变更测试 + 直接调用链 + typecheck + 受影响 lint，全量门禁在阶段出口、重构、发布前执行。
- 跨模块用路径别名，禁止
../../../；所有声明模块正上方写多行中文注释。 - 密钥只存环境变量/安全存储，日志脱敏；写接口做归属校验；外部输入先校验再进业务代码。
- 平台差异用运行时适配器判断，禁止构建分叉。
- 交付 = 计划、契约、设计稿、实现、测试、文档一致。
模板与清单
完整模板在本仓库 skills/generic-dev-sop/references/：architecture-template.md、task-plan-template.md、development-record-template.md、coding-standards.md、review-checklist.md、default-stack.md。单功能记录复制 development-record-template.md 到 references/features/<功能短名>.md 并全程回写。
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 · 35 lines · 1,008 tokens per session scan A a8e16364a832
vien-skills AGENTS.md is an instructions file published in the GitHub repository vien-meng/vien-skills (10 stars, last pushed 26d ago), licensed Apache-2.0. It adds 1,008 tokens to every session, about $0.0050 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.